* docs: restructure README.md — 2,539 → 209 lines (#247) - Cut from 2,539 lines / 73 sections to 209 lines / 18 sections - Consolidated 4 install methods into one unified section - Moved all skill details to domain-level READMEs (linked from table) - Front-loaded value prop and keywords for SEO - Added POWERFUL tier highlight section - Added skill-security-auditor showcase section - Removed stale Q4 2025 roadmap, outdated ROI claims, duplicate content - Fixed all internal links - Clean heading hierarchy (H2 for main sections only) Closes #233 Co-authored-by: Leo <leo@openclaw.ai> * fix: enhance 5 skills with scripts, references, and Anthropic best practices (#248) * fix(skill): enhance git-worktree-manager with scripts, references, and Anthropic best practices * fix(skill): enhance mcp-server-builder with scripts, references, and Anthropic best practices * fix(skill): enhance changelog-generator with scripts, references, and Anthropic best practices * fix(skill): enhance ci-cd-pipeline-builder with scripts, references, and Anthropic best practices * fix(skill): enhance prompt-engineer-toolkit with scripts, references, and Anthropic best practices * docs: update README, CHANGELOG, and plugin metadata * fix: correct marketing plugin count, expand thin references --------- Co-authored-by: Leo <leo@openclaw.ai> * ci: Add VirusTotal security scan for skills (#252) * Dev (#231) * Improve senior-fullstack skill description and workflow validation - Expand frontmatter description with concrete actions and trigger clauses - Add validation steps to scaffolding workflow (verify scaffold succeeded) - Add re-run verification step to audit workflow (confirm P0 fixes) * chore: sync codex skills symlinks [automated] * fix(skill): normalize senior-fullstack frontmatter to inline format Normalize YAML description from block scalar (>) to inline single-line format matching all other 50+ skills. Align frontmatter trigger phrases with the body's Trigger Phrases section to eliminate duplication. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(ci): add GITHUB_TOKEN to checkout + restore corrupted skill descriptions - Add token: ${{ secrets.GITHUB_TOKEN }} to actions/checkout@v4 in sync-codex-skills.yml so git-auto-commit-action can push back to branch (fixes: fatal: could not read Username, exit 128) - Restore correct description for incident-commander (was: 'Skill from engineering-team') - Restore correct description for senior-fullstack (was: '>') * fix(ci): pass PROJECTS_TOKEN to fix automated commits + remove duplicate checkout Fixes PROJECTS_TOKEN passthrough for git-auto-commit-action and removes duplicate checkout step in pr-issue-auto-close workflow. * fix(ci): remove stray merge conflict marker in sync-codex-skills.yml (#221) Co-authored-by: Leo <leo@leo-agent-server> * fix(ci): fix workflow errors + add OpenClaw support (#222) * feat: add 20 new practical skills for professional Claude Code users New skills across 5 categories: Engineering (12): - git-worktree-manager: Parallel dev with port isolation & env sync - ci-cd-pipeline-builder: Generate GitHub Actions/GitLab CI from stack analysis - mcp-server-builder: Build MCP servers from OpenAPI specs - changelog-generator: Conventional commits to structured changelogs - pr-review-expert: Blast radius analysis & security scan for PRs - api-test-suite-builder: Auto-generate test suites from API routes - env-secrets-manager: .env management, leak detection, rotation workflows - database-schema-designer: Requirements to migrations & types - codebase-onboarding: Auto-generate onboarding docs from codebase - performance-profiler: Node/Python/Go profiling & optimization - runbook-generator: Operational runbooks from codebase analysis - monorepo-navigator: Turborepo/Nx/pnpm workspace management Engineering Team (2): - stripe-integration-expert: Subscriptions, webhooks, billing patterns - email-template-builder: React Email/MJML transactional email systems Product Team (3): - saas-scaffolder: Full SaaS project generation from product brief - landing-page-generator: High-converting landing pages with copy frameworks - competitive-teardown: Structured competitive product analysis Business Growth (1): - contract-and-proposal-writer: Contracts, SOWs, NDAs per jurisdiction Marketing (1): - prompt-engineer-toolkit: Systematic prompt development & A/B testing Designed for daily professional use and commercial distribution. * chore: sync codex skills symlinks [automated] * docs: update README with 20 new skills, counts 65→86, new skills section * docs: add commercial distribution plan (Stan Store + Gumroad) * docs: rewrite CHANGELOG.md with v2.0.0 release (65 skills, 9 domains) (#226) * docs: rewrite CHANGELOG.md with v2.0.0 release (65 skills, 9 domains) - Consolidate 191 commits since v1.0.2 into proper v2.0.0 entry - Document 12 POWERFUL-tier skills, 37 refactored skills - Add new domains: business-growth, finance - Document Codex support and marketplace integration - Update version history summary table - Clean up [Unreleased] to only planned work * docs: add 24 POWERFUL-tier