80,000+ Skills to Supercharge Claude
The open directory for GitHub-integrated capabilities, tools, and prompts for your AI workflows.
iterative-analysis
by meglinge
Performs sequential multi-round oracle analysis where each round builds on previous findings. Use when user specifies an...
conventions-vue
by caiokf
Apply when working with Vue components, composables, stores, or styling. Ensures code matches established project patter...
writing-skills
by caiokf
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to proce...
gob-background-jobs
by caiokf
Use when user requests "parallel" commands, running multiple builds/tests simultaneously, or long-running tasks. Use `go...
coderabbit-fix
by caiokf
Implement fixes for specific CodeRabbit review issues. Runs in isolated subagent context with focused task. Verifies fix...
coderabbit-triage
by caiokf
Analyze code review findings and create execution plan. Decides parallel vs sequential fixing based on issue severity an...
finishing-work
by caiokf
Use when completing work on a task or feature. Prompts for code review before finishing. ALWAYS invoke this skill before...
coderabbit-request
by caiokf
Use after completing file changes - strongest for source code (AST-aware linting, security, tests), lighter support for...
conventions-css
by caiokf
Apply when writing styles. Ensures consistency with design system and project patterns.
generating-commit-message...
by FoundDream
Generates clear commit messages from git diffs. Use when writing commit messages or reviewing staged changes.
Create and modify Lua plugins for Open Brush with full API documentation access. Use when the user wants to create Open...
critique-agent
by awaaate
Specialized agent for code review, debugging critique, and quality assessment
agent-orchestrator
by awaaate
Orchestrator agent for coordinating multiple AI agents in a persistent system
multi-agent-patterns
by awaaate
Common patterns and best practices for multi-agent coordination
memory-manager
by awaaate
Advanced memory management techniques for the OpenCode memory system
hunt-optimization
by blt
Systematic optimization hunter. Finds memory optimizations AND bugs - both are valuable. Run /validate-correctness when...
review-optimization
by blt
Reviews memory optimization patches using a 5-persona peer review system. Requires unanimous approval backed by benchmar...
validate-correctness
by blt
Validates discovered bugs with reproducing tests and validates fixes with regression tests. Called by other skills when...
preflight
by blt
Environment validation checklist. Run this FIRST when starting a new Claude session to verify the environment is ready f...
rescue-optimization
by blt
Salvages optimization work lacking benchmarks. Generates missing evidence, validates claims. Bugs discovered during resc...
mongoose
by nicklaunches
Mongoose ODM for MongoDB and Node.js. Use for schemas, models, queries, validation, middleware, population, aggregation,...
skill-creator
by ceshine
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an exist...
using-skills
by ceshine
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY...
git-workflow
by ceshine
Always invoke this skill for any git-related request (commit messages, staging review, history, PR descriptions, etc.) s...