* chore: update gitignore for audit reports and playwright cache * fix: add YAML frontmatter (name + description) to all SKILL.md files - Added frontmatter to 34 skills that were missing it entirely (0% Tessl score) - Fixed name field format to kebab-case across all 169 skills - Resolves #284 * chore: sync codex skills symlinks [automated] * fix: optimize 14 low-scoring skills via Tessl review (#290) Tessl optimization: 14 skills improved from ≤69% to 85%+. Closes #285, #286. * chore: sync codex skills symlinks [automated] * fix: optimize 18 skills via Tessl review + compliance fix (closes #287) (#291) Phase 1: 18 skills optimized via Tessl (avg 77% → 95%). Closes #287. * feat: add scripts and references to 4 prompt-only skills + Tessl optimization (#292) Phase 2: 3 new scripts + 2 reference files for prompt-only skills. Tessl 45-55% → 94-100%. * feat: add 6 agents + 5 slash commands for full coverage (v2.7.0) (#293) Phase 3: 6 new agents (all 9 categories covered) + 5 slash commands. * fix: Phase 5 verification fixes + docs update (#294) Phase 5 verification fixes * chore: sync codex skills symlinks [automated] * fix: marketplace audit — all 11 plugins validated by Claude Code (#295) Marketplace audit: all 11 plugins validated + installed + tested in Claude Code * fix: restore 7 removed plugins + revert playwright-pro name to pw Reverts two overly aggressive audit changes: - Restored content-creator, demand-gen, fullstack-engineer, aws-architect, product-manager, scrum-master, skill-security-auditor to marketplace - Reverted playwright-pro plugin.json name back to 'pw' (intentional short name) * refactor: split 21 over-500-line skills into SKILL.md + references (#296) * chore: sync codex skills symlinks [automated] * docs: update all documentation with accurate counts and regenerated skill pages - Update skill count to 170, Python tools to 213, references to 314 across all docs - Regenerate all 170 skill doc pages from latest SKILL.md sources - Update CLAUDE.md with v2.1.1 highlights, accurate architecture tree, and roadmap - Update README.md badges and overview table - Update marketplace.json metadata description and version - Update mkdocs.yml, index.md, getting-started.md with correct numbers * fix: add root-level SKILL.md and .codex/instructions.md to all domains (#301) Root cause: CLI tools (ai-agent-skills, agent-skills-cli) look for SKILL.md at the specified install path. 7 of 9 domain directories were missing this file, causing "Skill not found" errors for bundle installs like: npx ai-agent-skills install alirezarezvani/claude-skills/engineering-team Fix: - Add root-level SKILL.md with YAML frontmatter to 7 domains - Add .codex/instructions.md to 8 domains (for Codex CLI discovery) - Update INSTALLATION.md with accurate skill counts (53→170) - Add troubleshooting entry for "Skill not found" error All 9 domains now have: SKILL.md + .codex/instructions.md + plugin.json Closes #301 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add Gemini CLI + OpenClaw support, fix Codex missing 25 skills Gemini CLI: - Add GEMINI.md with activation instructions - Add scripts/gemini-install.sh setup script - Add scripts/sync-gemini-skills.py (194 skills indexed) - Add .gemini/skills/ with symlinks for all skills, agents, commands - Remove phantom medium-content-pro entries from sync script - Add top-level folder filter to prevent gitignored dirs from leaking Codex CLI: - Fix sync-codex-skills.py missing "engineering" domain (25 POWERFUL skills) - Regenerate .codex/skills-index.json: 124 → 149 skills - Add 25 new symlinks in .codex/skills/ OpenClaw: - Add OpenClaw installation section to INSTALLATION.md - Add ClawHub install + manual install + YAML frontmatter docs Documentation: - Update INSTALLATION.md with all 4 platforms + accurate counts - Update README.md: "three platforms" → "four platforms" + Gemini quick start - Update CLAUDE.md with Gemini CLI support in v2.1.1 highlights - Update SKILL-AUTHORING-STANDARD.md + SKILL_PIPELINE.md with Gemini steps - Add OpenClaw + Gemini to installation locations reference table Marketplace: all 18 plugins validated — sources exist, SKILL.md present Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(product,pm): world-class product & PM skills audit — 6 scripts, 5 agents, 7 commands, 23 references/assets Phase 1 — Agent & Command Foundation: - Rewrite cs-project-manager agent (55→515 