aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Open the SAGA dashboard in your browser
List all running SAGA sessions
CLI user experience best practices for error messages, colors, progress indicators, and output formatting. Use when improving CLI usability and user experience.
Git troubleshooting techniques including recovering lost commits, fixing merge conflicts, resolving detached HEAD, and diagnosing repository issues. Use when user encounters git errors or needs to recover from mistakes.
Common Clap patterns and idioms for argument parsing, validation, and CLI design. Use when implementing CLI arguments with Clap v4+.
Rack middleware development, configuration, and integration patterns. Use when working with middleware stacks or creating custom middleware.
Distribution and packaging patterns including shell completions, man pages, cross-compilation, and release automation. Use when preparing CLI tools for distribution.
Performance optimization techniques for GPUI including rendering optimization, layout performance, memory management, and profiling strategies. Use when user needs to optimize GPUI application performance or debug performance issues.
GPUI styling system including theme design, responsive layouts, visual design patterns, and style composition. Use when user needs help with styling, theming, or visual design in GPUI.
Updates the .claude-plugin/marketplace.json file when plugins are added, modified, or removed. Use when creating or updating plugin entries in the marketplace catalog.
Advanced concurrency patterns with goroutines, channels, context, and synchronization primitives. Use when working with concurrent Go code, implementing parallel processing, or debugging race conditions.
Modern Go patterns, idioms, and best practices from Go 1.18+. Use when user needs guidance on idiomatic Go code, design patterns, or modern Go features like generics and workspaces.
Adds a new law to the CLAUDE.md constitution. Use when establishing new immutable constraints that must be enforced in every response.
Documents architecture WITHOUT implementation. Creates ADR and component docs with status: provisioned. MUST use this skill when user wants to DESIGN or PLAN without implementing: - "provision X", "provision a component", "provision new service" - "design the architecture for X", "design a component" - "plan X", "plan a new service", "plan the architecture" - "document X architecture", "architect X" - "envision X", "sketch X architecture" DO NOT use this skill if prompt contains: - "pattern", "patterns" → route to c3-ref - "ref", "refs" → route to c3-ref - "convention", "standard" → route to c3-ref Key indicator: User wants documentation/design output, NOT code changes. Requires .c3/ to exist. Creates ADR with status: provisioned. For implementation requests, route to c3-alter.
Routes C3 architecture requests and audits existing C3 documentation for consistency. Use when the user asks to "audit architecture", "validate C3", "check C3 docs", "verify docs", "check documentation", "are docs up to date", or when no .c3/ directory exists (routes to onboarding). Routes navigation to c3-query, changes to c3-alter, patterns to c3-ref, design to c3-provision.
Investigate suspected bugs with git archaeology and root cause analysis. Triggers: "bug", "broken", "doesn''t work", "failing", "investigate bug".
Use when: "document", "docs", "README", "API docs", "OpenAPI", "Swagger", "Diátaxis", "tutorial", "how-to", "reference", "explanation", "SDK", "developer docs", "knowledge OS", "7-pattern stack".
Investigate suspected bugs with git archaeology and root cause analysis. Triggers: "bug", "broken", "doesn't work", "failing", "investigate bug".
Fully autonomous epic execution. Runs until ALL children are CLOSED. Loops through beads issues, runs /implement on each, validates with /vibe. NO human prompts, NO stopping.
Execute testing workflows including unit tests, manifest validation, security scanning, and integration tests with proper reporting