Dev - #362
Conversation
…commands - Content Strategist: 6 commands (/content:audit, cluster, brief, calendar, repurpose, seo), 8 bundled skills - Product Manager: 7 commands (/pm:story, prd, prioritize, experiment, sprint, retro, metrics), 6 bundled skills - DevOps Engineer: 7 commands (/devops:deploy, infra, docker, monitor, incident, security, cost), 4 bundled skills - Finance Lead: 6 commands (/finance:model, fundraise, pricing, burn, unit-economics, board), 2 bundled skills Total personas: 3 → 7
…Metrics Aligns new personas with agency-agents structure: - Core Capabilities: scannable bullet-list summary - Decision Framework: when to use (and when NOT to) - Success Metrics: quantified outcomes All 4 Tier 1 personas now match full agency-agents spec.
…s, not job descriptions - Cut 70% bloat (750 lines removed, 220 added) - Dropped corporate sections (Core Capabilities, Decision Framework → merged naturally) - Commands as the centerpiece — what you DO, not what you ARE - 'How You Think' + 'What You Never Do' = personality, not résumé - 'When to Use Me' with ✅/❌ = clear routing - 'What Good Looks Like' = success without corporate metric tables Our format: opinionated colleague with tools Agency-agents format: job description with capabilities Different on purpose.
…r plugins, codex, gemini, cursor
|
test comment |
CLAUDE.mdThis file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. Project PurposeThis is a comprehensive skills library for Claude AI and Claude Code - reusable, production-ready skill packages that bundle domain expertise, best practices, analysis tools, and strategic frameworks. The repository provides modular skills that teams can download and use directly in their workflows. Current Scope: 177 production-ready skills across 9 domains with 254 Python automation tools, 357 reference guides, 17 agents, and 22 slash commands. Key Distinction: This is NOT a traditional application. It's a library of skill packages meant to be extracted and deployed by users into their own Claude workflows. Navigation MapThis repository uses modular documentation. For domain-specific guidance, see:
Architecture OverviewRepository StructureSkill Package PatternEach skill follows this structure: Design Philosophy: Skills are self-contained packages. Each includes executable tools (Python scripts), knowledge bases (markdown references), and user-facing templates. Teams can extract a skill folder and use it immediately. Key Pattern: Knowledge flows from Git WorkflowBranch Strategy: feature → dev → main (PR only) Branch Protection Active: Main branch requires PR approval. Direct pushes blocked. Quick Start# 1. Always start from dev
git checkout dev
git pull origin dev
# 2. Create feature branch
git checkout -b feature/agents-{name}
# 3. Work and commit (conventional commits)
feat(agents): implement cs-{agent-name}
fix(tool): correct calculation logic
docs(workflow): update branch strategy
# 4. Push and create PR to dev
git push origin feature/agents-{name}
gh pr create --base dev --head feature/agents-{name}
# 5. After approval, PR merges to dev
# 6. Periodically, dev merges to main via PRBranch Protection Rules:
See documentation/WORKFLOW.md for complete workflow guide. Development EnvironmentNo build system or test frameworks - intentional design choice for portability. Python Scripts:
If adding dependencies:
Current VersionVersion: v2.1.2 (latest) v2.1.2 Highlights:
v2.1.1 (2026-03-07):
v2.0.0 (2026-02-16):
Past Sprints: See documentation/delivery/ and CHANGELOG.md for history. RoadmapPhase 1-2 Complete: 177 production-ready skills deployed across 9 domains
See domain-specific roadmaps in each skill folder's README.md or roadmap files. Key Principles
ClawHub Publishing ConstraintsThis repository publishes skills to ClawHub (clawhub.com) as the distribution registry. The following rules are non-negotiable:
Anti-Patterns to Avoid
Working with This RepositoryCreating New Skills: Follow the appropriate domain's roadmap and CLAUDE.md guide (see Navigation Map above). Editing Existing Skills: Maintain consistency across markdown files. Use the same voice, formatting, and structure patterns. Quality Standard: Each skill should save users 40%+ time while improving consistency/quality by 30%+. Additional Resources
Last Updated: March 11, 2026 |
|