lines, 4 workflows, 6 skill integrations) - Expand cs-product-manager agent (408→684 lines, orchestrates all 8 product skills) - Add 7 slash commands: /rice, /okr, /persona, /user-story, /sprint-health, /project-health, /retro Phase 2 — Script Gap Closure (2,779 lines): - jira-expert: jql_query_builder.py (22 patterns), workflow_validator.py - confluence-expert: space_structure_generator.py, content_audit_analyzer.py - atlassian-admin: permission_audit_tool.py - atlassian-templates: template_scaffolder.py (Confluence XHTML generation) Phase 3 — Reference & Asset Enrichment: - 9 product references (competitive-teardown, landing-page-generator, saas-scaffolder) - 6 PM references (confluence-expert, atlassian-admin, atlassian-templates) - 7 product assets (templates for PRD, RICE, sprint, stories, OKR, research, design system) - 1 PM asset (permission_scheme_template.json) Phase 4 — New Agents: - cs-agile-product-owner, cs-product-strategist, cs-ux-researcher Phase 5 — Integration & Polish: - Related Skills cross-references in 8 SKILL.md files - Updated product-team/CLAUDE.md (5→8 skills, 6→9 tools, 4 agents, 5 commands) - Updated project-management/CLAUDE.md (0→12 scripts, 3 commands) - Regenerated docs site (177 pages), updated homepage and getting-started Quality audit: 31 files reviewed, 29 PASS, 2 fixed (copy-frameworks.md, governance-framework.md) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: audit and repair all plugins, agents, and commands - Fix 12 command files: correct CLI arg syntax, script paths, and usage docs - Fix 3 agents with broken script/reference paths (cs-content-creator, cs-demand-gen-specialist, cs-financial-analyst) - Add complete YAML frontmatter to 5 agents (cs-growth-strategist, cs-engineering-lead, cs-senior-engineer, cs-financial-analyst, cs-quality-regulatory) - Fix cs-ceo-advisor related agent path - Update marketplace.json metadata counts (224 tools, 341 refs, 14 agents, 12 commands) Verified: all 19 scripts pass --help, all 14 agent paths resolve, mkdocs builds clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: repair 25 Python scripts failing --help across all domains - Fix Python 3.10+ syntax (float | None → Optional[float]) in 2 scripts - Add argparse CLI handling to 9 marketing scripts using raw sys.argv - Fix 10 scripts crashing at module level (wrap in __main__, add argparse) - Make yaml/prefect/mcp imports conditional with stdlib fallbacks (4 scripts) - Fix f-string backslash syntax in project_bootstrapper.py - Fix -h flag conflict in pr_analyzer.py - Fix tech-debt.md description (score → prioritize) All 237 scripts now pass python3 --help verification. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(product-team): close 3 verified gaps in product skills - Fix competitive-teardown/SKILL.md: replace broken references DATA_COLLECTION.md → references/data-collection-guide.md and TEMPLATES.md → references/analysis-templates.md (workflow was broken at steps 2 and 4) - Upgrade landing_page_scaffolder.py: add TSX + Tailwind output format (--format tsx) matching SKILL.md promise of Next.js/React components. 4 design styles (dark-saas, clean-minimal, bold-startup, enterprise). TSX is now default; HTML preserved via --format html - Rewrite README.md: fix stale counts (was 5 skills/15+ tools, now accurately shows 8 skills/9 tools), remove 7 ghost scripts that never existed (sprint_planner.py, velocity_tracker.py, etc.) - Fix tech-debt.md description (score → prioritize) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * release: v2.1.2 — landing page TSX output, brand voice integration, docs update - Landing page generator defaults to Next.js TSX + Tailwind CSS (4 design styles) - Brand voice analyzer integrated into landing page generation workflow - CHANGELOG, CLAUDE.md, README.md updated for v2.1.2 - All 13 plugin.json + marketplace.json bumped to 2.1.2 - Gemini/Codex skill indexes re-synced - Backward compatible: --format html preserved, no breaking changes Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: alirezarezvani <5697919+alirezarezvani@users.noreply.github.com> Co-authored-by: Leo <leo@openclaw.ai> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
8.7 KiB
Template Governance Framework
Overview
Operational framework for managing template lifecycle — creation, updates, deprecation, and quality enforcement with concrete thresholds and decision criteria.
