Loading...
Loading...
Found 7,955 Skills
Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.
6-phase PPTX presentation generation with visual QA: Gather, Design, Generate, Convert, QA, Output. Use when user needs a PowerPoint deck, slide presentation, pitch deck, or conference talk slides. Triggers: "create a presentation", "make slides", "pitch deck", "powerpoint", "pptx", "slide deck", "generate presentation". Do NOT use for Google Slides, Keynote, or PDF-only documents.
Evidence-based 4-phase root cause analysis: Reproduce, Isolate, Identify, Verify. Use when user reports a bug, tests are failing, code introduced regressions, or production issues need investigation. Use for "debug", "fix bug", "why is this failing", "root cause", or "tests broken". Do NOT use for feature requests, refactoring, or performance optimization without a specific bug symptom.
Design exploration with parallel agents. Use when brainstorming ideas, exploring solutions, or comparing alternatives.
Decompose technical design into agent-sized implementation issues → numbered markdown files. Triggers: 'plan this,' 'break into issues,' 'create tasks,' 'ready to implement,' post-architect. Not for: designs without file paths/phases (run architect first).
NotebookLM integration patterns for external RAG, research synthesis, studio content generation (audio, cinematic video, slides, infographics, mind maps), and knowledge management. Use when creating notebooks, adding sources, generating audio/video, or querying NotebookLM via MCP.
UPDATE-DOCS phase. Refresh README.md, CLAUDE.md, and docs/index.html to reflect changes made this session. Commits and pushes doc updates. Terminal phase — declares COMPLETE.
Agent skill for swarm - invoke with $agent-swarm
Pick and work on the next task from TASKS.md. Use when the user says "next task", "work on the next thing", "what should I work on", or wants to start an autonomous coding loop.
Use when reviewing pending todos for approval, prioritizing code review findings, or interactively categorizing work items
Use when batch-resolving approved todos, especially after code review or triage sessions
Resolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing code review feedback.