firefrost-gaming/claude-skills-reference
3
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

feat(foundation): create directory structure and standards library

Browse Source 
- Create root-level directories: agents/, commands/, standards/, templates/
- Port 5 core standards from global Claude standards
- Adapt standards for claude-skills context (cs-* prefix, Python tools, skills)
- Create sprint planning documents (context.md, plan.md)
- All directories tracked with .gitkeep files

Standards created:
- communication-standards.md (absolute honesty, zero fluff, pragmatic focus)
- quality-standards.md (Python tool quality, agent workflows, testing)
- git-workflow-standards.md (conventional commits, semantic versioning)
- documentation-standards.md (Markdown standards, living docs, templates)
- security-standards.md (secret detection, dependency security, input validation)

Sprint plan ready for Days 1-6 implementation.

Phase: 1 (Foundation)
Issues: #8, #9
This commit is contained in:
Reza Rezvani
2025-11-05 11:37:53 +01:00
parent baa372a52e
commit e8af39aed6
17 changed files with 2948 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
agents/c-level/.gitkeep Normal file
View File

0
agents/marketing/.gitkeep Normal file
View File

0
agents/product/.gitkeep Normal file
View File

0
commands/.gitkeep Normal file
View File

238
documentation/delivery/sprint-11-05-2025/context.md Normal file
View File

@@ -0,0 +1,238 @@
# Sprint Context: Skill-Agent Integration Phase 1-2
**Sprint ID:** sprint-11-05-2025
**Sprint Name:** Skill-Agent Integration Foundation
**Start Date:** November 5, 2025
**Target End Date:** November 19, 2025
**Duration:** 14 days (2 weeks)
**Sprint Type:** Foundation Build
---
## Sprint Goal
**Primary Goal:**
Build the foundational agent integration system for claude-code-skills, enabling users to invoke specialized cs-* agents that seamlessly integrate with the existing 42 production skills.
**Success Criteria:**
- ✅ Root-level directory structure created (agents/, commands/, standards/, templates/)
- ✅ 5 core standards ported from factory and adapted
- ✅ 5 agents fully implemented (cs-content-creator, cs-demand-gen-specialist, cs-ceo-advisor, cs-cto-advisor, cs-product-manager)
- ✅ Agent template and creation guide complete
- ✅ All relative paths resolve correctly
- ✅ Python tools execute successfully from agent context
- ✅ Documentation updated (README, INSTALL, USAGE, CLAUDE)
- ✅ All quality gates pass
---
## Context & Background
### Why This Sprint?
The claude-code-skills repository currently contains 42 production-ready skills across 6 domains (marketing, C-level advisory, product team, project management, engineering, RA/QM). Each skill includes Python automation tools, knowledge bases, and templates.
**Current Gap:**
- Skills exist as standalone packages
- No orchestration layer for workflows
- Users must manually invoke Python scripts
- No guided workflows or best practices
**Solution:**
Agent integration provides a workflow orchestration layer where specialized agents (cs-* prefix) invoke skills, coordinate Python tools, and guide users through complex multi-step processes.
### Strategic Value
1. **User Experience:** Transform from "tool collection" to "guided workflows"
2. **Marketplace Ready:** Foundation for Anthropic plugin marketplace distribution
3. **Scalability:** Template system enables rapid expansion to 42+ agents
4. **Differentiation:** Only skill library with built-in agent orchestration
---
## Scope
### In Scope (Phase 1-2)
**Phase 1: Core Structure (Days 1)**
- Root-level directory creation
- Standards library (5 files)
**Phase 2: Agent Implementation (Days 2-4)**
- Marketing agents (2)
- C-level agents (2)
- Product agent (1)
- Agent template & creation guide
**Phase 4-5: Documentation & Testing (Days 5-6)**
- Documentation updates (README, INSTALL, USAGE, CLAUDE)
- Comprehensive testing & validation
### Out of Scope (Future Phases)
- Installation script (install.sh) → Phase 3
- Uninstall script (uninstall.sh) → Phase 3
- Remaining 37 agents (project management, engineering, RA/QM) → Future sprints
- Plugin marketplace submission → Phase 6-7
- Backwards compatibility migration → Phase 3
---
## Key Stakeholders
**Primary:**
- Repository users (developers, product teams, marketers, executives)
- Future Anthropic marketplace users
**Secondary:**
- Contributors to claude-code-skills
- Teams using skills in production
---
## Dependencies
### External Dependencies
1. **GitHub Automation** ✅ (Complete)
- Smart-sync workflow configured
- PROJECTS_TOKEN secret added
- Project #9 board configured
- Labels created
2. **Existing Skills** ✅ (Complete)
- 42 production skills
- 97 Python automation tools
- Complete knowledge bases
### Internal Dependencies
1. **Implementation Plan** ✅ (Complete)
- `documentation/implementation/implementation-plan-november-2025.md`
- 50+ pages with detailed specifications
2. **GitHub Issues** ✅ (Complete)
- 8 issues created (#8-#16, excluding #10)
- All linked to Milestone: Skill-Agent Integration v1.0
- All on Project #9 board
3. **Factory Reference** ✅ (Available)
- claude-code-skills-factory project
- Standards files to port
- Agent patterns to reference
---
## Risks & Mitigation
### Risk 1: Relative Path Resolution Failures
**Probability:** Medium
**Impact:** High
**Mitigation:**
- Test paths early and often
- Create validation script for path testing
- Document path patterns in creation guide
**Fallback:** Use absolute paths with environment variables
### Risk 2: Python Tool Execution Issues
**Probability:** Low
**Impact:** Medium
**Mitigation:**
- Test each tool from agent context
- Verify working directory assumptions
- Document execution requirements
**Fallback:** Provide wrapper scripts
### Risk 3: Scope Creep (Trying to do all 42 agents)
**Probability:** High
**Impact:** High
**Mitigation:**
- Strict focus on 5 foundational agents
- Template system enables future expansion
- Document "out of scope" clearly
**Fallback:** Defer additional agents to future sprints
### Risk 4: Documentation Burden
**Probability:** Medium
**Impact:** Medium
**Mitigation:**
- Use agent template to standardize
- Reference existing skill documentation
- Keep agent docs focused on workflows
**Fallback:** Minimal viable documentation for v1.0
---
## Success Metrics
### Quantitative Metrics
- **Directory Structure:** 10 directories created
- **Standards Files:** 5 files ported and adapted
- **Agents Created:** 5 agents fully implemented
- **Documentation Files:** 4 files updated/created
- **Test Coverage:** 100% of agents tested
- **Path Resolution:** 100% success rate
- **Python Tool Execution:** 100% success rate
### Qualitative Metrics
- **User Experience:** Clear, guided workflows in each agent
- **Code Quality:** All quality gates pass
- **Documentation Quality:** Beginner-friendly, actionable
- **Maintainability:** Template enables easy agent creation
- **Architecture:** Clean separation of skills vs agents
---
## Sprint Team
**Lead:** Implementation Team
**Contributors:**
- Documentation Team
- Quality Assurance Team
**Reviewers:**
- Repository Maintainer
- Domain Experts (marketing, C-level, product)
---
## Related Documents
- **Implementation Plan:** `documentation/implementation/implementation-plan-november-2025.md`
- **GitHub Milestone:** [Skill-Agent Integration v1.0](https://github.com/alirezarezvani/claude-skills/milestone/1)
- **Project Board:** [Project #9: @claude-code-skills](https://github.com/users/alirezarezvani/projects/9)
- **GitHub Issues:** #8, #9, #11, #12, #13, #14, #15, #16
- **Factory Reference:** `/Users/rezarezvani/projects/claude-code-skills-factory`
---
## Sprint Schedule Overview
**Week 1 (Nov 5-8):**
- Days 1: Foundation (directories, standards)
- Days 2-4: Agents (marketing, C-level, product)
**Week 2 (Nov 11-15):**
- Days 5-6: Documentation & testing
- Buffer: 3 days for unexpected issues
**Target Completion:** November 15, 2025 (4 days buffer before Nov 19 deadline)
---
## Next Steps
1. ✅ Review sprint plan (context.md + plan.md)
2. ✅ Confirm sprint goals and scope
3. ✅ Begin implementation in optimal order
4. Track progress daily on Project #9 board
5. Update living docs (README, CLAUDE) as we complete phases
---
**Document Version:** 1.0
**Created:** November 5, 2025
**Last Updated:** November 5, 2025
**Status:** Active Sprint

