benchmark-report-creator
Use PROACTIVELY when creating research reports, experiment writeups, technical whitepapers, or empirical study documentation. Orchestrates the complete benchmark report pipeline with structure, diagrams, hi-res...
Découvrez les skills Recherche, comparez leurs dépôts et consultez leurs instructions.
Use PROACTIVELY when creating research reports, experiment writeups, technical whitepapers, or empirical study documentation. Orchestrates the complete benchmark report pipeline with structure, diagrams, hi-res...
Reviews code for bugs, security issues, and quality improvements. Use when reviewing pull requests, checking code quality, or when asked to review changes.
Extract Intent Layer content from git history. Analyzes commits, PRs, and blame to discover pitfalls, contracts, architecture decisions, and entry points that should be documented in AGENTS.md files.
Four-phase debugging framework with root cause tracing - understand the source before proposing fixes. Use when investigating bugs, errors, unexpected behavior, or failed tests.
Evidence-driven debugging for project or system issues: reproduce the bug, capture commands/logs/stack traces, narrow scope, prove root cause with concrete evidence (no guessing), apply minimal fix, and re-run...
Write JavaScript code with deep understanding of the language fundamentals as envisioned by Brendan Eich, creator of JavaScript. Emphasizes first-class functions, prototypes, and the dynamic nature of the langu...
Write Python code in the style of David Beazley, author of Python Cookbook. Emphasizes generators, coroutines, metaprogramming, and understanding Python's internals. Use when writing advanced Python that requir...
Use PROACTIVELY when user asks for accessibility review, a11y audit, WCAG compliance check, screen reader testing, keyboard navigation validation, or color contrast analysis. Audits React/TypeScript application...
Write JavaScript code in the style of Kyle Simpson, author of "You Don't Know JS". Emphasizes deep understanding of JavaScript mechanics—scope, closures, this, prototypes, and async. Use when you need to truly...
Use PROACTIVELY when searching past Claude Code conversations, analyzing development patterns, or generating activity reports. Automatically processes conversation history from the project, enables RAG-powered...
Performance bottleneck analysis, workflow inefficiency detection, pattern recognition, and optimization recommendations. Use for identifying performance issues, root cause analysis, and generating actionable im...
Comprehensive code performance optimization workflow covering profiling, bottleneck analysis, and optimization patterns for frontend, backend, database, and algorithm layers.
AST-based structural code search, security scanning, and refactoring using ast-grep (sg CLI). Supports 40+ languages with pattern matching and code transformation.
AST-based code transformation skill using ast-grep. Structural code search and automated migration patterns for legacy code conversion.
Comprehensive codebase architecture mapping with AST analysis and dependency visualization
Identifies and fixes performance bottlenecks. Use when optimizing code performance, fixing slow operations, or when asked to improve speed.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Trigge...
Stage meaningful diffs and create commits with WHY-focused messages. Use when agent needs to commit code changes.
Fast compliance fixes for design tokens, imports, and common violations
Guide API routes with Validate→Queue→Respond pattern and Inngest integration
CodeQL suppressions, security vulnerability troubleshooting, and security best practices
Testing patterns, 99% pass rate target, strategic skips, and E2E workflows
Enforce DCYFR design token patterns and fix hardcoded values
Pre-completion validation checklists and approval gates
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.