en un clic
my-ai-tools
my-ai-tools contient 42 skills collectées depuis jellydn, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Verify understanding after implementation with targeted quizzes
Clarify requirements through targeted questions — uncovers unknown unknowns in specs
Remove AI-generated code patterns that don't match codebase style
Review code for quality, security, and best practices — read-only analysis
Create clear documentation for code and APIs
Audit code for security vulnerabilities — read-only analysis
Generate comprehensive tests for code changes
Remove AI-generated code patterns that don't match codebase style
Review code for quality, security, and best practices — read-only analysis
Create clear documentation for code and APIs
Audit code for security vulnerabilities — read-only analysis
Generate comprehensive tests for code changes
Remove AI-generated code patterns that don't match codebase style
Review code for quality, security, and best practices — read-only analysis
Create clear documentation for code and APIs
Audit code for security vulnerabilities — read-only analysis
Generate comprehensive tests for code changes
Find unknown unknowns before starting implementation — searches git history, patterns, and architecture for hidden gotchas
Experiment with model capabilities — HTML reports, embedded questionnaires, proactive research, multi-step reasoning
Map codebase structure with parallel analysis — produces 7 documents about architecture, concerns, and conventions
Discover context using MCP tools — fff, sem, ctx, qmd, codebase-memory-mcp for codebase understanding
Search project documentation — ADRs, wiki entries, conventions via ripgrep, qmd, fff, and ctx
Search git history for context — commit messages, blame, related changes, impact analysis
Create handoff plans for continuing work across sessions
Log implementation decisions — tracks deviations from plan and captures rationale
Resume work from previous handoff sessions stored in .planning/handoffs/
Turn ideas into executable goal packages with guided interviews and codebase analysis
Replace port numbers with stable named .localhost URLs for local development
Manage project knowledge with qmd — captures learnings, decisions, and conventions
Remove AI-generated code slop from git diffs to maintain code quality
Run an extremely strict maintainability and structural code quality review — flags abstraction issues, spaghetti growth, and boundary leaks
Review the diff since a fixed point along two axes — Conventions (does the code follow this repo's coding standards and Tidy First practices?) and Intent (does the change do what it claims to do?). Runs both reviews in parallel sub-agents and reports them side by side. Use when you want to review a branch, a PR, work-in-progress changes, or ask to "review since X".
Update docs when code changes — reviews commits and syncs user-facing documentation
Draft pull requests with structured descriptions using gh CLI
Convert PRDs to prd.json format for the Ralph autonomous agent system
Record architecture decisions with ADRs — captures why, alternatives considered, and consequences
Group staged changes into atomic commits with commitizen convention
Build a persistent compounding wiki from raw sources using the LLM Wiki pattern
Fix PR review comments by implementing requested changes
Generate Product Requirements Documents from feature ideas — plans specs and requirements