866
documentation/delivery/sprint-11-05-2025/plan.md Normal file
View File

@@ -0,0 +1,866 @@
# Sprint Plan: Skill-Agent Integration Phase 1-2
**Sprint:** sprint-11-05-2025
**Duration:** 14 days (Nov 5 - Nov 19, 2025)
**Target Completion:** Day 6 (Nov 15, 2025) with 4-day buffer
---
## Sprint Execution Strategy
### Critical Path (Must Complete in Sequence)
```
Day 1: Foundation
↓
Days 2-4: Parallel Agent Development
↓
Days 5-6: Documentation & Testing
```
### Work Distribution
- **Sequential Work:** Days 1 (foundation must complete first)
- **Parallel Work:** Days 2-4 (agents can be built concurrently once foundation exists)
- **Final Integration:** Days 5-6 (documentation and testing)
---
## Day 1: Foundation Build (November 5, 2025)
**Goal:** Complete Phase 1 - Establish directory structure and standards library
**Status:** 🎯 START HERE
### Morning Session (3 hours)
#### Task 1.1: Create Root Directory Structure
**GitHub Issue:** [#8 - Create root-level directory structure](https://github.com/alirezarezvani/claude-skills/issues/8)
**Estimated Time:** 30 minutes
**Priority:** P1 - CRITICAL (blocks all other work)
**Steps:**
```bash
# 1. Create agent directories
mkdir -p agents/marketing
mkdir -p agents/c-level
mkdir -p agents/product
# 2. Create commands directory
mkdir -p commands
# 3. Create standards directories
mkdir -p standards/communication
mkdir -p standards/quality
mkdir -p standards/git
mkdir -p standards/documentation
mkdir -p standards/security
# 4. Create templates directory
mkdir -p templates
# 5. Verify structure
tree agents commands standards templates
# 6. Update .gitignore if needed
# (ensure these directories are tracked, not ignored)
```
**Acceptance Criteria:**
- [ ] All 10 directories created
- [ ] No conflicts with existing structure
- [ ] Directories tracked by git
- [ ] Structure matches implementation plan
**Deliverable:** Directory structure ready for content
---
#### Task 1.2: Port Core Standards from Factory
**GitHub Issue:** [#9 - Port core standards from factory](https://github.com/alirezarezvani/claude-skills/issues/9)
**Estimated Time:** 2.5 hours
**Priority:** P1 - HIGH
**Depends On:** Task 1.1 (directories must exist)
**Standards to Port:**
1. **communication-standards.md** (30 min)
```bash
# Source: ~/projects/claude-code-skills-factory/.claude/standards/communication/
# Target: standards/communication/communication-standards.md
```
- Replace factory-specific references → claude-skills context
- Replace rr-* agents → cs-* agents
- Update file paths to root-level structure
- Validate: No broken links, markdown passes linting
2. **quality-standards.md** (30 min)
```bash
# Source: factory/.claude/standards/quality/
# Target: standards/quality/quality-standards.md
```
- Code quality requirements
- Testing standards (focus on Python tool testing)
- Review checklist
3. **git-workflow-standards.md** (30 min)
```bash
# Source: factory/.claude/standards/git/
# Target: standards/git/git-workflow-standards.md
```
- Conventional commits
- Branch naming
- PR requirements
- Commit message templates
4. **documentation-standards.md** (30 min)
```bash
# Source: factory/.claude/standards/documentation/
# Target: standards/documentation/documentation-standards.md
```
- Markdown formatting
- File naming conventions
- Structure requirements
- Living documentation principles
5. **security-standards.md** (30 min)
```bash
# Source: factory/.claude/standards/security/
# Target: standards/security/security-standards.md
```
- Secret detection
- Dependency scanning
- Security checklist
- Vulnerability reporting
**Acceptance Criteria:**
- [ ] All 5 standards files created
- [ ] No factory-specific references
- [ ] All references point to claude-skills architecture
- [ ] Files pass markdown linting
- [ ] Standards are actionable
**Deliverable:** Complete standards library
---
### Afternoon Session (1 hour)
#### Task 1.3: Commit Day 1 Work
**Estimated Time:** 30 minutes
```bash
# Review changes
git status
git diff
# Stage files
git add agents/ commands/ standards/ templates/
# Commit with conventional message
git commit -m "feat(foundation): create directory structure and standards library
- Create root-level directories: agents/, commands/, standards/, templates/
- Port 5 core standards from factory
- Adapt standards for claude-skills context
- Replace rr-* references with cs-* prefix
Phase: 1 (Foundation)
Issues: #8, #9"
# Push to dev branch
git push origin dev
```
#### Task 1.4: Update Issue Status
**Estimated Time:** 15 minutes
```bash
# Close completed issues
gh issue close 8 --comment "✅ Directory structure created and verified"
gh issue close 9 --comment "✅ All 5 standards ported and adapted"
# Move to next phase
gh issue edit 11 --remove-label "status:ready" --add-label "status:in-progress"
```
#### Task 1.5: Day 1 Validation
**Estimated Time:** 15 minutes
- [ ] Run `/review` command (validate YAML, markdown)
- [ ] Verify directory structure exists
- [ ] Verify all 5 standards files created
- [ ] Check for broken links
- [ ] Markdown linting passes
**End of Day 1 Status:**
- ✅ Foundation complete
- ✅ Ready for agent development
- ✅ Issues #8, #9 closed
---
## Days 2-4: Agent Development (November 6-8, 2025)
**Goal:** Implement 5 foundational agents + template
**Strategy:** Can work on agents in parallel (different domains)
### Day 2: Marketing Domain Agents
#### Task 2.1: Create cs-content-creator Agent
**GitHub Issue:** [#11 - Create marketing agents](https://github.com/alirezarezvani/claude-skills/issues/11)
**Estimated Time:** 2 hours
**Priority:** P1 - HIGH
**File:** `agents/marketing/cs-content-creator.md`
**Structure to Create:**
```yaml
---
name: cs-content-creator
description: Create SEO-optimized marketing content with brand voice consistency
skills: content-creator
domain: marketing
model: sonnet
tools: [Read, Write, Bash, Grep, Glob]
---
# Content Creator Agent
## Purpose
[1 paragraph describing what this agent does]
## Skill Integration
**Skill Location:** `../../marketing-skill/content-creator/`
### Python Tools
**Brand Voice Analyzer:**
```bash
python ../../marketing-skill/content-creator/scripts/brand_voice_analyzer.py input.txt
python ../../marketing-skill/content-creator/scripts/brand_voice_analyzer.py input.txt json
```
**SEO Optimizer:**
```bash
python ../../marketing-skill/content-creator/scripts/seo_optimizer.py article.md "primary keyword"
python ../../marketing-skill/content-creator/scripts/seo_optimizer.py article.md "primary keyword" "secondary,keywords"
```
### Knowledge Bases
- Brand Guidelines: `../../marketing-skill/content-creator/references/brand_guidelines.md`
- Content Frameworks: `../../marketing-skill/content-creator/references/content_frameworks.md`
- Social Media Optimization: `../../marketing-skill/content-creator/references/social_media_optimization.md`
### Templates
- Content Calendar: `../../marketing-skill/content-creator/assets/content-calendar-template.md`
- Brand Voice Checklist: `../../marketing-skill/content-creator/assets/brand-voice-checklist.md`
## Workflows
### Workflow 1: Create Blog Post
[Detailed step-by-step workflow]
### Workflow 2: Create Social Media Campaign
[Detailed step-by-step workflow]
### Workflow 3: Analyze Brand Voice
[Detailed step-by-step workflow]
## Integration Examples
[Concrete code examples]
## Success Metrics
[How to measure effectiveness]
## Related Agents
- cs-demand-gen-specialist (acquisition campaigns)
- cs-product-marketing (product launches)
## References
- Skill Documentation: `../../marketing-skill/content-creator/SKILL.md`
- Standards: `../../standards/communication/communication-standards.md`
```
**Testing:**
```bash
# Test relative paths
cd agents/marketing
ls ../../marketing-skill/content-creator/scripts/brand_voice_analyzer.py
ls ../../marketing-skill/content-creator/references/brand_guidelines.md
# Test Python tool execution
python ../../marketing-skill/content-creator/scripts/brand_voice_analyzer.py \
../../marketing-skill/content-creator/SKILL.md
# Back to root
cd ../..
```
**Acceptance Criteria:**
- [ ] Complete YAML frontmatter
- [ ] All relative paths resolve
- [ ] 3 workflows documented
- [ ] Integration examples present
- [ ] Python tools tested
- [ ] No broken links
---
#### Task 2.2: Create cs-demand-gen-specialist Agent
**GitHub Issue:** [#11 - Create marketing agents](https://github.com/alirezarezvani/claude-skills/issues/11)
**Estimated Time:** 2 hours
**Priority:** P1 - HIGH
**File:** `agents/marketing/cs-demand-gen-specialist.md`
**Structure:** Similar to cs-content-creator
- YAML frontmatter
- Skill integration: `../../marketing-skill/marketing-demand-acquisition/`
- Python tool: campaign_analyzer.py
- Workflows: Lead gen, conversion optimization, funnel analysis
**Testing:** Same pattern as Task 2.1
---
### Day 3: C-Level Advisory Agents
#### Task 3.1: Create cs-ceo-advisor Agent
**GitHub Issue:** [#12 - Create C-level agents](https://github.com/alirezarezvani/claude-skills/issues/12)
**Estimated Time:** 2 hours
**Priority:** P1 - HIGH
**File:** `agents/c-level/cs-ceo-advisor.md`
**Structure:**
- YAML frontmatter
- Skill integration: `../../c-level-advisor/ceo-advisor/`
- Python tools: strategic_framework_generator.py, scenario_planner.py, okr_tracker.py
- Workflows: Strategic planning, OKR setting, board deck prep, scenario analysis
---
#### Task 3.2: Create cs-cto-advisor Agent
**GitHub Issue:** [#12 - Create C-level agents](https://github.com/alirezarezvani/claude-skills/issues/12)
**Estimated Time:** 2 hours
**Priority:** P1 - HIGH
**File:** `agents/c-level/cs-cto-advisor.md`
**Structure:**
- YAML frontmatter
- Skill integration: `../../c-level-advisor/cto-advisor/`
- Python tools: tech_stack_analyzer.py, architecture_auditor.py, team_velocity_tracker.py
- Workflows: Tech roadmap, build vs buy, tech debt, team scaling
---
### Day 4: Product Agent + Template
#### Task 4.1: Create cs-product-manager Agent
**GitHub Issue:** [#13 - Create product agent](https://github.com/alirezarezvani/claude-skills/issues/13)
**Estimated Time:** 1.5 hours
**Priority:** P1 - HIGH
**File:** `agents/product/cs-product-manager.md`
**Structure:**
- YAML frontmatter
- Skill integration: `../../product-team/product-manager-toolkit/`
- Python tools: rice_prioritizer.py, customer_interview_analyzer.py
- Workflows: Feature prioritization, interview analysis, roadmap generation, quarterly planning
---
#### Task 4.2: Create Agent Template & Creation Guide
**GitHub Issue:** [#14 - Create agent template and guide](https://github.com/alirezarezvani/claude-skills/issues/14)
**Estimated Time:** 2 hours
**Priority:** P2 - MEDIUM
**File 1:** `templates/agent-template.md`
- Complete structure with YAML frontmatter
- Placeholder sections
- Comments explaining each section
- Reference all 5 completed agents as examples
**File 2:** `documentation/AGENT_CREATION_GUIDE.md`
- Step-by-step creation process
- Naming conventions (cs-* prefix, kebab-case)
- Relative path resolution guide
- Testing checklist
- Validation steps
- Troubleshooting section
---
#### Task 4.3: Commit Days 2-4 Work
**Estimated Time:** 30 minutes
```bash
# Review all agents
git status
git diff agents/
# Stage agents
git add agents/marketing/cs-content-creator.md
git add agents/marketing/cs-demand-gen-specialist.md
git add agents/c-level/cs-ceo-advisor.md
git add agents/c-level/cs-cto-advisor.md
git add agents/product/cs-product-manager.md
git add templates/agent-template.md
git add documentation/AGENT_CREATION_GUIDE.md
# Commit
git commit -m "feat(agents): implement 5 foundational agents and template
- Create cs-content-creator (marketing domain)
- Create cs-demand-gen-specialist (marketing domain)
- Create cs-ceo-advisor (C-level domain)
- Create cs-cto-advisor (C-level domain)
- Create cs-product-manager (product domain)
- Create agent template for future expansion
- Add comprehensive agent creation guide
All agents tested with relative path resolution and Python tool execution.
Phase: 2 (Agents)
Issues: #11, #12, #13, #14"
# Push
git push origin dev
```
#### Task 4.4: Update Issue Status
```bash
# Close completed issues
gh issue close 11 --comment "✅ Marketing agents (cs-content-creator, cs-demand-gen-specialist) implemented and tested"
gh issue close 12 --comment "✅ C-level agents (cs-ceo-advisor, cs-cto-advisor) implemented and tested"
gh issue close 13 --comment "✅ Product agent (cs-product-manager) implemented and tested"
gh issue close 14 --comment "✅ Agent template and creation guide complete"
# Start documentation phase
gh issue edit 15 --remove-label "status:backlog" --add-label "status:in-progress"
```
**End of Day 4 Status:**
- ✅ 5 agents implemented
- ✅ Agent template created
- ✅ Creation guide complete
- ✅ Issues #11, #12, #13, #14 closed
---
## Days 5-6: Documentation & Testing (November 11-12, 2025)
**Goal:** Update project documentation and validate all deliverables
### Day 5: Documentation Updates
#### Task 5.1: Update README.md
**GitHub Issue:** [#15 - Update project documentation](https://github.com/alirezarezvani/claude-skills/issues/15)
**Estimated Time:** 1 hour
**Sections to Add:**
1. **Quick Start** (add near top)
```markdown
## 🚀 Quick Start
### Installation
```bash
git clone https://github.com/alirezarezvani/claude-skills.git
cd claude-skills
# TODO: ./install.sh (Phase 3)
```
### Use Your First Agent
```bash
# Invoke content creator agent
claude-code --agent cs-content-creator
# Or use directly in workflows
```
See [INSTALL.md](INSTALL.md) for detailed setup.
```
2. **Agent Catalog** (new section)
```markdown
## 🤖 Agent Catalog
Specialized agents that orchestrate skills and provide guided workflows.
| Agent | Domain | Skills Used | Description |
|-------|--------|-------------|-------------|
| [cs-content-creator](agents/marketing/cs-content-creator.md) | Marketing | content-creator | SEO-optimized content with brand voice |
| [cs-demand-gen-specialist](agents/marketing/cs-demand-gen-specialist.md) | Marketing | marketing-demand-acquisition | Lead gen and conversion optimization |
| [cs-ceo-advisor](agents/c-level/cs-ceo-advisor.md) | C-Level | ceo-advisor | Strategic planning and OKR setting |
| [cs-cto-advisor](agents/c-level/cs-cto-advisor.md) | C-Level | cto-advisor | Tech roadmap and architecture decisions |
| [cs-product-manager](agents/product/cs-product-manager.md) | Product | product-manager-toolkit | RICE prioritization and roadmapping |
[View all 42 skills →](README.md#skills-overview)
```
3. **Skills vs Agents** (explanation section)
```markdown
## 💡 Skills vs Agents
**Skills** = Python tools + knowledge bases + templates
- 42 production-ready skills
- 97 automation tools
- Domain expertise packaged
**Agents** = Workflow orchestrators
- Invoke skills intelligently
- Guide multi-step processes
- Coordinate tools and knowledge
**Example:** cs-content-creator agent uses the content-creator skill's Python tools (brand_voice_analyzer.py, seo_optimizer.py) plus knowledge bases (brand guidelines, SEO frameworks) to guide you through content creation.
```
---
#### Task 5.2: Create INSTALL.md
**GitHub Issue:** [#15 - Update project documentation](https://github.com/alirezarezvani/claude-skills/issues/15)
**Estimated Time:** 45 minutes
**Contents:**
- Prerequisites (Claude Code CLI, Python 3.8+, Git)
- Installation steps (clone + manual setup until install.sh ready)
- Verification commands
- Troubleshooting section
---
#### Task 5.3: Create USAGE.md
**GitHub Issue:** [#15 - Update project documentation](https://github.com/alirezarezvani/claude-skills/issues/15)
**Estimated Time:** 1 hour
**Contents:**
- Agent invocation examples (all 5 agents)
- Multi-agent coordination patterns
- Skill + Agent workflow examples
- Best practices
- Tips and tricks
---
#### Task 5.4: Update CLAUDE.md
**GitHub Issue:** [#15 - Update project documentation](https://github.com/alirezarezvani/claude-skills/issues/15)
**Estimated Time:** 30 minutes
**Updates:**
- Architecture overview (new agents/ directory)
- Directory tree diagram
- Agent integration architecture section
- cs-* prefix convention
- Relative path patterns
---
### Day 6: Testing & Validation
#### Task 6.1: Comprehensive Testing
**GitHub Issue:** [#16 - Phase 1-2 Testing and Validation](https://github.com/alirezarezvani/claude-skills/issues/16)
**Estimated Time:** 2 hours
**Test Categories:**
1. **Directory Structure** (15 min)
```bash
# Verify all directories exist
ls agents/marketing agents/c-level agents/product
ls commands
ls standards/communication standards/quality standards/git standards/documentation standards/security
ls templates
```
2. **Standards Validation** (15 min)
```bash
# Check all standards files
ls standards/*/
# Verify no factory references
grep -r "rr-" standards/ || echo "✅ No rr-* references"
grep -r "factory" standards/ || echo "✅ No factory references"
# Markdown linting
yamllint standards/
```
3. **Agent Validation** (30 min)
```bash
# Check all agent files exist
ls agents/marketing/cs-content-creator.md
ls agents/marketing/cs-demand-gen-specialist.md
ls agents/c-level/cs-ceo-advisor.md
ls agents/c-level/cs-cto-advisor.md
ls agents/product/cs-product-manager.md
# Validate YAML frontmatter (check each file)
head -20 agents/marketing/cs-content-creator.md # Should show valid YAML
```
4. **Path Resolution Testing** (30 min)
```bash
# Test from each agent directory
cd agents/marketing
python ../../marketing-skill/content-creator/scripts/brand_voice_analyzer.py --help
ls ../../marketing-skill/content-creator/references/brand_guidelines.md
cd ../c-level
ls ../../c-level-advisor/ceo-advisor/scripts/
cd ../product
python ../../product-team/product-manager-toolkit/scripts/rice_prioritizer.py --help
cd ../..
```
5. **Python Tool Execution** (30 min)
```bash
# Run actual tools to verify they work
python marketing-skill/content-creator/scripts/brand_voice_analyzer.py CLAUDE.md
python marketing-skill/content-creator/scripts/seo_optimizer.py README.md "claude skills"
python product-team/product-manager-toolkit/scripts/rice_prioritizer.py --help
```
6. **Documentation Quality** (15 min)
```bash
# Check for broken links
# Verify markdown linting passes
yamllint agents/**/*.md
yamllint documentation/**/*.md
# Verify all required sections present in each agent
grep -l "## Purpose" agents/**/*.md
grep -l "## Skill Integration" agents/**/*.md
grep -l "## Workflows" agents/**/*.md
```
---
#### Task 6.2: Quality Gates
**Estimated Time:** 30 minutes
```bash
# Run quality checks
/review
# Run security scan
/security-scan
# Verify all pass
```
---
#### Task 6.3: Final Validation Checklist
**Estimated Time:** 15 minutes
- [ ] All 10 directories created
- [ ] 5 standards files ported and validated
- [ ] 5 agents implemented and tested
- [ ] All relative paths work
- [ ] All Python tools executable
- [ ] Agent template complete
- [ ] Creation guide actionable
- [ ] README.md updated
- [ ] INSTALL.md created
- [ ] USAGE.md created
- [ ] CLAUDE.md updated
- [ ] All quality gates pass
- [ ] No broken links
---
#### Task 6.4: Final Commit & PR
**Estimated Time:** 30 minutes
```bash
# Stage documentation
git add README.md INSTALL.md USAGE.md CLAUDE.md
# Commit documentation
git commit -m "docs: update project documentation for agent integration
- Update README with Quick Start and Agent Catalog
- Create INSTALL.md with setup instructions
- Create USAGE.md with comprehensive examples
- Update CLAUDE.md with architecture changes
Phase: 4 (Documentation)
Issue: #15"
# Push
git push origin dev
# Create PR for review
gh pr create \
--base main \
--head dev \
--title "feat: Skill-Agent Integration Phase 1-2 Complete" \
--body "$(cat <<'EOF'
## Summary
Complete Phase 1-2 implementation of skill-agent integration for claude-code-skills.
## What's New
### Foundation (Phase 1)
- ✅ Root-level directory structure (agents/, commands/, standards/, templates/)
- ✅ 5 core standards ported from factory and adapted
### Agents (Phase 2)
- ✅ cs-content-creator (marketing)
- ✅ cs-demand-gen-specialist (marketing)
- ✅ cs-ceo-advisor (C-level)
- ✅ cs-cto-advisor (C-level)
- ✅ cs-product-manager (product)
### Templates & Docs
- ✅ Agent template for future expansion
- ✅ Agent creation guide
- ✅ Updated README, INSTALL, USAGE, CLAUDE
## Testing
- ✅ All relative paths resolve correctly
- ✅ All Python tools execute successfully
- ✅ Quality gates pass (/review, /security-scan)
- ✅ No broken links
- ✅ Comprehensive testing complete
## Issues Closed
Closes #8, #9, #11, #12, #13, #14, #15, #16
## Milestone
Completes: [Skill-Agent Integration v1.0](https://github.com/alirezarezvani/claude-skills/milestone/1) Phase 1-2
## Next Steps
- Phase 3: Installation scripts (install.sh, uninstall.sh)
- Phase 4-5: Already complete (documentation & testing)
- Phase 6-7: Plugin marketplace submission
## Reviewers
Please review:
- [ ] Directory structure is clean
- [ ] Agent implementations are comprehensive
- [ ] Documentation is clear and actionable
- [ ] All quality checks pass
EOF
)"
```
---
#### Task 6.5: Close All Issues
**Estimated Time:** 15 minutes
```bash
# Close remaining issues
gh issue close 15 --comment "✅ All documentation updated (README, INSTALL, USAGE, CLAUDE)"
gh issue close 16 --comment "✅ Comprehensive testing complete - all quality gates pass"
# Verify all closed
gh issue list --milestone "Skill-Agent Integration v1.0" --state open
# Should show 0 open issues for Phase 1-2
```
**End of Day 6 Status:**
- ✅ All documentation updated
- ✅ Comprehensive testing complete
- ✅ All quality gates pass
- ✅ PR created for review
- ✅ All Phase 1-2 issues closed
---
## Sprint Completion Summary
### Deliverables
**Phase 1: Foundation**
- ✅ 10 directories created
- ✅ 5 standards ported
**Phase 2: Agents**
- ✅ 5 agents implemented
- ✅ Agent template created
- ✅ Creation guide written
**Phase 4: Documentation**
- ✅ README updated
- ✅ INSTALL.md created
- ✅ USAGE.md created
- ✅ CLAUDE.md updated
**Phase 5: Testing**
- ✅ Comprehensive validation
- ✅ All quality gates pass
### Metrics
- **Issues Completed:** 8 (all Phase 1-2 issues)
- **Files Created:** 17 (10 dirs, 5 standards, 5 agents, 1 template, 1 guide, 4 docs)
- **Lines of Code:** ~3000+ (agent files, documentation)
- **Test Coverage:** 100% (all agents tested)
- **Quality Score:** 100% (all gates pass)
### Next Sprint Planning
**Phase 3: Installation System**
- Create install.sh (interactive)
- Create uninstall.sh
- Backwards compatibility
**Phase 6-7: Plugin Creation**
- Research marketplace requirements
- Design plugin.yaml manifest
- Package for distribution
- Submit to Anthropic marketplace
---
## Sprint Retrospective Notes
### What Went Well
- Clear implementation plan
- Comprehensive GitHub issues
- Strong foundation established
- Template enables future expansion
### Challenges Encountered
- [To be filled during sprint]
### Lessons Learned
- [To be filled during sprint]
### Process Improvements
- [To be filled during sprint]
---
## References
- **Implementation Plan:** `documentation/implementation/implementation-plan-november-2025.md`
- **Sprint Context:** `documentation/delivery/sprint-11-05-2025/context.md`
- **GitHub Issues:** [#8](https://github.com/alirezarezvani/claude-skills/issues/8), [#9](https://github.com/alirezarezvani/claude-skills/issues/9), [#11](https://github.com/alirezarezvani/claude-skills/issues/11), [#12](https://github.com/alirezarezvani/claude-skills/issues/12), [#13](https://github.com/alirezarezvani/claude-skills/issues/13), [#14](https://github.com/alirezarezvani/claude-skills/issues/14), [#15](https://github.com/alirezarezvani/claude-skills/issues/15), [#16](https://github.com/alirezarezvani/claude-skills/issues/16)
- **Milestone:** [Skill-Agent Integration v1.0](https://github.com/alirezarezvani/claude-skills/milestone/1)
- **Project Board:** [Project #9](https://github.com/users/alirezarezvani/projects/9)
---
**Sprint Status:** 🎯 Ready to Start
**Next Action:** Begin Day 1 - Task 1.1 (Create Directory Structure)
**Document Version:** 1.0
**Created:** November 5, 2025
**Last Updated:** November 5, 2025