skills to plugin, fix counts to 85 across all docs - Add engineering-advanced-skills plugin (24 POWERFUL-tier skills) to marketplace.json - Add 13 missing skills to CHANGELOG v2.0.0 (agent-workflow-designer, api-test-suite-builder, changelog-generator, ci-cd-pipeline-builder, codebase-onboarding, database-schema-designer, env-secrets-manager, git-worktree-manager, mcp-server-builder, monorepo-navigator, performance-profiler, pr-review-expert, runbook-generator) - Fix skill count: 86→85 (excl sample-skill) across README, CHANGELOG, marketplace.json - Fix stale 53→85 references in README - Add engineering-advanced-skills install command to README - Update marketplace.json version to 2.0.0 --------- Co-authored-by: Leo <leo@openclaw.ai> * feat: add skill-security-auditor POWERFUL-tier skill (#230) Security audit and vulnerability scanner for AI agent skills before installation. Scans for: - Code execution risks (eval, exec, os.system, subprocess shell injection) - Data exfiltration (outbound HTTP, credential harvesting, env var extraction) - Prompt injection in SKILL.md (system override, role hijack, safety bypass) - Dependency supply chain (typosquatting, unpinned versions, runtime installs) - File system abuse (boundary violations, binaries, symlinks, hidden files) - Privilege escalation (sudo, SUID, cron manipulation, shell config writes) - Obfuscation (base64, hex encoding, chr chains, codecs) Produces clear PASS/WARN/FAIL verdict with per-finding remediation guidance. Supports local dirs, git repo URLs, JSON output, strict mode, and CI/CD integration. Includes: - scripts/skill_security_auditor.py (1049 lines, zero dependencies) - references/threat-model.md (complete attack vector documentation) - SKILL.md with usage guide and report format Tested against: rag-architect (PASS), agent-designer (PASS), senior-secops (FAIL - correctly flagged eval/exec patterns). Co-authored-by: Leo <leo@openclaw.ai> * docs: add skill-security-auditor to marketplace, README, and CHANGELOG - Add standalone plugin entry for skill-security-auditor in marketplace.json - Update engineering-advanced-skills plugin description to include it - Update skill counts: 85→86 across README, CHANGELOG, marketplace - Add install command to README Quick Install section - Add to CHANGELOG [Unreleased] section --------- Co-authored-by: Baptiste Fernandez <fernandez.baptiste1@gmail.com> Co-authored-by: alirezarezvani <5697919+alirezarezvani@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Leo <leo@leo-agent-server> Co-authored-by: Leo <leo@openclaw.ai> * Dev (#249) * docs: restructure README.md — 2,539 → 209 lines (#247) - Cut from 2,539 lines / 73 sections to 209 lines / 18 sections - Consolidated 4 install methods into one unified section - Moved all skill details to domain-level READMEs (linked from table) - Front-loaded value prop and keywords for SEO - Added POWERFUL tier highlight section - Added skill-security-auditor showcase section - Removed stale Q4 2025 roadmap, outdated ROI claims, duplicate content - Fixed all internal links - Clean heading hierarchy (H2 for main sections only) Closes #233 Co-authored-by: Leo <leo@openclaw.ai> * fix: enhance 5 skills with scripts, references, and Anthropic best practices (#248) * fix(skill): enhance git-worktree-manager with scripts, references, and Anthropic best practices * fix(skill): enhance mcp-server-builder with scripts, references, and Anthropic best practices * fix(skill): enhance changelog-generator with scripts, references, and Anthropic best practices * fix(skill): enhance ci-cd-pipeline-builder with scripts, references, and Anthropic best practices * fix(skill): enhance prompt-engineer-toolkit with scripts, references, and Anthropic best practices * docs: update README, CHANGELOG, and plugin metadata * fix: correct marketing plugin count, expand thin references --------- Co-authored-by: Leo <leo@openclaw.ai> --------- Co-authored-by: Leo <leo@openclaw.ai> * Dev (#250) * docs: restructure README.md — 2,539 → 209 lines (#247) - Cut from 2,539 lines / 73 sections to 209 lines / 18 sections - Consolidated 4 install methods into one unified section - Moved all skill details to domain-level READMEs (linked from table) - Front-loaded value prop and keywords for SEO - Added POWERFUL tier highlight section - Added skill-security-auditor showcase section - Removed stale Q4 2025 roadmap, outdated ROI claims, duplicate content - Fixed all internal links - Clean heading hierarchy (H2 for main sections only) Closes #233 Co-authored-by: Leo <leo@openclaw.ai> * fix: enhance 5 skills with scripts, references, and Anthropic best practices (#248) * fix(skill): enhance git-worktree-manager with scripts, references, and Anthropic best practices * fix(skill): enhance mcp-server-builder with scripts, references, and Anthropic best practices * fix(skill): enhance changelog-generator with scripts, references, and Anthropic best practices * fix(skill): enhance ci-cd-pipeline-builder with scripts, references, and Anthropic best practices * fix(skill): enhance prompt-engineer-toolkit with