Agent skills

Code Review & Quality skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
2,936 found
1,0571,104 · page 23 / 62
product-ad-productionDiagnose, design, script, produce, adapt, and quality-control product video advertisements from evidence-backed briefs. Use for…calesthioproduct-review-analysisAnalyze product reviews across any e-commerce platform. Extract actionable insights from customer feedback including pain points…majiayu000programmatic-seo-spyReverse-engineer how competitors do programmatic SEO. Detects URL pattern clusters (vs/, integrations/, for-{industry}/)…gooseworks-aiprompt-builderGuide users through creating high-quality GitHub Copilot prompts with proper structure, tools, and best practices.majiayu000prompt-engineer-toolkitAnalyzes and rewrites prompts for better AI output, creates reusable prompt templates for marketing use cases (ad copy, email…majiayu000prompt-engineeringEngineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques. Use when building…majiayu000prompt-engineeringExpert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts…majiayu000prompt-engineeringProvides workflows to write, debug, and optimize prompts for LLMs, including few-shot example selection, chain-of-thought…majiayu000writesprompt-engineeringCrafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or…majiayu000prompt-engineeringDesign and optimize prompts for large language models (LLMs) to achieve reliable, high-quality outputs across diverse tasks.majiayu000prompt-engineeringExpert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts…majiayu000prompt-enhancerPrompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure…majiayu000prompt-generatorGenerate or convert Claude Code prompt files — command orchestrators, skill files, agent role definitions, or style conversion of…majiayu000writesprompt-improvementMeta-skill for improving and optimizing prompts using Anthropic's prompt engineering best practices. Provides the 4-step…majiayu000writesprompt-improverOptimize prompts for code-related tasks following Claude best practices. Use when refining prompts for implementation, debugging…majiayu000prompt-libraryCurated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and…majiayu000prompt-optimizationImprove and rewrite user prompts to reduce ambiguity and improve LLM output quality. Use when a user asks to optimize, refine…majiayu000prompt-optimizeExpert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts…majiayu000prompt-optimizerThis skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models.…majiayu000prompt-review.github/prompts/*.prompt.md をレビューして改善提案を出す。frontmatterの妥当性、入力変数(${input:...})の設計、出力フォーマット固定、instructions/skillsへの参照(重複排除)、tools最小化…majiayu000prompt-reviewReviews a prompt/instruction file against Anthropic prompt engineering best practices. Use when evaluating skill files, agent…majiayu000prompt-senseiStage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt…majiayu000prompt-template-builderCreates reusable prompt templates with strict output contracts, style rules, few-shot examples, and do/don't guidelines. Provides…majiayu000pubar-submissionUse when running the final pre-submission preflight for Public Administration Review (PAR) — article-type selection, double-blind…brycewang-stanfordpy-debug-botExecute BioETL py-debug-bot profile for role-specific workflow and constraints.majiayu000pydantic-ai-agentsBuild and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output…majiayu000pydantic-ai-common-pitfallsAvoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing…majiayu000quality-hooksLanguage-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go…a5c-aiwritesquantization-evaluation-pipelineExecute GGUF quantization with imatrix protection, perform statistical benchmark evaluation with error bars, generate…majiayu000query-sub-agent專責處理 IDF (Information Display Frame) 類型的需求。讀取規格目錄結構,生成/審查 Query Side 設計與實作。支援 Java、TypeScript、Go 多語言。majiayu000quic-channel-gradingQUIC channel quality grading with BBRv3 congestion control analysis. Classifies network paths into GF(3) tiers based on RTT…majiayu000quiz-generatorGenerate educational quizzes from topics, learning goals, or provided documents. Supports multiple question types, difficulty…mingchen666rag-accuracy-skillMeasure RAG answer quality through three core metrics: Faithfulness (accuracy to context), Relevance (retrieval quality), and…majiayu000rag-and-vector-searchUse when building RAG systems, implementing semantic/hybrid search, selecting vector databases, tuning retrieval quality, or…majiayu000rag-architectureRetrieval-Augmented Generation (RAG) system design patterns, chunking strategies, embedding models, retrieval techniques, and…majiayu000RAG EvaluationComprehensive guide to evaluating Retrieval-Augmented Generation systems including retrieval metrics, generation quality…majiayu000rag-qualityRAG 시스템 품질 평가 및 개선을 위한 스킬입니다. RAGAS 기반 LLM-as-Judge 평가, 사용자 페르소나 시뮬레이션, 합성 데이터 생성, 평가 결과 저장 및 분석 기능을 제공합니다.majiayu000writesrag-rerankingCross-encoder reranking and MMR diversity filtering for improved retrieval qualitya5c-aiwritesrag-rerankingCross-encoder reranking and MMR diversity filtering for improved retrieval qualitymajiayu000writesralph-calibrateRun Ralph calibration checks to analyze intention drift, technical quality, and self-improvement opportunities. Use when user…majiayu000ralphCreate and run Ralph loops for structured AI-driven development. Triggered by "create a ralph loop for X" or "ralph plan for X".…majiayu000ralph-executeAutonomous execution loop that processes a Beads epic task-by-task with fresh subagents, two-stage review, and circuit breaker…majiayu000ralph-executeAutonomously implement user stories from the PRD, running quality gates and committing after each successful story. Maintains…majiayu000ralph-loopUse after first code change. Autonomous iteration until all quality gates pass (max 7 iterations).majiayu000ralph-loopRalph Wiggum-inspired automation loop for specification-driven development. Orchestrates task implementation, review, cleanup…majiayu000writesralph-prompt-generatorUse when a user has a rough prompt that needs a staged prompt-improvement workflow for `$ralph-wiggum-codex`, with saved…majiayu000ralphExecute iterative development loop through user stories. Implements one story at a time with quality gates, commits, and learning…majiayu000writesralph-wiggum-codexUse when a coding task needs an objective-first long-running loop with fresh-context work and review phases, explicit acceptance…majiayu000
← Prev23 / 62Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going