0
standards/communication/.gitkeep Normal file
View File

38
standards/communication/communication-standards.md Normal file
View File

@@ -0,0 +1,38 @@
# Communication Standards
## Core Requirements
- **Absolute Honesty**: Direct assessments without diplomatic cushioning
- **Zero Fluff**: Eliminate vague statements and buzzwords
- **Pragmatic Focus**: Every suggestion must be immediately actionable
- **Critical Analysis**: Challenge assumptions and identify flaws before responding
- **Always Ask for Clarification**: Never assume or fill gaps with generic advice
## Solution Standards
- **File Economy**: Edit existing files instead of creating new ones when possible
- **Anti-Overengineering**: Choose simple, direct solutions over elaborate architectures
## Response Protocol
1. **Pre-Response Check**: Verify answer is specific and actionable
2. **Critical Review**: Identify and address solution weaknesses
3. **Implementation Reality**: Confirm feasibility within stated constraints
## Prohibited Responses
- Generic praise without technical analysis
- Vague suggestions without clear reasoning
- Advice without implementation details
- Assumptions when requirements are unclear
- Over-engineered solutions for simple problems
## Standard Structure
1. Direct assessment following user specifications
2. Critical analysis with potential issues
3. Step-by-step recommendations (edit vs. create approach)
4. Resource requirements and code organization
5. Documentation and maintenance considerations
**Remember**: This repository provides production-ready skills and agent workflows. Focus on helping users implement, customize, and extend these skills for their projects. Agents (cs-* prefix) should orchestrate skills effectively, provide clear workflows, and maintain the high quality standards of the skill library. Always use the current date when creating files or examples.