scripts, references, and Anthropic best practices * docs: update README, CHANGELOG, and plugin metadata * fix: correct marketing plugin count, expand thin references --------- Co-authored-by: Leo <leo@openclaw.ai> --------- Co-authored-by: Leo <leo@openclaw.ai> * ci: add VirusTotal security scan for skills - Scans changed skill directories on PRs to dev/main - Scans all skills on release publish - Posts scan results as PR comment with analysis links - Rate-limited to 4 req/min (free tier compatible) - Appends VirusTotal links to release body on publish * fix: resolve YAML lint errors in virustotal workflow - Add document start marker (---) - Quote 'on' key for truthy lint rule - Remove trailing spaces - Break long lines under 160 char limit --------- Co-authored-by: Baptiste Fernandez <fernandez.baptiste1@gmail.com> Co-authored-by: alirezarezvani <5697919+alirezarezvani@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Leo <leo@leo-agent-server> Co-authored-by: Leo <leo@openclaw.ai> * feat: add playwright-pro plugin — production-grade Playwright testing toolkit (#254) Complete Claude Code plugin with: - 9 skills (/pw:init, generate, review, fix, migrate, coverage, testrail, browserstack, report) - 3 specialized agents (test-architect, test-debugger, migration-planner) - 55 test case templates across 11 categories (auth, CRUD, checkout, search, forms, dashboard, settings, onboarding, notifications, API, accessibility) - TestRail MCP server (TypeScript) — 8 tools for bidirectional sync - BrowserStack MCP server (TypeScript) — 7 tools for cross-browser testing - Smart hooks (auto-validate tests, auto-detect Playwright projects) - 6 curated reference docs (golden rules, locators, assertions, fixtures, pitfalls, flaky tests) - Leverages Claude Code built-ins (/batch, /debug, Explore subagent) - Zero-config for core features; TestRail/BrowserStack via env vars - Both TypeScript and JavaScript support throughout Co-authored-by: Leo <leo@openclaw.ai> * feat: add playwright-pro to marketplace registry (#256) - New plugin: playwright-pro (9 skills, 3 agents, 55 templates, 2 MCP servers) - Install: /plugin install playwright-pro@claude-code-skills - Total marketplace plugins: 17 Co-authored-by: Leo <leo@openclaw.ai> * fix: integrate playwright-pro across all platforms (#258) - Add root SKILL.md for OpenClaw and ClawHub compatibility - Add to README: Skills Overview table, install section, badge count - Regenerate .codex/skills-index.json with playwright-pro entry - Add .codex/skills/playwright-pro symlink for Codex CLI - Fix YAML frontmatter (single-line description for index parsing) Platforms verified: - Claude Code: marketplace.json ✅ (merged in PR #256) - Codex CLI: symlink + skills-index.json ✅ - OpenClaw: SKILL.md auto-discovered by install script ✅ - ClawHub: published as playwright-pro@1.1.0 ✅ Co-authored-by: Leo <leo@openclaw.ai> * docs: update CLAUDE.md — reflect 87 skills across 9 domains Sync CLAUDE.md with actual repository state: add Engineering POWERFUL tier (25 skills), update all skill counts, add plugin registry references, and replace stale sprint section with v2.0.0 version info. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: mention Claude Code in project description Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add self-improving-agent plugin — auto-memory curation for Claude Code (#260) New plugin: engineering-team/self-improving-agent/ - 5 skills: /si:review, /si:promote, /si:extract, /si:status, /si:remember - 2 agents: memory-analyst, skill-extractor - 1 hook: PostToolUse error capture (zero overhead on success) - 3 reference docs: memory architecture, promotion rules, rules directory patterns - 2 templates: rule template, skill template - 20 files, 1,829 lines Integrates natively with Claude Code's auto-memory (v2.1.32+). Reads from ~/.claude/projects/<path>/memory/ — no duplicate storage. Promotes proven patterns from MEMORY.md to CLAUDE.md or .claude/rules/. Also: - Added to marketplace.json (18 plugins total) - Added to README (Skills Overview + install section) - Updated badge count to 88+ - Regenerated .codex/skills-index.json + symlink Co-authored-by: Leo <leo@openclaw.ai> * feat: C-Suite expansion — 8 new executive advisory roles (2→10) (#264) * feat: C-Suite expansion — 8 new executive advisory roles Add COO, CPO, CMO, CFO, CRO, CISO, CHRO advisors and Executive Mentor. Expands C-level advisory from 2 to 10 roles with 74 total files. Each role includes: - SKILL.md (lean, <5KB, ~1200 tokens for context efficiency) - Reference docs (loaded on demand, not at startup) - Python analysis scripts (stdlib only, runnable CLI) Executive Mentor features /em: slash commands (challenge, board-prep, hard-call, stress-test, postmortem) with devil's advocate agent. 