REPLACING PREVIOUS TEST COMMENT - PR Review: 4 New Personas + README Rebrand. The 4 personas are high quality with a compelling voice and clear command structure. Key issues: (1) README badge updated 177->192 but only 4 files added - inflated count needs correction or documentation. (2) TEMPLATE.md not updated to reflect new opinionated-colleague format - future contributors will produce inconsistent personas. (3) Frontmatter skill references need validation (ceo-advisor is a persona not a skill; ms365-tenant-manager is an odd fit for DevOps; competitor-alternatives has no clear mapping). (4) PR checklist left entirely unchecked. (5) No license field in YAML frontmatter. Minor: devops-engineer.md has 4 bundled skills vs 8 for content-strategist; /finance:fundraise lacks a valuation tool reference; README and CLAUDE.md descriptions are out of sync on the library description. |
Commercial Distribution — Stan Store & GumroadProduct Bundles🚀 Indie Hacker Pack — $49
Includes 6 skills:
Value prop: "Ship your SaaS in days, not months. 6 skills that replace $1,200+ in boilerplate templates." 🏗️ Engineering Lead Pack — $49
Includes 6 skills:
Value prop: "Stop wasting hours on DevOps busywork. 6 skills that save 10+ hours per week." 💼 Agency & Freelancer Pack — $39
Includes 5 skills:
Value prop: "From proposal to handoff — everything you need to run a professional dev agency." 🤖 AI Builder Pack — $39
Includes 4 skills:
Value prop: "From prompt to production. 4 skills for serious AI engineering." 🎯 Complete Collection — $99
Everything above plus:
Value prop: "The most comprehensive Claude Code skill library available. 86 skills, 10K+ lines of production-ready expertise." Individual Skills — $9 eachAny single skill can be purchased individually on Gumroad. Free Tier (GitHub)All skills remain free and open source on GitHub. Paid bundles add:
Stan Store SetupProducts to Create
Delivery
Landing Page CopyHeadline: "86 Expert Skills for Claude Code — Ship Faster, Build Better" Subheadline: "Production-ready expertise bundles that turn Claude Code into a senior engineer, product manager, and business consultant. Used by 960+ developers." Social Proof:
Gumroad SetupProductsSame 5 bundles + 20 individual skills at $9 each. Tagsclaude-code, ai-skills, developer-tools, saas-boilerplate, claude-ai, mcp, prompt-engineering, ai-engineering Categories
|
|
test2 |
PR Review: 4 New Personas + README Rebrand |
|
PR Review: 4 New Personas + README Rebrand. This PR is already merged; feedback is for future reference. STRENGTHS: (1) Opinionated-colleague voice is more engaging than TEMPLATE.md - clean How-You-Think / What-You-Never-Do / When-to-Use-Me structure. (2) Commands well-scoped with clear one-sentence deliverables. (3) Routing yes/no sections set correct expectations. (4) Quantified success metrics are useful. ISSUES: (1) README badge 177->192 but only 4 files added - inflated by 11. Fix: revert to 177 or document the delta. CLAUDE.md still says 177. (2) TEMPLATE.md not updated for new opinionated format - future contributors will produce inconsistent personas. Fix: update TEMPLATE.md or document both patterns in README. (3) Frontmatter skill references need validation: ceo-advisor is a persona not a skill; ms365-tenant-manager is odd for DevOps; competitor-alternatives has no clear mapping. (4) PR checklist entirely unchecked - mark N/A where not applicable. (5) No license field in YAML frontmatter for any of the 4 files. MINOR: devops-engineer.md has 4 bundled skills vs 8 for content-strategist; finance:fundraise lacks a valuation tool reference; README and CLAUDE.md library descriptions are out of sync. SUMMARY: High quality personas with compelling voice. Main fixes: skill count (177 vs 192) and update TEMPLATE.md. |
|
PR Review: 4 New Personas + README Rebrand (already merged - for team reference) |
|
PR Review: 4 New Personas + README Rebrand (already merged - for team reference) What Works Well Opinionated voice (How-You-Think / What-You-Never-Do / When-to-Use-Me) is much more engaging than TEMPLATE.md. Command definitions are well-scoped (/finance:burn, /devops:incident, /pm:prd) with clear deliverables. Quantified success metrics ("20%+ MoM organic growth", "LTV:CAC above 3:1") give real signal. Issues to Address
Minor Observations devops-engineer.md has only 4 bundled skills vs 8 for content-strategist (could add ci-cd or observability). The /finance:fundraise command mentions "comparable valuations" but references no tool that provides this (cs-financial-analyst would fit). README now says "Agent Skills and Plugins" but CLAUDE.md says "comprehensive skills library for Claude AI" - keep these in sync. Summary The 4 personas are high quality with compelling voice and clear command structure. Main actionable fixes: correct the README skill count (177 vs 192) and update TEMPLATE.md so future contributors have a consistent reference. |
1 participant
Summary
Checklist
dev(notmain— PRs to main will be auto-closed)SKILL.mdwith valid YAML frontmatter (name,description,license)--helpwithout errorsdomain/skill-name/SKILL.md)Type of Change
Testing