0
standards/documentation/.gitkeep Normal file
View File

545
standards/documentation/documentation-standards.md Normal file
View File

@@ -0,0 +1,545 @@
# Documentation Standards
## Core Principles
### **1. Living Documentation**
- Documentation stays current with code
- Update docs in the same PR as code changes
- Living docs (README, CLAUDE, AGENTS) updated regularly
- Outdated information removed promptly
### **2. Clarity & Accessibility**
- Write for beginners, not experts
- Use simple, clear language
- Provide examples for all concepts
- Include troubleshooting sections
### **3. Structure & Consistency**
- Follow established templates
- Use consistent formatting
- Maintain clear hierarchy
- Keep related content together
## File Naming Conventions
### **General Rules**
```yaml
# Markdown files
README.md # Repository root (UPPERCASE)
CLAUDE.md # Repository root (UPPERCASE)
AGENTS.md # Repository root (UPPERCASE)
CHANGELOG.md # Repository root (UPPERCASE)
LICENSE # Repository root (no extension)
# Other documentation (lowercase with hyphens)
installation-guide.md
user-guide.md
api-reference.md
troubleshooting.md
```
### **Directory-Specific Naming**
```yaml
# Agents (lowercase with hyphens)
agents/marketing/cs-content-creator.md
agents/c-level/cs-ceo-advisor.md
# Skills (lowercase, no hyphens in folder names)
marketing-skill/content-creator/SKILL.md
# Standards (lowercase with hyphens)
standards/communication/communication-standards.md
# Documentation (lowercase with hyphens)
documentation/implementation/implementation-plan-november-2025.md
documentation/delivery/sprint-11-05-2025/context.md
```
## Markdown Formatting Standards
### **1. Headings**
```markdown
# H1 - Document Title (only one per file)
## H2 - Major Sections
### H3 - Subsections
#### H4 - Details
**Don't skip heading levels!**
✅ H1 → H2 → H3
❌ H1 → H3 (skips H2)
```
### **2. Lists**
```markdown
# Unordered lists
- Item 1
- Item 2
- Sub-item 2.1
- Sub-item 2.2
- Item 3
# Ordered lists
1. First step
2. Second step
3. Third step
# Task lists
- [ ] Incomplete task
- [x] Completed task
```
### **3. Code Blocks**
```markdown
# Inline code
Use `code` for commands, filenames, and variables.
# Code blocks with syntax highlighting
\`\`\`bash
# Bash commands
git commit -m "feat(agents): implement cs-content-creator"
\`\`\`
\`\`\`python
# Python code
def analyze_content(text: str) -> Dict[str, Any]:
return {"score": 0.85}
\`\`\`
\`\`\`yaml
# YAML configuration
name: cs-content-creator
domain: marketing
\`\`\`
```
### **4. Links**
```markdown
# External links
[Link text](https://example.com)
# Internal links (relative paths)
[Agent catalog](agents/README.md)
[Installation guide](INSTALL.md)
# Link to specific heading
[See quality standards](#quality-standards)
# Reference-style links (for repeated URLs)
[Claude Code][1]
[GitHub][2]
[1]: https://claude.com/code
[2]: https://github.com
```
### **5. Images**
```markdown
# Standard image
![Alt text describing image](path/to/image.png)
# Image with title
![Alt text](image.png "Image title")
# Linked image
[![Alt text](image.png)](https://link-destination.com)
**Always provide alt text for accessibility!**
```
### **6. Tables**
```markdown
| Column 1 | Column 2 | Column 3 |
|----------|----------|----------|
| Data 1 | Data 2 | Data 3 |
| Data 4 | Data 5 | Data 6 |
# Alignment
| Left | Center | Right |
|:-----|:------:|------:|
| L1 | C1 | R1 |
```
### **7. Emphasis**
```markdown
*Italic text* or _italic text_
**Bold text** or __bold text__
***Bold and italic*** or ___bold and italic___
~~Strikethrough~~
Use **bold** for emphasis, *italic* for definitions.
```
### **8. Blockquotes**
```markdown
> Single line quote
> Multi-line quote
> continues here
> and here
> **Note:** Important information
> highlighted in a quote block
```
### **9. Horizontal Rules**
```markdown
---
Use sparingly to separate major sections.
```
## Document Structure Templates
### **Agent Documentation (agents/*/cs-*.md)**
```markdown
---
name: cs-agent-name
description: One-line description
skills: skill-folder-name
domain: domain-name
model: sonnet
tools: [Read, Write, Bash, Grep, Glob]
---
# Agent Name
## Purpose
[1-2 paragraphs describing what this agent does]
## Skill Integration
**Skill Location:** `../../skill-folder/`
### Python Tools
[List with usage examples]
### Knowledge Bases
[List with relative paths]
### Templates
[List with relative paths]
## Workflows
### Workflow 1: [Name]
[Step-by-step process]
### Workflow 2: [Name]
[Step-by-step process]
## Integration Examples
[Concrete examples with code]
## Success Metrics
[How to measure effectiveness]
## Related Agents
[Links to related agents]
## References
[Links to documentation]
```
### **README.md Structure**
```markdown
# Project Title
[1-sentence project description]
## Quick Start
[Installation and first use - 30 seconds]
## Features
- Feature 1
- Feature 2
- Feature 3
## Installation
[Detailed installation steps]
## Usage
[Basic usage examples]
## Documentation
- [Installation Guide](INSTALL.md)
- [Usage Guide](USAGE.md)
- [Agent Catalog](agents/README.md)
## Contributing
[Contribution guidelines]
## License
[License information]
```
### **SKILL.md Structure**
```markdown
# Skill Name
[1-2 paragraph description]
## What This Skill Does
[Clear explanation of purpose and value]
## Contents
- Python Tools (X scripts)
- Knowledge Bases (X references)
- Templates (X templates)
## Python Automation Tools
### Tool 1: [Name]
**Purpose:** [What it does]
**Usage:**
\`\`\`bash
python scripts/tool-name.py input.txt
\`\`\`
## Knowledge Bases
### Reference 1: [Name]
**Location:** `references/file-name.md`
**Content:** [What's inside]
## Templates
### Template 1: [Name]
**Location:** `assets/template-name.md`
**Use Case:** [When to use]
## Examples
[Real-world usage examples]
## Requirements
- Python 3.8+
- Standard library only (or list dependencies)
## Installation
[How to use this skill]
## Related Skills
[Links to related skills]
```
## Living Documentation
### **Files That Must Stay Current**
```yaml
repository_root:
README.md:
update_frequency: "Every major feature"
purpose: "Primary project documentation"
audience: "All users"
CLAUDE.md:
update_frequency: "Every structural change"
purpose: "AI context and architecture"
audience: "Claude Code and developers"
AGENTS.md:
update_frequency: "Every agent added/modified"
purpose: "Agent catalog and reference"
audience: "Agent developers"
CHANGELOG.md:
update_frequency: "Every release"
purpose: "Version history and changes"
audience: "All users"
```
### **Update Triggers**
```yaml
update_readme_when:
- New skill added
- New agent implemented
- Installation process changes
- Major feature added
update_claude_md_when:
- Directory structure changes
- Architecture changes
- New standards added
- Agent integration patterns change
update_agents_md_when:
- New agent created
- Agent modified
- Agent deprecated
- Agent template changes
```
## Quality Checklist
### **Pre-Commit Documentation Review**
```yaml
content_quality:
- [ ] All headings follow hierarchy (no skipped levels)
- [ ] All code blocks have syntax highlighting
- [ ] All links work (no 404s)
- [ ] All images have alt text
- [ ] No spelling errors
- [ ] Grammar is correct
- [ ] Examples are tested and working
formatting:
- [ ] Consistent heading style
- [ ] Consistent list formatting
- [ ] Consistent code block style
- [ ] No trailing whitespace
- [ ] Single blank line between sections
- [ ] Proper indentation
accessibility:
- [ ] Alt text describes images meaningfully
- [ ] Link text is descriptive (not "click here")
- [ ] Heading hierarchy is logical
- [ ] Tables have headers
- [ ] Color is not the only way to convey information
```
### **Link Validation**
```bash
# Check for broken markdown links
find . -name "*.md" -exec grep -l "](.*)" {} \; | while read file; do
echo "Checking links in: $file"
# Manual check or use markdown-link-check tool
done
```
## Documentation Best Practices
### **Do's**
- ✅ Write for the target audience
- ✅ Use clear, simple language
- ✅ Provide concrete examples
- ✅ Include screenshots where helpful
- ✅ Update docs with code changes
- ✅ Link to related documentation
- ✅ Use consistent terminology
- ✅ Test all code examples
### **Don'ts**
- ❌ Assume prior knowledge
- ❌ Use jargon without explanation
- ❌ Write vague instructions
- ❌ Skip error scenarios
- ❌ Let docs get stale
- ❌ Use "click here" as link text
- ❌ Skip proofreading
- ❌ Forget about mobile users
## Special Documentation Types
### **API Documentation**
```markdown
## Function Name
**Purpose:** What this function does
**Parameters:**
- `param1` (type): Description
- `param2` (type, optional): Description, default: value
**Returns:**
- (type): Description of return value
**Raises:**
- `ExceptionName`: When this is raised
**Example:**
\`\`\`python
result = function_name(param1="value", param2=42)
print(result)
# Output: expected output
\`\`\`
```
### **Troubleshooting Guide**
```markdown
## Problem: [Describe the problem]
**Symptoms:**
- Symptom 1
- Symptom 2
**Cause:**
[What causes this issue]
**Solution:**
1. Step 1
2. Step 2
3. Step 3
**Verification:**
[How to confirm it's fixed]
```
### **Decision Records**
```markdown
# Decision: [Title]
**Date:** YYYY-MM-DD
**Status:** Accepted | Rejected | Superseded
## Context
[What's the situation?]
## Decision
[What did we decide?]
## Rationale
[Why did we decide this?]
## Consequences
[What are the impacts?]
## Alternatives Considered
1. Alternative 1 - [Why rejected]
2. Alternative 2 - [Why rejected]
```
---
**Focus**: Markdown quality, structure consistency, living documentation
**Updated**: November 2025
**Review**: Monthly documentation quality assessment
**Compliance**: Markdown standards, accessibility guidelines