21 Python tools, 24 reference frameworks, 28,379 total lines. All SKILL.md files combined: ~17K tokens (8.5% of 200K context window). Badge: 88 → 116 skills * feat: C-Suite orchestration layer + 18 complementary skills ORCHESTRATION (new): - cs-onboard: Founder interview → company-context.md - chief-of-staff: Routing, synthesis, inter-agent orchestration - board-meeting: 6-phase multi-agent deliberation protocol - decision-logger: Two-layer memory (raw transcripts + approved decisions) - agent-protocol: Inter-agent invocation with loop prevention - context-engine: Company context loading + anonymization CROSS-CUTTING CAPABILITIES (new): - board-deck-builder: Board/investor update assembly - scenario-war-room: Cascading multi-variable what-if modeling - competitive-intel: Systematic competitor tracking + battlecards - org-health-diagnostic: Cross-functional health scoring (8 dimensions) - ma-playbook: M&A strategy (acquiring + being acquired) - intl-expansion: International market entry frameworks CULTURE & COLLABORATION (new): - culture-architect: Values → behaviors, culture code, health assessment - company-os: EOS/Scaling Up operating system selection + implementation - founder-coach: Founder development, delegation, blind spots - strategic-alignment: Strategy cascade, silo detection, alignment scoring - change-management: ADKAR-based change rollout framework - internal-narrative: One story across employees/investors/customers UPGRADES TO EXISTING ROLES: - All 10 roles get reasoning technique directives - All 10 roles get company-context.md integration - All 10 roles get board meeting isolation rules - CEO gets stage-adaptive temporal horizons (seed→C) Key design decisions: - Two-layer memory prevents hallucinated consensus from rejected ideas - Phase 2 isolation: agents think independently before cross-examination - Executive Mentor (The Critic) sees all perspectives, others don't - 25 Python tools total (stdlib only, no dependencies) 52 new files, 10 modified, 10,862 new lines. Total C-suite ecosystem: 134 files, 39,131 lines. * fix: connect all dots — Chief of Staff routes to all 28 skills - Added complementary skills registry to routing-matrix.md - Chief of Staff SKILL.md now lists all 28 skills in ecosystem - Added integration tables to scenario-war-room and competitive-intel - Badge: 116 → 134 skills - README: C-Level Advisory count 10 → 28 Quality audit passed: ✅ All 10 roles: company-context, reasoning, isolation, invocation ✅ All 6 phases in board meeting ✅ Two-layer memory with DO_NOT_RESURFACE ✅ Loop prevention (no self-invoke, max depth 2, no circular) ✅ All /em: commands present ✅ All complementary skills cross-reference roles ✅ Chief of Staff routes to every skill in ecosystem * refactor: CEO + CTO advisors upgraded to C-suite parity Both roles now match the structural standard of all new roles: - CEO: 11.7KB → 6.8KB SKILL.md (heavy content stays in references) - CTO: 10KB → 7.2KB SKILL.md (heavy content stays in references) Added to both: - Integration table (who they work with and when) - Key diagnostic questions - Structured metrics dashboard table - Consistent section ordering (Keywords → Quick Start → Responsibilities → Questions → Metrics → Red Flags → Integration → Reasoning → Context) CEO additions: - Stage-adaptive temporal horizons (seed=3m/6m/12m → B+=1y/3y/5y) - Cross-references to culture-architect and board-deck-builder CTO additions: - Key Questions section (7 diagnostic questions) - Structured metrics table (DORA + debt + team + architecture + cost) - Cross-references to all peer roles All 10 roles now pass structural parity: ✅ Keywords ✅ QuickStart ✅ Questions ✅ Metrics ✅ RedFlags ✅ Integration * feat: add proactive triggers + output artifacts to all 10 roles Every C-suite role now specifies: - Proactive Triggers: 'surface these without being asked' — context-driven early warnings that make advisors proactive, not reactive - Output Artifacts: concrete deliverables per request type (what you ask → what you get) CEO: runway alerts, board prep triggers, strategy review nudges CTO: deploy frequency monitoring, tech debt thresholds, bus factor flags COO: blocker detection, scaling threshold warnings, cadence gaps CPO: retention curve monitoring, portfolio dog detection, research gaps CMO: CAC trend monitoring, positioning gaps, budget staleness CFO: runway forecasting, burn multiple alerts, scenario planning gaps CRO: NRR monitoring, pipeline coverage, pricing review triggers CISO: audit overdue alerts, compliance gaps, vendor risk CHRO: retention risk, comp band gaps, org scaling thresholds Executive Mentor: board prep triggers, groupthink detection, hard call surfacing This transforms the C-suite from reactive advisors into proactive partners. * feat: User Communication Standard — structured output for all roles Defines 3 output formats in agent-protocol/SKILL.md: 1. Standard Output: Bottom Line → What → Why → How to Act → Risks → Your Decision 2. Proactive Alert: What I Noticed → Why It Matters → Action → Urgency (🔴🟡⚪) 3. Board Meeting: Decision Required → Perspectives → Agree/Disagree → Critic → Action Items 10 non-negotiable rules: - Bottom line first, always - Results and decisions only (no process narration) - What + Why + How for every finding - Actions have owners and deadlines ('we should consider' is banned) - Decisions framed as options with trade-offs - Founder is the highest