Automatically discover container and Docker skills when working with Docker. Activates for containers development tasks.

Use when distributing independent tasks across multiple AI coding assistants in parallel. Triggers include "fork this work", "spawn agents", "run in parallel", "distribute tasks", or when multiple...

Automatically discover observability and monitoring skills when working with monitoring. Activates for observability development tasks.

Automatically discover caching and performance skills when working with caching. Activates for caching development tasks.

Expert guidance on Swift Concurrency concepts. Use when working with async/await, Tasks, actors, MainActor, Sendable, isolation domains, or debugging concurrency compiler errors. Helps write safe...

Automatically discover mathematics and algorithm skills when working with mathematics. Activates for math development tasks.

Automatically discover debugging and profiling skills when working with debugging. Activates for debugging development tasks.

Use when user says "resume session", "what did I work on", or "find conversation about [topic]". Automatically searches, resumes, and analyzes Claude Code sessions. Handles session discovery,...

Agentic orchestration patterns for long-running tasks. Implements evidence-based delivery and Simon Willison's agent loop. Use when managing multi-step work, coordinating subagents, or...

Use when starting new feature work to create isolated git worktrees with smart directory selection and safety verification. Keeps main branch clean while developing.

Plan complex frontend work by analyzing requirements and creating executable task sequences. Use this skill when breaking down UI features, component architectures, or frontend integrations into...

Full autonomous execution from idea to working Android app

Generate improvement reports for skills or CLI packages you authored. Use when ending a session where you worked on your own skill, when the user mentions "skill-feedback", "capture improvements",...

Creates minimal working prototypes for quick idea validation. Single-file when possible, includes test data, ready to demo immediately. Use when user says "prototype", "MVP", "proof of concept",...

Manage Git worktrees for parallel Claude Code development. Use this skill when engineers ask to "create a worktree", "run parallel Claude sessions", "work on multiple features simultaneously", or...

This skill helps troubleshoot issues with codebase analysis - failed analyses, incorrect results, performance problems, and Gemini API errors. Use when analysis isn't working as expected.

Use when at major project milestones, before sharing/deploying, or when user says "review this", "check my work", "is this ready", or similar quality gate requests. Orchestrates specialized review...

Local-first backlog workflow. Use when planning work, creating/updating backlog items, writing ADRs, enforcing Ready gate, generating views, or maintaining derived indexes (SQLite/FTS/embeddings).

Use when working with error debugging multi agent review

Use when working with error debugging multi agent review