0
standards/git/.gitkeep Normal file
View File

439
standards/git/git-workflow-standards.md Normal file
View File

@@ -0,0 +1,439 @@
# Git Workflow Standards
## Core Principles
### **1. Conventional Commits**
- All commits follow conventional commits specification
- Enable automated changelog generation
- Clear categorization of all changes
- Explicit marking of breaking changes
### **2. Semantic Versioning**
- Automated versioning based on commit types
- MAJOR version: BREAKING CHANGE
- MINOR version: feat type commits
- PATCH version: fix type commits
### **3. Branch Protection**
- Main branch requires review
- All quality gates must pass
- No force pushes to main
- Signed commits recommended
## Conventional Commits Specification
### **Commit Message Structure**
```
<type>[optional scope]: <description>
[optional body]
[optional footer(s)]
```
### **Standard Types**
```yaml
feat: # New features (agents, skills, tools)
fix: # Bug fixes
docs: # Documentation only changes
style: # Formatting changes (no functional impact)
refactor: # Code restructuring without feature changes
perf: # Performance improvements
test: # Adding or correcting tests
chore: # Maintenance tasks (dependencies, build)
ci: # CI/CD configuration changes
```
### **Examples**
```bash
# New agent implementation
feat(agents): implement cs-content-creator agent
# Bug fix in Python tool
fix(seo-optimizer): correct keyword density calculation
# Documentation update
docs(README): add agent catalog section
# Breaking change
feat(agents)!: replace agent template structure
BREAKING CHANGE: agent frontmatter now requires 'tools' field
```
### **Scopes for Claude Skills**
```yaml
Common Scopes:
agents: # Agent implementation
skills: # Skill packages
standards: # Standards library
templates: # Templates
docs: # Documentation
foundation: # Core infrastructure
marketing: # Marketing domain
c-level: # C-level domain
product: # Product domain
engineering: # Engineering domain
ra-qm: # RA/QM domain
```
## Branch Strategy
### **Branch Naming Conventions**
```yaml
# Feature branches (agent/skill development)
feature/agents-{name}: # New agent implementation
feature/skills-{name}: # New skill package
feature/{domain}-{component}: # Domain-specific features
# Documentation branches
docs/{component}: # Documentation updates
docs/standards-{name}: # Standards library updates
# Bug fixes
fix/{issue-number}-{description}: # Bug fixes
# Hotfixes (critical production issues)
hotfix/{issue}-{description}: # Emergency fixes
# Test branches
test/{feature}: # Testing and validation
```
### **Examples**
```bash
# Create feature branch for new agent
git checkout -b feature/agents-ceo-advisor
# Create documentation branch
git checkout -b docs/installation-guide
# Create fix branch
git checkout -b fix/23-broken-relative-paths
# Create test branch
git checkout -b test/agent-path-resolution
```
## Workflow Process
### **1. Development Workflow**
```bash
# Start new feature
git checkout -b feature/agents-product-manager
# Make changes
# ... edit files ...
# Stage changes
git add agents/product/cs-product-manager.md
# Commit with conventional message
git commit -m "feat(agents): implement cs-product-manager agent
- Add YAML frontmatter
- Document RICE prioritization workflow
- Add interview analysis integration
- Test relative path resolution
Phase: 2.3
Issue: #13"
# Push to remote
git push origin feature/agents-product-manager
```
### **2. Pull Request Workflow**
```bash
# Create PR using gh CLI
gh pr create \
--base main \
--head feature/agents-product-manager \
--title "feat(agents): implement cs-product-manager agent" \
--body "Closes #13
## Summary
Implements product management agent with RICE prioritization and interview analysis.
## Testing
- [x] Relative paths resolve correctly
- [x] Python tools execute successfully
- [x] Workflows documented
- [x] Quality gates pass"
```
### **3. Review & Merge**
```bash
# After review approval
gh pr merge feature/agents-product-manager \
--squash \
--delete-branch
```
### **4. Release Workflow**
```bash
# Create release with semantic versioning
git tag v1.0.0-agents
git push origin v1.0.0-agents
# GitHub Actions automatically creates release with changelog
```
## Commit Message Templates
### **For Agent Implementation**
```
feat(agents): implement cs-{agent-name}
- Add YAML frontmatter with required fields
- Document {number} workflows
- Add integration examples
- Test Python tool execution
- Verify relative path resolution
Phase: {phase-number}
Issue: #{issue-number}
```
### **For Skill Development**
```
feat(skills): add {skill-name} to {domain} domain
- Create skill directory structure
- Implement {number} Python automation tools
- Add knowledge base references
- Create user templates
Domain: {domain}
Issue: #{issue-number}
```
### **For Standards Updates**
```
docs(standards): update {standard-name} for {context}
- Adapt for claude-skills context
- Remove factory-specific references
- Add agent-specific guidelines
- Update examples
Issue: #{issue-number}
```
### **For Bug Fixes**
```
fix({scope}): resolve {issue-description}
Problem: {what was broken}
Solution: {what was fixed}
Impact: {who/what this affects}
Fixes #{issue-number}
```
## Git Hooks
### **Pre-commit Hook**
```bash
#!/bin/bash
# .git/hooks/pre-commit
echo "Running pre-commit checks..."
# Check for secrets
if git diff --cached | grep -iE '(api[_-]?key|secret|password|token).*=.*[^x{5}]'; then
echo "❌ Potential secret detected in commit"
exit 1
fi
# Validate Python syntax
python -m compileall $(git diff --cached --name-only --diff-filter=ACM | grep '\.py$')
if [ $? -ne 0 ]; then
echo "❌ Python syntax errors detected"
exit 1
fi
echo "✅ Pre-commit checks passed"
```
### **Commit-msg Hook**
```bash
#!/bin/bash
# .git/hooks/commit-msg
# Validate conventional commit format
commit_regex='^(feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert)(\([a-z-]+\))?(!)?:\ .{1,}'
if ! head -1 "$1" | grep -qE "$commit_regex"; then
echo "❌ Commit message does not follow conventional commits format"
echo "Format: <type>[(scope)]: <description>"
echo "Example: feat(agents): implement cs-product-manager"
exit 1
fi
echo "✅ Commit message format valid"
```
## Quality Gates Integration
### **Pre-push Validation**
```bash
#!/bin/bash
# .git/hooks/pre-push
echo "Running pre-push validation..."
# Run quality checks
/review
# Check for TODO comments in production code
if git diff origin/main...HEAD | grep -i "TODO"; then
echo "⚠️ TODO comments found - consider addressing before push"
fi
echo "✅ Pre-push validation complete"
```
## Branch Protection Rules
### **Main Branch Protection**
```yaml
branch_protection:
required_status_checks:
strict: true
contexts:
- "ci-quality-gate"
- "claude-review"
required_pull_request_reviews:
required_approving_review_count: 1
dismiss_stale_reviews: true
require_code_owner_reviews: false
enforce_admins: true
required_conversation_resolution: true
allow_force_pushes: false
allow_deletions: false
```
## Common Workflows
### **Hotfix Process**
```bash
# Create hotfix branch from main
git checkout main
git pull origin main
git checkout -b hotfix/critical-path-resolution
# Fix issue
# ... make changes ...
# Commit with high priority
git commit -m "fix(agents)!: resolve critical path resolution failure
BREAKING CHANGE: agent path resolution now requires absolute project root
Fixes #42
Priority: P0"
# Create PR with hotfix label
gh pr create --label "P0,hotfix" --base main
# After merge, tag immediately
git tag v1.0.1-hotfix
git push origin v1.0.1-hotfix
```
### **Multi-Agent Coordination**
```bash
# Coordinating changes across multiple agents
git checkout -b feature/update-all-marketing-agents
# Update cs-content-creator
git add agents/marketing/cs-content-creator.md
git commit -m "feat(agents): enhance cs-content-creator workflows"
# Update cs-demand-gen-specialist
git add agents/marketing/cs-demand-gen-specialist.md
git commit -m "feat(agents): enhance cs-demand-gen-specialist workflows"
# Push coordinated changes
git push origin feature/update-all-marketing-agents
```
## Best Practices
### **Do's**
- ✅ Use conventional commit format for all commits
- ✅ Reference issue numbers in commit messages
- ✅ Keep commits atomic (one logical change per commit)
- ✅ Write clear, descriptive commit messages
- ✅ Test changes before committing
- ✅ Pull before pushing to avoid conflicts
- ✅ Use feature branches for all changes
- ✅ Delete branches after merging
### **Don'ts**
- ❌ Commit directly to main (use PRs)
- ❌ Force push to shared branches
- ❌ Commit secrets or credentials
- ❌ Mix multiple unrelated changes in one commit
- ❌ Use vague commit messages ("fix stuff", "updates")
- ❌ Skip quality checks
- ❌ Leave branches unmerged for extended periods
## Emergency Procedures
### **Rollback Commit**
```bash
# Revert the last commit (creates new commit)
git revert HEAD
# Revert specific commit
git revert <commit-hash>
# Force rollback (use with caution!)
git reset --hard HEAD~1
git push origin main --force # Only if absolutely necessary!
```
### **Fix Bad Commit Message**
```bash
# Amend last commit message (before push)
git commit --amend -m "feat(agents): corrected commit message"
# After push (creates new commit)
git revert HEAD
git commit -m "feat(agents): correct implementation with proper message"
```
---
**Standard**: Conventional Commits v1.0.0
**Versioning**: Semantic Versioning v2.0.0
**Updated**: November 2025
**Review**: Monthly git workflow assessment