authority — roles recommend, founder decides - Risks are concrete (if X → Y, costs $Z) - Max 5 bullets per section - No jargon without explanation - Silence over fabricated updates All 10 roles reference this standard. Chief of Staff enforces it as a quality gate. Board meeting Phase 4 uses the Board Meeting Output format. * feat: Internal Quality Loop — verification before delivery No role presents to the founder without passing verification: Step 1: Self-Verification (every role, every time) - Source attribution: where did each data point come from? - Assumption audit: [VERIFIED] vs [ASSUMED] tags on every finding - Confidence scoring: 🟢 high / 🟡 medium / 🔴 low per finding - Contradiction check against company-context + decision log - 'So what?' test: every finding needs a business consequence Step 2: Peer Verification (cross-functional) - Financial claims → CFO validates math - Revenue projections → CRO validates pipeline backing - Technical feasibility → CTO validates - People/hiring impact → CHRO validates - Skip for single-domain, low-stakes questions Step 3: Critic Pre-Screen (high-stakes only) - Irreversible decisions, >20% runway impact, strategy changes - Executive Mentor finds weakest point before founder sees it - Suspicious consensus triggers mandatory pre-screen Step 4: Course Correction (after founder feedback) - Approve → log + assign actions - Modify → re-verify changed parts - Reject → DO_NOT_RESURFACE + learn why - 30/60/90 day post-decision review Board meeting contributions now require self-verified format with confidence tags and source attribution on every finding. * fix: resolve PR review issues 1, 4, and minor observation Issue 1: c-level-advisor/CLAUDE.md — completely rewritten - Was: 2 skills (CEO, CTO only), dated Nov 2025 - Now: full 28-skill ecosystem map with architecture diagram, all roles/orchestration/cross-cutting/culture skills listed, design decisions, integration with other domains Issue 4: Root CLAUDE.md — updated all stale counts - 87 → 134 skills across all 3 references - C-Level: 2 → 33 (10 roles + 5 mentor commands + 18 complementary) - Tool count: 160+ → 185+ - Reference count: 200+ → 250+ Minor observation: Documented plugin.json convention - Explained in c-level-advisor/CLAUDE.md that only executive-mentor has plugin.json because only it has slash commands (/em: namespace) - Other skills are invoked by name through Chief of Staff or directly Also fixed: README.md 88+ → 134 in two places (first line + skills section) * fix: update all plugin/index registrations for 28-skill C-suite 1. c-level-advisor/.claude-plugin/plugin.json — v2.0.0 - Was: 2 skills, generic description - Now: all 28 skills listed with descriptions, all 25 scripts, namespace 'cs', full ecosystem description 2. .codex/skills-index.json — added 18 complementary skills - Was: 10 roles only - Now: 28 total c-level entries (10 roles + 6 orchestration + 6 cross-cutting + 6 culture) - Each with full description for skill discovery 3. .claude-plugin/marketplace.json — updated c-level-skills entry - Was: generic 2-skill description - Now: v2.0.0, full 28-skill ecosystem description, skills_count: 28, scripts_count: 25 * feat: add root SKILL.md for c-level-advisor ClawHub package --------- Co-authored-by: Leo <leo@openclaw.ai> * chore: sync codex skills symlinks [automated] * feat: Marketing Division expansion — 7 → 42 skills (#266) * feat: Skill Authoring Standard + Marketing Expansion plans SKILL-AUTHORING-STANDARD.md — the DNA of every skill in this repo: 10 universal patterns codified from C-Suite innovations + Corey Haines' marketingskills patterns: 1. Context-First: check domain context, ask only for gaps 2. Practitioner Voice: expert persona, goal-oriented, not textbook 3. Multi-Mode Workflows: build from scratch / optimize existing / situation-specific 4. Related Skills Navigation: when to use, when NOT to, bidirectional 5. Reference Separation: SKILL.md lean (≤10KB), refs deep 6. Proactive Triggers: surface issues without being asked 7. Output Artifacts: request → specific deliverable mapping 8. Quality Loop: self-verify, confidence tagging 9. Communication Standard: bottom line first, structured output 10. Python Tools: stdlib-only, CLI-first, JSON output, sample data Marketing expansion plans for 40-skill marketing division build. * feat: marketing foundation — context + ops router + authoring standard marketing-context/: Foundation skill every marketing skill reads first - SKILL.md: 3 modes (auto-draft, guided interview, update) - templates/marketing-context-template.md: 14 sections covering product, audience, personas, pain points, competitive landscape, differentiation, objections, switching dynamics, customer language (verbatim), brand voice, style guide, proof points, SEO context, goals - scripts/context_validator.py: Scores completeness 0-100, section-by-section marketing-ops/: Central router for 40-skill marketing ecosystem - Full routing matrix: 7 pods + cross-domain routing to 6 skills in business-growth, product-team, engineering-team, c-level-advisor - Campaign orchestration