Loading...
Loading...
Found 346 Skills
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Only to be triggered by explicit /parallel-task commands.
Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements. Use when asked to "analyze workflow logs", "review action runs", or "analyze GitHub Actions".
Use when the response requires complex reasoning, creativity, nuance, evaluation, decision-making, subjectivity, or communication-sensitive work. If the task is simple and the user has not manually invoked this skill, do not use it.
Use when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery.
Verify iOS app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.
Analyze, describe, read, or extract content from any screenshot, image, photo, picture, pic, snap, screen grab, or screen capture the user shares. Triggers when users ask about images ("what's in this", "what can you see", "what does this show", "what am I looking at", "tell me about this", "can you read this"), request review ("check this", "look at this", "review these", "analyze this"), request extraction ("extract text", "convert to markdown", "transcribe this", "parse this", "pull the data"), or describe attachments ("here's a screenshot", "I pasted this", "see attached"). Works with single or multiple images. Converts UI data into clean, structured markdown.
[Fix & Debug] ⚡⚡ Analyze and fix UI issues
Explain how something works in this codebase by exploring code and producing a clear architectural explanation. Optionally critique the architecture for issues.
Execute all plans in a phase with wave-based parallelization, running phase execution, or completing phase work. Triggers include "execute phase", "run phase", "execute plans", "run the phase", and "phase execution".
[Implementation] ⚡ No research. Only scout, plan & implement ["trust me bro"]
Cheat sheet + workflow for launching interactive coding-agent CLIs (Claude Code, Gemini CLI, Codex CLI, Cursor CLI, and pi itself) via the interactive_shell overlay or headless dispatch. Use for TUI agents and long-running processes that need supervision, fire-and-forget delegation, or headless background execution. Regular bash commands should use the bash tool instead.