0
standards/quality/.gitkeep Normal file
View File

319
standards/quality/quality-standards.md Normal file
View File

@@ -0,0 +1,319 @@
# Quality Standards
## Core Quality Principles
### **1. Quality-First Completion**
- **Zero Defect Handoff:** No work considered complete with known quality issues
- **Comprehensive Validation:** All acceptance criteria verified through testing
- **Path Resolution:** All relative paths validated and working
- **Tool Execution:** All Python tools tested and executing correctly
### **2. Testing Standards**
- **Python Tools:** All automation tools must execute without errors
- **Agent Workflows:** Agent markdown files validated for completeness
- **Integration Testing:** Agent-to-skill integration verified
- **Documentation Quality:** All documentation clear, accurate, and actionable
### **3. Code Quality**
- **Python Standards:** PEP 8 compliance for all Python scripts
- **No Hardcoded Secrets:** Use environment variables or configuration files
- **Error Handling:** Proper exception handling in all tools
- **Type Hints:** Use type annotations for Python functions
## Universal Completion Criteria (ALL TASKS)
```yaml
functional_requirements:
- [ ] All acceptance criteria satisfied with documented verification
- [ ] Feature functionality validated in target environments
- [ ] Edge cases identified and handled appropriately
- [ ] Error scenarios tested with proper error handling
- [ ] Integration points tested and validated
quality_standards:
- [ ] Code review completed with documented feedback
- [ ] Automated tests passing where applicable
- [ ] Manual testing completed for user-facing functionality
- [ ] Documentation updated with changes
- [ ] No broken links or missing references
documentation_requirements:
- [ ] Technical documentation updated with implementation details
- [ ] User documentation updated with new functionality guidance
- [ ] Change documentation prepared with impact analysis
- [ ] Handoff documentation prepared with clear next steps
```
## Agent-Specific Quality Gates
### **Agent Implementation Standards**
```yaml
agent_quality_validation:
yaml_frontmatter:
- [ ] Valid YAML syntax (no parsing errors)
- [ ] All required fields present (name, description, skills, domain, model, tools)
- [ ] cs-* prefix used for agent naming
- [ ] Domain correctly categorized
skill_integration:
- [ ] Relative paths resolve correctly (../../ pattern)
- [ ] Skill location documented and accessible
- [ ] Python tools referenced with correct paths
- [ ] Knowledge bases referenced with correct paths
- [ ] Templates referenced with correct paths
workflow_documentation:
- [ ] Minimum 3 workflows documented
- [ ] Each workflow has clear step-by-step instructions
- [ ] Integration examples provided
- [ ] Success metrics defined
- [ ] Related agents cross-referenced
testing_requirements:
- [ ] Python tool execution tested from agent context
- [ ] Relative path resolution verified
- [ ] Knowledge base files accessible
- [ ] All examples in documentation work
- [ ] No broken markdown links
```
## Python Tool Quality Standards
### **Python Script Requirements**
```python
# All Python tools must follow these standards
"""
Module: tool_name.py
Description: [Clear description of what this tool does]
Usage: python tool_name.py [arguments]
"""
from typing import Optional, List, Dict
import sys
import json
def main(arg1: str, arg2: Optional[str] = None) -> int:
"""
Main function description.
Args:
arg1: Description of argument 1
arg2: Description of optional argument 2
Returns:
Exit code (0 for success, 1 for error)
"""
try:
# Tool implementation
result = process_data(arg1, arg2)
# Output results
if json_output:
print(json.dumps(result, indent=2))
else:
print(format_human_readable(result))
return 0
except Exception as e:
print(f"Error: {e}", file=sys.stderr)
return 1
if __name__ == "__main__":
sys.exit(main())
```
### **Python Quality Checklist**
```yaml
python_tool_quality:
code_standards:
- [ ] PEP 8 compliant (use pylint or flake8)
- [ ] Type hints for all functions
- [ ] Docstrings for all public functions
- [ ] Clear error messages
- [ ] Proper exception handling
functionality:
- [ ] Handles missing arguments gracefully
- [ ] Provides helpful usage information (--help)
- [ ] Supports both JSON and human-readable output
- [ ] Returns appropriate exit codes
- [ ] No hardcoded file paths (use relative or arguments)
dependencies:
- [ ] Uses standard library when possible
- [ ] External dependencies documented in skill README
- [ ] Requirements.txt provided if external packages needed
- [ ] Version constraints specified for dependencies
```
## Documentation Quality Standards
### **Markdown Documentation Requirements**
```yaml
documentation_quality:
structure:
- [ ] Clear hierarchy with proper headings
- [ ] Table of contents for long documents
- [ ] Consistent formatting throughout
- [ ] Code blocks use appropriate syntax highlighting
- [ ] Lists properly formatted
content:
- [ ] All links work (no 404s)
- [ ] All code examples tested and working
- [ ] All file paths are correct
- [ ] Screenshots/diagrams up to date
- [ ] No outdated information
accessibility:
- [ ] Alt text for images
- [ ] Descriptive link text (not "click here")
- [ ] Proper heading hierarchy (no skipping levels)
- [ ] Code examples include explanatory text
maintenance:
- [ ] Date updated timestamp
- [ ] Version information if applicable
- [ ] Changelog for significant updates
```
## Quality Validation Commands
### **Automated Quality Checks**
```bash
# Markdown linting
yamllint agents/**/*.md standards/**/*.md documentation/**/*.md
# Python syntax validation
python -m compileall marketing-skill product-team c-level-advisor engineering-team ra-qm-team
# Check for broken links (manual check required)
# Verify all ../../ relative paths resolve
# Test Python tools
for script in $(find . -name "*.py" -path "*/scripts/*"); do
echo "Testing: $script"
python "$script" --help || echo "❌ Failed: $script"
done
```
### **Manual Validation Checklist**
```yaml
pre_commit_validation:
agent_files:
- [ ] YAML frontmatter valid
- [ ] All workflows documented
- [ ] Integration examples present
- [ ] No broken links
- [ ] Relative paths verified
python_tools:
- [ ] Scripts execute without errors
- [ ] --help flag works
- [ ] Error handling tested
- [ ] Output formats correct
documentation:
- [ ] README updated if needed
- [ ] CLAUDE.md reflects changes
- [ ] All examples tested
- [ ] Changelog updated
pre_push_validation:
- [ ] All quality checks pass
- [ ] No secrets in code
- [ ] Commit messages follow convention
- [ ] Branch protection requirements met
```
## Quality Metrics for Agents & Skills
### **Success Criteria**
```yaml
agent_effectiveness:
workflow_clarity:
target: "Users can follow workflows without assistance"
measurement: "Documentation completeness and clarity"
tool_reliability:
target: "100% of Python tools execute successfully"
measurement: "Script execution success rate"
path_resolution:
target: "100% of relative paths resolve correctly"
measurement: "Path validation tests passing"
integration_quality:
target: "Agents seamlessly invoke skills"
measurement: "Agent-skill integration tests passing"
documentation_quality:
completeness:
target: "All required sections present"
measurement: "Documentation structure checklist"
accuracy:
target: "Zero broken links or outdated information"
measurement: "Link validation and content review"
usability:
target: "Users can implement workflows in <30 minutes"
measurement: "Time-to-implementation tracking"
```
## Quality Improvement Process
### **Continuous Quality Enhancement**
- **Pre-commit:** Validate syntax, check paths, test tools locally
- **Pull Request:** Peer review, automated testing, quality gate checks
- **Post-merge:** Monitor for issues, collect user feedback
- **Monthly:** Review quality metrics, update standards as needed
- **Quarterly:** Assess skill/agent effectiveness, plan improvements
### **Quality Issue Resolution**
```yaml
issue_priority:
P0_critical:
- Broken Python tools (execution failures)
- Invalid relative paths (404 errors)
- Security vulnerabilities
- Data loss or corruption
response_time: "<1 hour"
P1_high:
- Broken workflows in agents
- Documentation inaccuracies
- Missing required sections
- Performance issues
response_time: "<24 hours"
P2_medium:
- Enhancement requests
- Documentation improvements
- Code refactoring
- Optimization opportunities
response_time: "<1 week"
P3_low:
- Nice-to-have features
- Minor documentation updates
- Style improvements
response_time: "<1 month"
```
---
**Focus**: Python tool quality, agent workflow clarity, skill integration testing
**Updated**: November 2025
**Review**: Monthly quality assessment
**Compliance**: PEP 8, Markdown standards, relative path conventions

