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
865912 · page 19 / 62
interview-cheatsheetGenerate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch…majiayu000writesinterview-cheatsheetGenerate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch…majiayu000writesintrospectAnalyze Claude Code session logs - extract thinking blocks, tool usage stats, error patterns, debug trajectories. Triggers on…majiayu000writesInvestigation PatternsThis skill should be used when the user asks to "investigate code", "analyze implementation", "find patterns", "understand…majiayu000invoice-review-complianceInvoice review, non-compliance flagging, rejection communication, billing trend analysis, and conversation preparation for…lawve-aiios-debugger-agentDebug the current iOS project on a booted simulator with XcodeBuildMCP.sickn33javascript-testing-patternsComprehensive guide for implementing robust testing strategies in JavaScript/TypeScript applications using modern testing…sickn33joe-submissionUse when running the final pre-submission preflight for the Journal of Econometrics (JoE) — live portal routing, the USD $75 fee…brycewang-stanfordjournal-reviewDraft a senior peer-review report on a social-science manuscript.majiayu000jtag-swd-debugDeep integration with JTAG/SWD debug probes for hardware-level debugging and flash programminga5c-aiwritesjulesDelegate coding tasks to Google Jules AI agent for asynchronous execution. Use when user says: 'have Jules fix', 'delegate to…majiayu000kanban-boardTo do / In progress / In review / Done 四列, 卡片 + 头像 + 泳道nexu-iokanban-boardKanban / task board with columns (To do / In progress / In review / Done), draggable-looking cards, assignee avatars, swimlanes…nexu-iokata-set-profileSwitch model profile for kata agents (quality/balanced/budget). Triggers include "set profile", "set profile".majiayu000writeskill-argumentTwo-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer…majiayu000writeskiro-debugInvestigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or…gotalabkiro-reviewReview a task implementation against approved specs, task boundaries, and verification evidence. Use after an implementer…gotalabkling-kolors-imagePlan, generate, edit, reference, and quality-control still images with Kling AI's hosted IMAGE surfaces or Kuaishou's open Kolors…calesthiolangchain-common-errorsDiagnose and fix common LangChain errors and exceptions. Use when encountering LangChain errors, debugging failures, or…majiayu000writeslangchain-debug-bundleCollect LangChain debug evidence for troubleshooting and support. Use when preparing bug reports, collecting traces, or gathering…majiayu000writeslangchain-dependenciesINVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for…majiayu000langchainLangChain workflows for `create_agent`, LCEL chains, `bind_tools`, middleware, and structured output with production-safe…majiayu000langchainjsLangChain.js - TypeScript framework for building LLM-powered applications with agents, chains, RAG, tools, memory, and…majiayu000langflowA powerful Python-based visual framework for building and deploying AI-powered agents and workflows with Model Context Protocol…majiayu000langflowA powerful Python-based visual framework for building and deploying AI-powered agents and workflows with Model Context Protocol…majiayu000langfuseDebug AI traces, find exceptions, analyze sessions, and manage prompts via Langfuse MCP. Use when debugging AI pipelines…majiayu000langfuse-debug-bundleCollect Langfuse debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing…majiayu000langfuseExpert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and…majiayu000langgraph-code-reviewReviews LangGraph code for bugs, anti-patterns, and improvements. Use when reviewing code that uses StateGraph, nodes, edges…majiayu000langgraph-human-in-loopLangGraph human-in-the-loop patterns. Use when implementing approval workflows, manual review gates, user feedback integration…majiayu000langgraph-streaming从 LangGraph 流式传输实时更新:流式模式(values、updates、messages、custom、debug)用于响应式 UXmajiayu000langsmith-fetchDebug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior…majiayu000langsmith-fetchDebug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior…majiayu000latent-space-engineeringShapes agent behavior via instruction framing and style transfer. Use when composing dispatch prompts or writing skill…majiayu000launch-positioning-builderResearch competitors, analyze their messaging, and generate a positioning document with category definition, differentiation…gooseworks-ailaw-expertise-to-skill-ignacio-adrian-lererTurn a lawyer's bounded expertise, workflow, review standard, or legal judgment pattern into a safe, inspectable legal AI skill.…lawve-ailead-projectAutonomous technical lead. Takes commander's intent and drives a project to completion through an OODA loop over implementation…majiayu000learnable-pattern-searchAnalyze review comments from brave-core PRs to discover learnable patterns for improving bot documentation and best practices.…majiayu000learning-curatorSummarize PR review comments and CI failure logs into structured fix patterns (JSON output) for the learning store. Use when…majiayu000learning-literature-reviewliterature-review for evidence-based learning research and evaluation.majiayu000libanalysislibanalysis - Code analysis and formatting utilities. formatForAnalysis function prepares markdown documents with Prettier…majiayu000libevallibeval - RAG evaluation system. Evaluator orchestrates quality assessment using LLM-as-judge patterns. CriteriaEvaluator scores…majiayu000lindy-debug-bundleComprehensive debugging toolkit for Lindy AI agents. Use when investigating complex agent failures, collecting diagnostics, or…jeremylongshorewritesLiquid ArchitectureLiquid Architecture enables the AI system to modify and optimize its own codebase in real-time without human intervention. This…majiayu000lisa-review-implementationThis skill should be used when comparing a project's Lisa-managed files against Lisa's source templates to identify drift. It…majiayu000lisa-review-projectThis skill should be used when comparing Lisa's source templates against a target project's implementation to identify drift. It…majiayu000list-membersDisplays the roster of architecture team members with their specialties and expertise areas. Use when the user asks "Who's on the…majiayu000lit-pmUse when coordinating comprehensive literature reviews requiring multi-stage pipeline (archival setup, scope refinement, parallel…majiayu000
← Prev19 / 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