Ownership Model
Roles
Template Owner (1 per template):
- Reviews usage dashboard on the 1st of each quarter
- Archives templates with <5 uses in the past 90 days
- Responds to change requests within 14 calendar days
- Runs quarterly accuracy check: open 3 random pages created from the template, verify content matches current process
- Escalates to committee if change affects >50 users
Template Steward (1 per team/domain):
- Runs monthly usage pull:
CQL: type = page AND label = "template-{name}" AND created >= "now-30d" - Flags templates where >30% of users delete or heavily modify a section (indicates friction)
- Collects and triages feedback — tags Jira tickets with
template-changeand links to template page
Template Committee (3-5 people, for orgs with 20+ templates):
- Meets quarterly (45 min max): reviews new proposals, resolves conflicts, flags duplicates
- Decision rule: approve if template serves >1 team and doesn't duplicate existing template by >60% content overlap
- Publishes quarterly "Template Health" Confluence page with adoption rates and actions taken
Assignment Matrix
| Template Category | Owner Role | Steward Role |
|---|---|---|
| Engineering templates | Engineering Manager | Senior Engineer |
| Product templates | Head of Product | Senior PM |
| Meeting templates | Operations Lead | EA/Admin |
| Project templates | PMO Lead | Senior PM |
| HR/People templates | HR Director | HR Coordinator |
| Company-wide templates | Operations Lead | Template Committee |
Approval Workflow
New Template Proposal
-
Request - Submitter creates proposal with:
- Template name and purpose
- Target audience
- Justification (why existing templates are insufficient)
- Draft content
- Proposed owner
-
Review - Template owner/committee evaluates:
- Does this duplicate an existing template?
- Is the scope appropriate (not too broad or narrow)?
- Does it follow design standards?
- Is it needed by more than one team?
-
Pilot - If approved:
- Deploy to a small group for 2-4 weeks
- Collect feedback on usability and completeness
- Iterate based on feedback
-
Launch - After successful pilot:
- Publish to template library
- Announce to relevant teams
- Add to Template Index page
- Train users if needed
-
Monitor - Post-launch:
- Track adoption rate (first 30 days)
- Collect initial feedback
- Make quick adjustments if needed
Template Update Process
-
Change Request - Anyone can suggest changes via:
- Comment on the template page
- Jira ticket tagged
template-change - Direct message to template owner
-
Assessment - Owner evaluates:
- Impact on existing documents using this template
- Alignment with organizational standards
- Effort required for update
-
Implementation - Owner or steward:
- Makes changes in a draft version
- Reviews with 1-2 frequent users
- Updates version number and changelog
- Publishes updated template
-
Communication - Notify users:
- Post update in relevant Slack/Teams channel
- Update Template Index page
- Send email for major changes
Change Management
Impact Categories
Low Impact (Owner decides):
- Typo fixes and formatting improvements
- Clarifying existing instructions
- Adding optional sections
Medium Impact (Owner + 1 reviewer):
- Adding new required sections
- Changing variable names or structure
- Updating macro usage
High Impact (Committee review):
- Removing sections from widely-used templates
- Merging or splitting templates
- Changing organizational template standards
Communication Plan
| Change Type | Communication | Timeline |
|---|---|---|
| Low impact | Changelog update | Same day |
| Medium impact | Team channel announcement | 1 week notice |
| High impact | Email + meeting + migration guide | 2-4 weeks notice |
Deprecation Process
When to Deprecate
- Template replaced by a better alternative
- Process the template supports has been retired
- Template has zero usage in the past 6 months
- Template is redundant with another active template
Deprecation Steps
- Decision - Owner proposes deprecation with justification
- Announcement - Notify users 30 days before deprecation:
