argument-validator
This skill should be used when users want to validate or critique an argument by extracting premises, surfacing hidden assumptions, checking logical validity, optionally formalizing in Lean, and researching pre...
Découvrez les skills Outils, comparez leurs dépôts et consultez leurs instructions.
This skill should be used when users want to validate or critique an argument by extracting premises, surfacing hidden assumptions, checking logical validity, optionally formalizing in Lean, and researching pre...
Captures session learnings, decisions, and context to a markdown file for future agent ramp-up. Use when user says "ppage", "page context", "save context", "capture learnings", or before ending a substantial wo...
Fast file and code search using `fd` and `rg`. Use when the user asks to locate files or search code patterns.
Generate a GitHub Pull Request description. Creates structured, reviewer-centric PR descriptions with title, summary, why (before/after), implementation details, and impact. Use when user says "write PR descrip...
Interactive chunk-by-chunk review of PR or branch changes. Identifies logical groupings, explains each chunk, and critiques for issues. Use when user says "analyze-changes", "review changes", "review this PR",...
Multi-specialist collaborative analysis for complex decisions. Spawns parallel subagents with diverse domain expertise to analyze a topic from multiple angles. Use when user says "multi-mind", or for complex ar...
Deep line-by-line analysis of a function or method. Explains what each line does, why it's written that way, performance implications, edge cases, and design patterns. Use when user says "analyze-function", "an...
Simplifies code for clarity and maintainability while preserving exact behavior. Focuses on recently modified code. Use when user says "simplify", "simplify code", "make this simpler", "clean up", or "refactor...
Generate and execute code for acting with Python tools. Activate when user explicitly requests to "use the codeact skill" or similar phrases.
Use for deep requirements analysis, technical specifications, agile documentation, or architecture/design reviews.
Use to standardize project context (Rules) or automate complex multi-step tasks (Workflows).
Use when implementing frontend code, optimizing performance, or ensuring strict adherence to documentation/references.
Use when planning tests, creating test cases, reporting bugs, or executing Unit/E2E/Security/Performance tests.
React and Next.js performance optimization guidelines from Vercel Engineering. Sub-skill of frontend-developer. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, o...
Use when building UI, branding, design systems, or auditing accessibility/UX.
Use when designing APIs, Architecture, Security, or Scalability for Node, Python, Go, or Java backend systems.
Use when defining product vision, agile roadmapping, prioritization (RICE/Kano), or user-centric discovery.
Use when architecturalizing protocols, developing smart contracts, or auditing security for blockchain systems.
Use when creating new skills, updating existing skills, or packaging skills for distribution.
Use for high-stakes technical decisions, system design (Microservices/Monolith), cloud infrastructure, or generating ADRs/RFCs.
Use when building production-grade GenAI, Agentic Systems, Advanced RAG, or setting up rigorous Evaluation pipelines.
Use when designing Universal CI/CD, Multi-Cloud Infrastructure, or Observability systems.
Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements. Use this skill when users provide corrections, express preferences about code style, o...
Creates Python projects with proper structure, virtual environments, and dependency management. Use when users request to create a new Python project, set up a Python development environment, or initialize a Py...
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.