sequences (launch, content, CRO sprint) - Quality gate matching C-Suite standard - scripts/campaign_tracker.py: Campaign status tracking with progress, overdue detection, pod coverage, blocker identification SKILL-AUTHORING-STANDARD.md: Universal DNA for all skills - 10 patterns: context-first, practitioner voice, multi-mode workflows, related skills navigation, reference separation, proactive triggers, output artifacts, quality loop, communication standard, python tools - Quality checklist for skill completion verification - Domain context file mapping for all 5 domains * feat: import 20 workspace marketing skills + standard sections Imported 20 marketing skills from OpenClaw workspace into repo: Content Pod (5): content-strategy, copywriting, copy-editing, social-content, marketing-ideas SEO Pod (2): seo-audit (+ references enriched by subagent), programmatic-seo (+ refs) CRO Pod (5): page-cro, form-cro, signup-flow-cro, onboarding-cro, popup-cro, paywall-upgrade-cro Channels Pod (2): email-sequence, paid-ads Growth + Intel + GTM (5): ab-test-setup, competitor-alternatives, marketing-psychology, launch-strategy, brand-guidelines All 29 skills now have standard sections per SKILL-AUTHORING-STANDARD.md: ✅ Proactive Triggers (4-5 per skill) ✅ Output Artifacts table ✅ Communication standard reference ✅ Related Skills with WHEN/NOT disambiguation Subagents enriched 8 skills with additional reference docs: seo-audit, programmatic-seo, page-cro, form-cro, onboarding-cro, popup-cro, paywall-upgrade-cro, email-sequence 43 files, 10,566 lines added. * feat: build 13 new marketing skills + social-media-manager upgrade All skills are 100% original work — inspired by industry best practices, written from scratch in our own voice following SKILL-AUTHORING-STANDARD.md. NEW Content Pod (2): content-production — full research→draft→optimize pipeline, content_scorer.py content-humanizer — AI pattern detection + voice injection, humanizer_scorer.py NEW SEO Pod (3): ai-seo — AI search optimization (AEO/GEO/LLMO), entirely new category schema-markup — JSON-LD structured data, schema_validator.py site-architecture — URL structure + internal linking, sitemap_analyzer.py NEW Channels Pod (2): cold-email — B2B outreach (distinct from email-sequence lifecycle) ad-creative — bulk ad generation + platform specs, ad_copy_validator.py NEW Growth Pod (3): churn-prevention — cancel flows + save offers + dunning, churn_impact_calculator.py referral-program — referral + affiliate programs free-tool-strategy — engineering as marketing NEW Intelligence Pod (1): analytics-tracking — GA4/GTM setup + event taxonomy, tracking_plan_generator.py NEW Sales Pod (1): pricing-strategy — pricing, packaging, monetization UPGRADED: social-media-analyzer → social-media-manager (strategy, calendar, community) Totals: 42 skills, 27 Python scripts, 60 reference docs, 163 files, 43,265 lines * feat: update index, marketplace, README for 42 marketing skills - skills-index.json: 89 → 124 skills (42 marketing entries) - marketplace.json: marketing-skills v2.0.0 (42 skills, 27 tools) - README.md: badge 134 → 169, marketing row updated - prompt-engineer-toolkit: added YAML frontmatter - Removed build logs from repo - Parity check: 42/42 passed (YAML + Related + Proactive + Output + Communication) * fix: merge content-creator into content-production, split marketing-psychology Quality audit fixes: 1. content-creator → DEPRECATED redirect - Scripts (brand_voice_analyzer.py, seo_optimizer.py) moved to content-production - SKILL.md replaced with redirect to content-production + content-strategy - Eliminates duplicate routing confusion 2. marketing-psychology → 24KB split to 6.8KB + reference - 70+ mental models moved to references/mental-models-catalog.md (397 lines) - SKILL.md now lean: categories overview, most-used models, quick reference - Saves ~4,300 tokens per invocation * feat: add plugin configs, Codex/OpenClaw compatibility, ClawHub packaging - marketing-skill/SKILL.md: ClawHub-compatible root with Quick Start for Claude Code, Codex CLI, OpenClaw - marketing-skill/CLAUDE.md: Agent instructions (routing, context, anti-patterns) - marketing-skill/.codex/instructions.md: Codex CLI skill routing - .claude-plugin/marketplace.json: deduplicated, marketing-skills v2.0.0 - .codex/skills-index.json: content-creator marked deprecated, psychology updated - Total: 42 skills, 27 Python tools, 60 references, 18 plugins * feat: add 16 Python tools to knowledge-only skills Enriched 12 previously tool-less skills with practical Python scripts: - seo-audit/seo_checker.py — HTML on-page SEO analysis (0-100) - copywriting/headline_scorer.py — headline quality scoring (0-100) - copy-editing/readability_scorer.py — Flesch + passive + filler detection - content-strategy/topic_cluster_mapper.py — keyword clustering - page-cro/conversion_audit.py — HTML CRO signal analysis (0-100) - paid-ads/roas_calculator.py — ROAS/CPA/CPL calculator - email-sequence/sequence_analyzer.py — email sequence scoring (0-100) - form-cro/form_field_analyzer.py — form field CRO audit (0-100) - onboarding-cro/activation_funnel_analyzer.py — funnel drop-off analysis - programmatic-seo/url_pattern_generator.py — URL pattern planning - ab-test-setup/sample_size_calculator.py — statistical sample sizing - signup-flow-cro/funnel_drop_analyzer.py — signup funnel analysis - launch-strategy/launch_readiness_scorer.py — launch checklist scoring - competitor-alternatives/comparison_matrix_builder.py — feature comparison - social-media-manager/social_calendar_generator.py — content calendar - readability_scorer.py — fixed demo mode for non-TTY execution All 43/43 scripts pass execution. All stdlib-only, zero pip installs. Total: 42 skills, 43 Python tools, 60+ reference docs. * feat: add 3 more Python tools + improve 6 existing scripts New tools from build agent: - email-sequence/scripts/sequence_analyzer.py — email sequence scoring (91/100 demo) - paid-ads/scripts/roas_calculator.py — ROAS/CPA/CPL/break-even calculator - competitor-alternatives/scripts/comparison_matrix_builder.py — feature matrix Improved scripts (better demo modes, fuller analysis): - seo_checker.py, headline_scorer.py, readability_scorer.py, conversion_audit.py, topic_cluster_mapper.py, launch_readiness_scorer.py Total: 42 skills, 47 Python tools, all passing. * fix: remove duplicate scripts from deprecated content-creator Scripts already live in content-production/scripts/. The content-creator directory is now a pure redirect (SKILL.md only + legacy assets/refs). * fix: scope VirusTotal scan to executable files only Skip scanning .md, .py, .json, .yml — they're plain text files that VirusTotal can't meaningfully analyze. This prevents 429 rate limit errors on PRs with many text file changes (like 42 marketing skills). Scan still covers: .js, .ts, .sh, .mjs, .cjs, .exe, .dll, .so, .bin, .wasm --------- Co-authored-by: Leo <leo@openclaw.ai> * chore: sync codex skills symlinks [automated] --------- Co-authored-by: Leo <leo@openclaw.ai> Co-authored-by: Baptiste Fernandez <fernandez.baptiste1@gmail.com> Co-authored-by: alirezarezvani <5697919+alirezarezvani@users.noreply.github.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Leo <leo@leo-agent-server>
9.0 KiB
Cold Email Outreach Frameworks
Three frameworks that work, when to use each, and how to apply them with examples.
How to Use This Guide
A framework is a structure, not a script. Use it to organize your thinking, then write in your own voice. If an email sounds like it was written from a template, the framework failed.
Each framework works best in specific situations — the mismatch between framework and context is why most cold emails fall flat.
Framework 1: Observation → Problem → Proof → Ask (OPPA)
Best for: Prospects where you have a specific, real observation (trigger event, signal, public info). This is the most versatile framework and the default for most B2B cold email.
What it does: Starts with something real and specific about them, connects it to a problem they likely have, brings in credibility, and asks a focused question.
Structure
[Observation]: Something specific and true about them right now.
[Problem]: The logical challenge or risk that creates.
[Proof]: One concrete piece of evidence you can solve it.
[Ask]: A single, low-friction question or request.
How to Write Each Part
Observation — This must be:
- Specific (not "I see you're in the software industry")
- Recent (not something from 2 years ago)
- Relevant to the problem you're about to raise
- Non-creepy (public info: LinkedIn, press, job postings, tech stack signals)
Good observations:
- "Saw the announcement that you're opening a Berlin office."
- "Noticed you're hiring 4 SDRs simultaneously — unusual to scale the team that fast."
- "Your last three blog posts have all been about compliance — guessing that's a pressure point right now."
Problem — This should feel like something they already know is true, not something you're trying to convince them of.
- ❌ "Companies like yours struggle with X."
- ✅ "That scale-up usually surfaces a bunch of process gaps that are invisible when you're smaller."
Proof — Keep it tight. One result, one customer name (if allowed), or one specific claim. Not a list.
- ❌ "We work with 300+ companies and have won 7 awards."
- ✅ "We helped a similar-sized team in fintech cut SDR ramp time by 40% in the first quarter."
Ask — One ask. Low friction. Makes it easy to say yes or no.
- ❌ "Would you be open to a 45-minute product walkthrough with our sales team?"
- ✅ "Worth 15 minutes to compare notes on how you're handling this?"
Full Example
Subject: your Berlin expansion
Congrats on the Berlin announcement — Series B followed by a new market in the same quarter is a big move.
The part that usually bites teams at this stage: the go-to-market motion that worked for your home market rarely translates directly, especially if you're dealing with different buyer personas and a cold pipeline.
We've helped three B2B SaaS teams with exactly this transition — the fastest got pipeline moving in Germany within 90 days. Happy to share what worked.
Worth a 20-minute call to compare notes?
