GitHub
learning-style
Learning-mode output style that mixes interactive coding with concise educational explanations. Use when the user asks for "learning mode", wants to co-write code, or requests a teaching/mentoring style: ask th...
Skills IA data ai debugging
Découvrez les skills data ai debugging, comparez leurs dépôts et consultez leurs instructions.
Catégories: data ai debugging
data ai debugging Effacer les filtres
Explorer
GitHub
caniuse-docs
Browser compatibility documentation for web features. Use when checking browser support, feature compatibility, CSS/JS/HTML feature availability, or answering "can I use" questions. Covers 569 web features and...
GitHub
bun-developer
Expert Bun runtime and toolkit guidance for JavaScript/TypeScript development. Use when writing Bun code, building servers with Bun.serve, running tests with bun test, using bun:sqlite, Bun Shell ($), file I/O...
GitHub
radare2
Reverse engineering binaries using radare2 (r2). Analyze executables, disassemble code, find functions, extract strings, patch binaries, debug programs, and explore firmware. Supports persistent sessions for la...
GitHub
claude-engineering-best-practices
General-purpose guidance for Claude Code (terminal) and Claude Dev (platform). Covers stable principles (progressive disclosure, hooks, security) and volatile details with lookup workflows.
GitHub
mcp-inspector
Test Model Context Protocol (MCP) servers using the MCP Inspector CLI
GitHub
refacter
Refacter code using complexity analysis and hotspot detection. Use when asked to refactor code, improve code quality, reduce complexity, or identify high-risk areas that need attention.
GitHub
investigating-a-codebase
Use when planning or designing features and need to understand current codebase state, find existing patterns, or verify assumptions about what exists - prevents hallucination by grounding plans in reality
GitHub
react-nextjs-validator
Use when reviewing React/Next.js code, choosing hooks, optimizing performance, or deciding between patterns. Use when you see useState overuse, missing memoization, prop drilling, useEffect misuse, or Next.js r...
GitHub
performance-analyzer
Automatically analyze performance issues when user mentions slow pages, performance problems, or optimization needs. Performs focused performance checks on specific code, queries, or components. Invoke when use...
GitHub
security-scanner
Automatically scan code for security vulnerabilities when user asks if code is secure or shows potentially unsafe code. Performs focused security checks on specific code, functions, or patterns. Invoke when use...
GitHub
browser-validator
Automatically validate implementations in real browsers after code is written or when user says "test this". Uses Chrome DevTools MCP to test responsive breakpoints (320px, 768px, 1024px), check accessibility c...
GitHub
coverage-analyzer
Automatically analyze test coverage when user asks which code is tested, mentions coverage gaps, or shows code asking about testing. Identifies untested code paths and suggests test additions. Invoke when user...
GitHub
test-scaffolding
Automatically generate test scaffolding when user writes new code without tests or mentions needing tests. Supports unit, integration, e2e, and data tests for PHP and JavaScript. Invoke when user mentions "test...
GitHub
fix-bug
Orchestrates disciplined bug fixing from diagnosis through verification. Infers severity and adapts approach - fast triage for critical bugs, scientific method for normal bugs. Prevents jumping to fixes and tra...
GitHub
oe-trace-and-fallback-triage
Debug and eliminate fallback/generic-stub replies quickly. Use when you see empty assistant replies, “Thanks for your message…” stubs, or “no specific information available” messages. Produces a minimal reprodu...
GitHub
oe-test-matrix-navigator
Maps a code change or bug symptom to the smallest high-signal test subset. Use when deciding what tests to run (DET_/FLOW_/REG_), when a regression guard mentions a test ID, or when you need a minimal repro tha...
GitHub
oe-backend-startup-triage
Debug “backend won’t start / first request 500 / ports stuck” quickly. Use when uvicorn reload behaves strangely, ports 8000/3000 are blocked, or you see first-request errors like “unexpected keyword argument”...
GitHub
oe-test-matrix-navigator
Maps a code change or bug symptom to the smallest high-signal test subset. Use when deciding what tests to run (DET_/FLOW_/REG_), when a regression guard mentions a test ID, or when you need a minimal repro tha...
GitHub
oe-trace-and-fallback-triage
Debug and eliminate fallback/generic-stub replies quickly. Use when you see empty assistant replies, “Thanks for your message…” stubs, or “no specific information available” messages. Produces a minimal reprodu...
GitHub
oe-backend-prod-hardening
Production hardening review for the OpenEvent backend. Use when scanning for LLM smells, noisy prints, swallowed exceptions, dev-only defaults, fallback diagnostic leakage, and inconsistent error/logging patter...
GitHub
oe-backend-startup-triage
Debug “backend won’t start / first request 500 / ports stuck” quickly. Use when uvicorn reload behaves strangely, ports 8000/3000 are blocked, or you see first-request errors like “unexpected keyword argument”...
GitHub
local-dev-evaluator
Evaluate local development experience for any stack. Use when user asks about local dev setup, docker-compose vs kubernetes, or developer experience for a technology stack.
GitHub
debug-like-expert
Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or wh...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.