0
standards/security/.gitkeep Normal file
View File

503
standards/security/security-standards.md Normal file
View File

@@ -0,0 +1,503 @@
# Security Standards
## Core Security Principles
### **1. No Secrets in Code**
- Never hardcode API keys, passwords, or tokens
- Use environment variables for sensitive data
- Exclude sensitive files from git (.env, credentials.json)
- Scan for secrets before committing
### **2. Dependency Security**
- Use standard library when possible
- Minimize external dependencies
- Keep dependencies updated
- Audit dependencies for vulnerabilities
### **3. Input Validation**
- Validate all user input
- Sanitize file paths
- Prevent command injection
- Handle edge cases safely
### **4. Data Protection**
- Don't store sensitive user data
- Encrypt data in transit
- Follow privacy best practices
- Comply with GDPR/CCPA when applicable
## Secret Detection
### **Pre-Commit Secret Scanning**
```bash
# Check for common secrets before committing
git diff --cached | grep -iE 'api[_-]?key|secret|password|token|Bearer|Authorization'
# Specific patterns to detect
patterns=(
"api[_-]?key.*=.*['\"][^x']+"
"secret.*=.*['\"][^x']+"
"password.*=.*['\"][^x']+"
"token.*=.*['\"][^x']+"
"Bearer\s+[A-Za-z0-9\-._~+/]+"
"sk-[A-Za-z0-9]{20,}" # OpenAI API keys
"ghp_[A-Za-z0-9]{36}" # GitHub Personal Access Tokens
"AKIA[A-Z0-9]{16}" # AWS Access Keys
)
```
### **Prohibited Patterns**
```python
# ❌ Bad - Hardcoded secret
API_KEY = "sk-1234567890abcdef"
password = "mypassword123"
# ✅ Good - Environment variable
import os
API_KEY = os.getenv("API_KEY")
if not API_KEY:
raise ValueError("API_KEY environment variable not set")
```
### **Git Ignore Patterns**
```gitignore
# Secrets and credentials
.env
.env.*
*.key
*.pem
credentials.json
secrets.yaml
config/local.py
# Python cache (may contain sensitive data)
__pycache__/
*.pyc
*.pyo
# OS files
.DS_Store
Thumbs.db
# IDE files
.vscode/settings.json
.idea/
```
## Python Security Best Practices
### **1. Safe File Handling**
```python
# ✅ Good - Safe path handling
import os
from pathlib import Path
def read_user_file(filename: str) -> str:
"""Safely read user-provided file."""
# Validate filename
if not filename or '..' in filename or filename.startswith('/'):
raise ValueError("Invalid filename")
# Use Path for safe path manipulation
base_dir = Path(__file__).parent
file_path = (base_dir / filename).resolve()
# Ensure file is within allowed directory
if not file_path.is_relative_to(base_dir):
raise ValueError("File path outside allowed directory")
# Read safely
with open(file_path, 'r') as f:
return f.read()
# ❌ Bad - Unsafe path handling
def read_file_unsafe(filename: str) -> str:
# Vulnerable to directory traversal
with open(filename, 'r') as f:
return f.read()
```
### **2. Command Execution Safety**
```python
# ✅ Good - Safe command execution
import subprocess
from typing import List
def run_safe_command(args: List[str]) -> str:
"""Execute command safely with argument list."""
# Use argument list, not shell=True
result = subprocess.run(
args,
capture_output=True,
text=True,
check=True,
timeout=30 # Prevent hanging
)
return result.stdout
# Example
output = run_safe_command(['python', 'script.py', '--input', 'file.txt'])
# ❌ Bad - Shell injection vulnerability
def run_command_unsafe(command: str) -> str:
# Vulnerable to command injection
result = subprocess.run(
command,
shell=True, # DANGEROUS!
capture_output=True
)
return result.stdout.decode()
```
### **3. Input Validation**
```python
# ✅ Good - Validate and sanitize input
def validate_email(email: str) -> bool:
"""Validate email format."""
import re
pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
return re.match(pattern, email) is not None
def sanitize_filename(filename: str) -> str:
"""Remove unsafe characters from filename."""
import re
# Remove path separators and null bytes
safe = re.sub(r'[/\\:\0]', '', filename)
# Remove leading dots (hidden files)
safe = safe.lstrip('.')
# Limit length
return safe[:255]
# ❌ Bad - No validation
def process_input_unsafe(user_input: str):
# Directly using unvalidated input
exec(user_input) # EXTREMELY DANGEROUS!
```
### **4. Error Handling**
```python
# ✅ Good - Don't expose sensitive info in errors
def connect_to_api(api_key: str):
try:
# Connection logic
pass
except Exception as e:
# Don't log the API key!
print("API connection failed. Check your credentials.")
raise ValueError("Authentication failed") from None
# ❌ Bad - Exposing secrets in error messages
def connect_unsafe(api_key: str):
try:
pass
except Exception as e:
# Leaks API key in logs!
print(f"Failed to connect with key: {api_key}")
raise
```
## Dependency Management
### **Dependency Security Checklist**
```yaml
dependency_security:
minimize_dependencies:
- [ ] Use Python standard library when possible
- [ ] Justify each external dependency
- [ ] Prefer well-maintained packages
- [ ] Check package reputation (downloads, stars, maintenance)
version_pinning:
- [ ] Pin exact versions in requirements.txt
- [ ] Use version constraints (>=, <)
- [ ] Document why specific versions required
- [ ] Test upgrades before deploying
vulnerability_scanning:
- [ ] Run `pip-audit` or `safety check` regularly
- [ ] Review security advisories
- [ ] Update vulnerable packages promptly
- [ ] Monitor dependabot alerts (GitHub)
license_compliance:
- [ ] Check package licenses
- [ ] Avoid GPL in commercial code (if applicable)
- [ ] Document all licenses
- [ ] Comply with attribution requirements
```
### **Security Scanning Commands**
```bash
# Check for known vulnerabilities in dependencies
pip install pip-audit
pip-audit
# Or use safety
pip install safety
safety check
# Check for outdated packages
pip list --outdated
# Generate requirements with version pins
pip freeze > requirements.txt
```
### **Safe Requirements.txt**
```txt
# Pin exact versions for reproducibility
requests==2.31.0
pyyaml==6.0.1
# Use version constraints for flexibility
click>=8.0.0,<9.0.0
python-dateutil>=2.8.0
# Document why specific versions
# numpy==1.24.0 # Required for Python 3.11 compatibility
```
## Data Protection
### **1. User Data Handling**
```python
# ✅ Good - Minimal data collection
def analyze_text(text: str) -> dict:
"""Analyze text without storing it."""
# Process locally, don't send to external services
score = calculate_score(text)
return {"score": score}
# ❌ Bad - Unnecessary data storage
def analyze_text_unsafe(text: str, user_id: str) -> dict:
# Stores user data unnecessarily
save_to_database(user_id, text)
return analyze(text)
```
### **2. Privacy Best Practices**
```yaml
privacy_guidelines:
data_minimization:
- Collect only essential data
- Process data locally when possible
- Delete data after processing
- Don't log sensitive information
transparency:
- Document what data is collected
- Explain how data is used
- Provide opt-out mechanisms
- Allow data export/deletion
compliance:
- Follow GDPR if EU users
- Follow CCPA if California users
- Obtain consent for data collection
- Provide privacy policy
```
## Code Review Security Checklist
### **Pre-Commit Security Review**
```yaml
security_review:
secrets_and_credentials:
- [ ] No hardcoded API keys
- [ ] No hardcoded passwords
- [ ] No hardcoded tokens
- [ ] No private keys committed
- [ ] .env files in .gitignore
input_validation:
- [ ] All user input validated
- [ ] File paths sanitized
- [ ] SQL queries parameterized (if applicable)
- [ ] Command injection prevented
- [ ] XSS prevention (if web app)
dependency_security:
- [ ] No known vulnerable dependencies
- [ ] Dependencies minimized
- [ ] Versions pinned in requirements.txt
- [ ] Licenses checked and compatible
error_handling:
- [ ] Errors don't expose sensitive data
- [ ] Stack traces sanitized in production
- [ ] Logging doesn't include secrets
- [ ] Error messages are user-friendly
data_protection:
- [ ] Sensitive data not logged
- [ ] Personal data handled properly
- [ ] Encryption used where needed
- [ ] Privacy policy updated (if applicable)
```
## Incident Response
### **Security Issue Severity**
```yaml
severity_levels:
P0_critical:
description: "Exposed secrets, active exploits, data breach"
response_time: "<1 hour"
actions:
- Rotate exposed credentials immediately
- Disable compromised accounts
- Notify affected users
- Patch vulnerability
- Document incident
P1_high:
description: "Vulnerable dependencies, potential exploits"
response_time: "<24 hours"
actions:
- Update vulnerable packages
- Test fixes thoroughly
- Deploy security patches
- Monitor for exploitation
P2_medium:
description: "Security best practice violations"
response_time: "<1 week"
actions:
- Review and fix issues
- Update security documentation
- Educate team
P3_low:
description: "Minor security improvements"
response_time: "<1 month"
actions:
- Schedule fixes in backlog
- Update standards
```
### **Exposed Secret Response**
```bash
# If you accidentally commit a secret:
# 1. IMMEDIATELY rotate the credential
# (Change password, regenerate API key, etc.)
# 2. Remove from git history
git filter-branch --force --index-filter \
"git rm --cached --ignore-unmatch path/to/file" \
--prune-empty --tag-name-filter cat -- --all
# 3. Force push (only if not on main/production!)
git push origin --force --all
# 4. Notify security team
# Document the incident
```
## Security Tools
### **Recommended Security Tools**
```yaml
security_tools:
secret_detection:
- gitleaks: "Scan git repos for secrets"
- trufflehog: "Find secrets in git history"
- detect-secrets: "Prevent new secrets"
dependency_scanning:
- pip-audit: "Scan Python dependencies"
- safety: "Check for known vulnerabilities"
- dependabot: "Automated dependency updates (GitHub)"
code_analysis:
- bandit: "Python security linter"
- pylint: "General Python linter with security checks"
- semgrep: "Static analysis for security patterns"
runtime_protection:
- fail2ban: "Prevent brute force attacks (if applicable)"
- rate limiting: "Prevent abuse"
- monitoring: "Detect anomalous behavior"
```
### **Security Scanning Script**
```bash
#!/bin/bash
# security-scan.sh - Run all security checks
echo "🔒 Running security scans..."
# Secret detection
echo "Scanning for secrets..."
gitleaks detect --verbose --redact || echo "⚠️ Potential secrets found"
# Dependency vulnerabilities
echo "Checking dependencies..."
pip-audit || echo "⚠️ Vulnerable dependencies found"
# Python security linter
echo "Running Bandit security linter..."
bandit -r . -f screen || echo "⚠️ Security issues found"
# Check for common security issues
echo "Checking for hardcoded secrets..."
grep -r "password\s*=" --include="*.py" . && echo "⚠️ Potential hardcoded passwords"
echo "✅ Security scan complete"
```
## Security Update Process
### **Regular Security Maintenance**
- **Weekly:** Review dependabot alerts, scan for secrets
- **Monthly:** Run full security audit, update dependencies
- **Quarterly:** Review security standards, update tools
- **Annually:** Comprehensive security assessment
### **Security Documentation**
```markdown
## Security Policy
### Reporting Security Issues
**Do NOT open public issues for security vulnerabilities!**
Email: security@example.com
PGP Key: [link to public key]
Expected response time: 24 hours
### Disclosure Process
1. Report received and acknowledged
2. Issue verified and assessed
3. Fix developed and tested
4. Security advisory published
5. Credits given to reporter
```
---
**Focus**: Python security, secret detection, dependency management
**Updated**: November 2025
**Review**: Monthly security assessment
**Compliance**: OWASP Top 10, Python security best practices

0
templates/.gitkeep Normal file
View File