Framework 2: Question → Value → Ask (QVA)
Best for: Situations where you don't have a strong trigger event, but you understand the prospect's world well enough to lead with a sharp insight or question. Good for segmented outreach to a persona with a known, common pain.
What it does: Opens with a question that creates cognitive engagement — they can't help but answer it in their head. Then delivers value before asking for anything.
Structure
[Question]: A question they're probably already asking themselves.
[Value]: An insight, reframe, or resource that helps them — before they've agreed to anything.
[Ask]: Low-friction request to continue the conversation.
How to Write Each Part
Question — Not a rhetorical sales question ("Are you struggling with X?"). An actual, thoughtful question they'd ask at a team meeting.
- ❌ "Are you struggling to hit your pipeline targets?"
- ✅ "What's your current approach to EMEA expansion — inside sales, channel, or hybrid?"
The question works because it's specific enough that only a relevant person can answer it, and answering it in their head pulls them into the email.
Value — Give something before asking for anything. This is the differentiator. Options:
- A useful insight from your experience working in their space
- A specific data point or benchmark they probably don't have
- A framework or reframe that's genuinely useful
- A short, actionable observation about their situation
This doesn't need to be long. Two sentences of genuine value beats two paragraphs of soft selling.
Ask — Same rules as OPPA. One ask, low friction, specific.
Full Example
Subject: EMEA expansion approach
Quick question — are you planning to open EMEA with a field sales team, or running it remotely from the US for the first 12 months?
I ask because we've seen both approaches play out across about 30 SaaS companies doing this move, and the one that consistently underperforms is the "remote first, hire local later" model — not because of the sales motion, but because of the support/onboarding gap that follows when you close enterprise deals in a timezone you don't cover.
Happy to share a quick breakdown of what the fastest-scaling teams do differently if that's useful. 15 minutes?
Framework 3: Trigger → Insight → Ask (TIA)
Best for: When you have a very specific, time-sensitive trigger event and want to move fast. Great for sales teams with intent signals, tech stack changes, funding news, leadership changes, or industry regulatory shifts.
What it does: Names the trigger directly, provides a non-obvious insight about what that trigger means, and asks a focused question while the timing is relevant.
Structure
[Trigger]: Name the specific event/signal you observed.
[Insight]: Something non-obvious about what that trigger typically means/leads to.
[Ask]: Direct, time-aware request.
How to Write Each Part
Trigger — Be specific and direct. Don't be coy about why you're reaching out.
- ❌ "I was browsing LinkedIn and happened to notice..."
- ✅ "Saw the funding announcement this morning."
Insight — The non-obvious part is what separates this from lazy trigger-based outreach. You're not just saying "congrats on the funding" — you're showing you understand what that trigger means operationally.
Pattern: "That usually means [specific operational challenge] that most [their role] underestimate."
- ❌ "Congrats! We'd love to help you grow."
- ✅ "Series A typically means the first real pressure to build repeatable pipeline — and most companies at this stage haven't yet figured out which channels actually scale."
Ask — Frame the timing as genuine, not manufactured urgency.
- ❌ "Act now before it's too late!"
- ✅ "First 60 days post-funding is when this gets set up or doesn't — worth a quick call?"
Full Example
Subject: post-Series A pipeline
Saw the Series A close — congrats.
The next 90 days are when pipeline architecture either gets built properly or gets bolted together in a way that causes problems at Series B. Most founders don't realize until 18 months later that they're paying for shortcuts made now.
We work specifically with post-Series A B2B SaaS teams setting up their outbound motion for the first time. Happy to do a no-strings 20-minute call on what works and what doesn't at your stage.
Useful?
Choosing the Right Framework
| Situation | Use |
|---|---|
| Strong trigger event (funding, hiring, news, tech change) | TIA |
| Good persona understanding, no specific trigger | QVA |
| Mix of trigger + problem knowledge | OPPA |
| Referral or warm intro context | OPPA with referral opener |
| Re-engaging a past prospect | QVA with callback to previous context |
Combining Frameworks
These frameworks aren't rigid. In practice, the best emails blend elements:
- TIA trigger + OPPA proof
- QVA question + TIA timing
- OPPA observation + QVA value
What you can't blend: two questions, two proof points, or two asks. One of each, always.
Subject Line Frameworks
Subject lines have their own logic — separate from the email body.
The Blank Subject
Two or three words, no capitalization, feels like an internal message.
quick questioncold outreachyour q3 pipeline
The Named Trigger
Specific enough to signal you did research, vague enough to create curiosity.
your Series ABerlin officeyour ATS stack
The Shared Context
Implies a pre-existing relationship or shared frame.
re: EMEA expansionfollowing up on the hiring spike
The Named Person (Referral)
Only use if the referral is real — never fake this.
[Mutual Name] suggested I reach out[Name] mentioned you're building out your SDR team
Never Use
Quick question about your [product category] strategy!Revolutionize your [function] with [product name][FIRST NAME], we have a special offer for you- Emojis
- ALL CAPS
- Question marks (feels like an ad)