- Mark template with "DEPRECATED" status
- Add deprecation notice at top of template
- Point to replacement template (if applicable)
- Transition Period - 30 days:
- Template still available but marked deprecated
- New documents should use replacement
- Existing documents do not need to change
- Archive - After transition:
- Move template to Archive section
- Remove from active template list
- Keep accessible for historical reference
- Review - 90 days after archive:
- Confirm no active usage
- Add to annual cleanup list if truly unused
Usage Tracking
Metrics & Thresholds
| Metric | Healthy | Flagged | Deprecate |
|---|---|---|---|
| Pages created/month | >10 | 3-10 | <3 for 2 consecutive quarters |
| Unique users/month | >5 | 2-5 | 0-1 for 90 days |
| Section deletion rate | <10% | 10-30% | >30% (users removing sections = template mismatch) |
| Time to first use (new templates) | <7 days | 7-30 days | >30 days (failed launch, re-announce or rethink) |
Tracking via CQL
-- Monthly usage for a specific template
type = page AND label = "template-sprint-retro" AND created >= "now-30d"
-- Stale templates (no usage in 90 days)
type = page AND label IN ("template-sprint-retro", "template-decision-log") AND created < "now-90d" AND created >= "now-91d"
-- All template-created pages for audit
type = page AND label = "template-*" ORDER BY created DESC
Reporting
- Monthly: Top 10 templates by usage → auto-generated Confluence table
- Quarterly: Flag templates below thresholds → owner action required within 14 days
- Annually: Full catalog review — archive anything with 0 uses in 6 months
Quality Standards
Content Checklist (pass/fail per template)
- Every section has placeholder text showing expected content (not just a heading)
- No section references a process, tool, or team that no longer exists
- All Jira macro JQL filters return results (test quarterly)
- Links to other Confluence pages resolve (no 404s)
- Template renders correctly in both desktop and mobile preview
FAIL examples: Template says "Update the JIRA board" but team uses Linear. Template has a "QA Sign-Off" section but team has no QA role. Placeholder text says "TODO: add content here" with no guidance on what content.
Structural Checklist
- Metadata header: owner name, version (semver), status (
active/deprecated/draft), last-reviewed date - Table of Contents macro if template has 4+ sections
- Change History table at bottom (date, author, change description)
- Placeholder text uses
{placeholder}syntax or ac:placeholder macro — visually distinct from real content
Maintenance Triggers
- Template not reviewed in 90+ days → owner gets Jira ticket auto-created via automation
- 3+ unresolved feedback items → escalate to committee
- Broken macro detected → owner notified same day via Slack/email automation
Review Cadence
Quarterly Review (Template Owner)
- Review usage metrics
- Address pending feedback
- Update content for accuracy
- Verify all links and macros work
- Update version number if changed
Semi-Annual Review (Template Committee)
- Review full template catalog
- Identify gaps (missing templates)
- Identify overlaps (duplicate templates)
- Evaluate template standards compliance
- Plan improvements for next half
Annual Review (Leadership — 60 min meeting)
Agenda:
- (10 min) Catalog stats: total templates, usage trend YoY, templates added/deprecated
- (15 min) Top 5 templates by adoption — what makes them work
- (15 min) Bottom 5 templates — deprecate, rework, or retrain?
- (10 min) Gaps identified by teams — templates requested but not yet built
- (10 min) Governance process retro — is the framework itself working? Adjust thresholds, roles, or cadence as needed
Deliverable: Updated Template Health page published within 1 week of meeting
Getting Started
For New Organizations
- Start with 5-10 essential templates (meeting notes, decision record, project plan)
- Assign owners for each template
- Establish basic quality standards
- Review after 90 days and expand
- Formalize governance as template count grows beyond 20