Skill Reference
Think of skills as reference manuals that Claude Code can read mid-conversation. When you're writing Rails code and want DHH's style, or building a gem like Andrew Kane would, you don't need to paste documentation—just invoke the skill. Claude reads it, absorbs the patterns, and writes code that way.
How to Use Skills
# In your prompt, reference the skill
skill: [skill-name]
# Examples
skill: gemini-imagegen
skill: dhh-rails-style
skill: create-agent-skillsSkills vs Agents
Agents are personas—they do things. Skills are knowledge—they teach Claude how to do things. Use claude agent [name] when you want someone to review your code. Use skill: [name] when you want to write code in a particular style yourself.
Skills (7)
wf-delivery
Workflow policy for CI repair, release preparation, pull requests, merge gates, artifact transfer, deployment handoff, and release communication. Use when work is implemented and must be shipped. This skill owns delivery sequencing; repository commands and credentials come from repository capability targets.
skill: wf-deliverywf-development
Workflow policy for implementing planned engineering changes, diagnosing root causes, fixing reproduced bugs, refactoring, and building APIs, interfaces, or agent-native systems. Use when code or configuration must change after grooming, including end-to-end implementation orchestration. This skill owns development sequencing and handoffs; repository mechanics come from repository capability targets.
skill: wf-developmentwf-documentation
Workflow policy for creating, reviewing, repairing, compounding, and shipping documentation. Use when documentation is the primary deliverable or when engineering work must leave durable knowledge before delivery completes. Repository locations, tooling, and publication steps come from repository capability targets.
skill: wf-documentationwf-grooming
Workflow policy for turning ideas, requests, bug reports, and un-groomed work into an actionable plan. Use first for requirements discovery, brainstorming, triage, bug reproduction, issue decomposition, grooming, or planning. This skill owns the ready-for-development boundary and never invents repository-specific commands.
skill: wf-groomingwf-review
Workflow policy for reviewing code, architecture, security, plans, documents, and pull-request feedback. Use when evaluating a proposed or implemented change and deciding whether findings block progress. This skill owns review gates and triage; repository conventions come from repository capability targets.
skill: wf-reviewwf-setup
Workflow policy for adopting and configuring agentic-engineering in a repository. Use for first-time setup, repository-contract creation or repair, lifecycle bootstrap, configuration flags, hook installation, and readiness diagnostics. This skill owns setup completion; repository-specific values still come from repository evidence or explicit user input.
skill: wf-setupwf-testing
Workflow policy for test strategy, test-first development, regression coverage, browser or device testing, and verify-before-done evidence. Use when deciding what to test, executing validation, or proving a change works. Repository commands and environments must come from repository capability targets.
skill: wf-testingmarketing Plugin Skills (1)
seo-audit
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit.
skill: marketing:seo-audit