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
817864 · page 18 / 62
phx:fullUse for large features spanning multiple contexts, new domain modules, or when the user wants autonomous end-to-end…majiayu000full-output-enforcementUse when a task requires exhaustive unabridged output, complete files, or strict prevention of placeholders and skipped code.majiayu000fuzzing-untrusted-inputsUse when fuzzing untrusted inputs is required during quality work, especially when the result must be traceable, independently…casioreview20-glitchgalaxy-query-rewriteUse this skill when you want an agent to review all benchmark queries and rewrite any that are:'majiayu000bio-gatk-variant-callingVariant calling with GATK HaplotypeCaller following best practices. Covers germline SNP/indel calling, GVCF workflow for cohorts…majiayu000geminiUse when the user asks to run Gemini CLI for code review, plan review, big context (>200k) processing or when the user explicitly…majiayu000gemini-blogConfigure or debug LLM blog post generation using Vercel AI SDK and Google Gemini. Use when updating blog generation prompts…majiayu000writesgemini-cliUse Google's Gemini CLI for web-grounded research (Google Search), automation via one-shot prompts, and second-opinion review.…majiayu000writesgemini-cliGoogle Gemini CLI orchestration (v0.22.0+) for AI-assisted development. Capabilities: second opinion/cross-validation, real-time…majiayu000gemini-cliGoogle Gemini CLI orchestration for AI-assisted development. Capabilities: second opinion/cross-validation, real-time web search…majiayu000writesgemini-peer-review🖥️ Claude Code Only - Requires terminal access to execute Gemini CLI commands.majiayu000geminiUse when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive…softaworksgenkitBuild production-ready AI workflows using Firebase Genkit. Use when creating flows, tool-calling agents, RAG pipelines…majiayu000genlayer-erc7710-connectorConnect GenLayer Intelligent Contract decisions to ERC-7710-style delegated authority. Use when an agent needs to design the…internet-courtget-review-theme从任意输入源提取结构化综述主题:支持文件(PDF/Word/Markdown/Tex)、文件夹、图片、自然语言描述、网页 URL 等;自动识别输入类型并提取内容;生成"主题+关键词+核心问题"结构化输出,可直接用于…majiayu000get-review-theme当用户明确要求"从文件/图片/网页/描述中提取综述主题"或"生成主题+关键词+核心问题结构化输出"时使用。支持文件(PDF/Word/Markdown/Tex)、文件夹、图片、自然语言描述、网页 URL…majiayu000git-pr-workflows-pr-enhanceYou are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews.…sickn33github-analysisAnalyze GitHub commits, generate PR reviews, calculate contributor leaderboards, and assess code quality. Use when analyzing git…majiayu000github-copilotAI-powered coding assistant providing inline suggestions, chat interface, code review, and autonomous coding agent across IDEs…majiayu000github-review-prReview GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the…feiskyergpt-researcherUse this skill for comprehensive research tasks requiring deep investigation, multiple source validation, and citation-backed…majiayu000granola-debug-bundleCreate diagnostic bundles for Granola support requests. Use when preparing support tickets, collecting system/audio/network info…jeremylongshorewritesgranola-performance-tuningOptimize Granola transcription accuracy, note quality, and processing speed. Use when improving transcription quality, reducing…jeremylongshorewritesgroq-common-errorsDiagnose and fix Groq common errors and exceptions. Use when encountering Groq errors, debugging failed requests, or…majiayu000groq-debug-bundleCollect Groq debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support…majiayu000Ground Truth ManagementComprehensive guide to creating, managing, and maintaining ground truth datasets for AI evaluation including annotation, quality…majiayu000retroWeekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and…majiayu000retroWeekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and…majiayu000harness-coderMain coding agent for autonomous harness system. Continues work from previous sessions, implements one feature per session…majiayu000monitoringMonitor Hawk job status, view logs, and diagnose issues. Use when the user wants to check job progress, view error logs, debug a…majiayu000heterogeneous-agentImplement or debug LobeHub heterogeneous agents. Use for Claude Code/Codex adapters, external CLI agents, event mapping, IPC…lobehubhlr-submissionUse when running the final pre-submission preflight for the Harvard Law Review (HLR) via HLR's own electronic submission system —…brycewang-stanfordhtml-ppt-hermes-cyber-terminalOpen Design + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a…nexu-iohtml-ppt-xhs-white-editorialA staff-engineer promotion packet — scope, the proof moments, the artifacts, and the impact that clears the bar. Built as a…nexu-iohummbl-frameworkComplete HUMMBL Base120 mental models framework with all 120 models across 6 transformations (Perspective, Inversion…majiayu000hybrid-searchUse when building search systems that need both semantic similarity and keyword matching - covers combining vector and BM25…majiayu000hyde-retrievalHyDE (Hypothetical Document Embeddings) for improved semantic retrieval. Use when queries don't match document vocabulary…majiayu000Icelandic Contract ReviewUse this skill when asked to review, analyze, or draft a contract governed by Icelandic law. Triggers on requests involving…lawve-aiicp-website-reviewEvaluate a website, landing page, content, or any online asset through the eyes of pre-built synthetic ICP personas. Loads…gooseworks-aiimage-generatorGenerate professional visuals using Gemini via browser automation with 6-gate quality control. Use when creating chapter…majiayu000image-generatorGenerate professional visuals using Gemini via browser automation with 6-gate quality control. Use when creating chapter…majiayu000implicit-decision-captureAutomatically capture implicit technical decisions and uncertainties encountered by AI agents during coding work. This skill logs…majiayu000improve-code-qualityGuided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a…wondelaiimprove-promptPrompt engineering architect that transforms raw prompts into optimized, production-ready prompts. PROACTIVELY activate for: (1)…majiayu000india-stock-analysisUse when user requests analysis of Indian stocks, fundamental assessment, technical review, comparisons, or investment reports…majiayu000intent-analyzerAdvanced intent interpretation system that analyzes user requests using cognitive science principles and extrapolates logical…majiayu000reasoning-trace-optimizerDebug and optimize AI agents by analyzing reasoning traces. Activates on 'debug agent', 'optimize prompt', 'analyze reasoning'…majiayu000interpret-feedbackInterpret third-party feedback by running parallel internal and peer interpretations to surface intent, correctness concerns, and…majiayu000
← Prev18 / 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