cancel-loop
Cancel the active Ralph implementation loop. Use when you want to stop the iterative process.
Browse published AI skills maintained by Z-M-Huang. Compare skill descriptions and follow each source repository for setup instructions.
Indexed skills
15Repository stars across indexed skills
196Repository forks
62Average repository stars per indexed skill
13Repository stars may repeat across skills from the same repository.
Cancel the active Ralph implementation loop. Use when you want to stop the iterative process.
Gather and clarify requirements before autonomous pipeline execution. Interactive phase for user input.
Deep code/plan review for architecture, subtle bugs, and test quality. Use after sonnet review for thorough analysis.
Start the multi-AI pipeline with TDD-driven ralph loop. Plan → Review → Implement (loop until tests pass + reviews approve).
Implement code using sonnet model with full main context access
Fast code/plan review for quality, security, and tests. Use for quick reviews before deeper analysis.
Final code/plan review using Codex. Use as the last review step after sonnet and opus.
Show memory system status and tracked projects. Use to check memory system health and list projects.
Repair common issues with the memory system. Cleans up orphan temp files, stale sessions, lock files, and old logs.
Two-phase cleanup - normalize long filenames, then consolidate semantic duplicates using AI
AI-powered validation of knowledge notes against current codebase. Detects stale content by comparing documented knowledge with actual files.
Fix issues detected by mem-audit. Supports dry-run mode to preview changes before applying them.
Search the Claude Code knowledge base for errors, solutions, decisions, and patterns. Use this to find information from your memory system.
Explicitly save knowledge, patterns, decisions, or learnings to the knowledge base. Use when you want to document something for future reference.
Scan the knowledge base for structural issues like broken links, orphan notes, missing indexes, and optionally AI-powered content staleness detection.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.