Claude Skills

Core principle that the main agent is a coordinator, not an implementer. All work must be delegated to subagents.

This skill should be used when the user asks about "output formatting", "concise responses", "Matt Pocock planning style", "scannable output", "action steps format", or needs guidance on communication and output formatting rules for Ralph agents.

Core Smart Ralph skill defining common arguments, execution modes, and shared behaviors across all Ralph plugins.

This skill should be used when the user asks to "build a feature", "create a spec", "start spec-driven development", "run research phase", "generate requirements", "create design", "plan tasks", "implement spec", "check spec status", or needs guidance on the spec-driven development workflow.

Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.

Use when you need direct browser control - teaches Chrome DevTools Protocol for controlling existing browser sessions, multi-tab management, form automation, and content extraction via use_browser MCP tool

Generate new Navigator slash commands following project conventions. Use when user says "add slash command", "create command", "new /nav command", or "add /nav:[name] command".

Show and toggle Navigator features. Auto-invoke when user says "show features", "enable/disable feature", "my navigator settings", or "configure navigator".

Generate frontend component tests (unit, snapshot, e2e). Auto-invoke when user says "test this component", "write component test", or "add component test".

Setup visual regression testing with Storybook stories, configuration, and CI/CD workflows. Supports Chromatic, Percy, BackstopJS. Auto-invoke when user says "set up visual regression", "add Chromatic tests", "add screenshot testing", or "set up Percy".

Query project knowledge graph. Search across tasks, SOPs, memories, and concepts. Use when user asks "what do we know about X?", "show everything related to X", or "remember this pattern/pitfall/decision".

Generate backend tests (unit, integration, mocks). Auto-invoke when user says "write test for", "add test", "test this", or "create test".

Validate and release Navigator plugin to marketplace. Auto-invoke when user says "release plugin", "publish navigator", "create release", or "deploy new version".

Install Navigator multi-Claude workflow orchestration scripts. Auto-invokes when user says "install multi-Claude workflows", "set up multi-Claude", or "enable parallel execution".

Create context save points to preserve conversation state before breaks, risky changes, or compaction. Use when user says "save my progress", "create checkpoint", "mark this point", or before clearing context.

Interactive onboarding for Navigator - learn by doing. Auto-invoke when user says "onboard me", "teach me Navigator", "how do I use Navigator", "Navigator tutorial", "learn Navigator", "new to Navigator", or "what skills should I use".

Manage memories - search, view, update, delete, rename projects

Configure Cortex settings with presets

Automatically diagnose and fix CI failures in the current PR

Remove AI-generated code slop from code changes in the current branch

Fetches AI news from smol.ai RSS and generates structured markdown with intelligent summarization and categorization. Optionally creates beautiful HTML webpages with Apple-style themes and shareable card images. Use when user asks about AI news, daily tech updates, or wants news organized by date or category.

Patterns for data loading, exploration, and statistical analysis

Enforces baseline comparisons, cross-validation, interpretation, and leakage prevention for ML pipelines

This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces.