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
769816 · page 17 / 62
embedding-strategiesSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing…majiayu000embedding-strategiesSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing…majiayu000embedding-strategiesSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing…majiayu000embedding-strategiesSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing…majiayu000embedding-strategiesSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing…majiayu000embedding-strategiesSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing…wshobsonenhancing-promptsAnalyze prompt quality, classify task type, and enhance with optimized templates while preserving original intent. Provides…majiayu000error-analysisSystematically identify and categorize failure modes in evaluated traces using Truesight datasets and error-analysis tools. Use…majiayu000Error MessagesExpert skill for designing and implementing high-quality compiler error messagesa5c-aiwriteseval-frameworksTraditional software metrics (accuracy, F1) fail to capture the quality of LLM outputs. Evaluation frameworks like Ragas and…majiayu000eval-frameworksTraditional software metrics (accuracy, F1) fail to capture the quality of LLM outputs. Evaluation frameworks like Ragas and…majiayu000eval-harnessEvaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality scoring.a5c-aiwritesevaluate-findingsCritically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using…majiayu000evaluate-traceEvaluate one or more traces against an existing Truesight live evaluation. Use when a deployed live evaluation already exists and…majiayu000evaluating-ai-qualityUse when evaluating ai quality is required during ai-products product work, especially when the result must be traceable…casioreview20-glitchevaluating-llmsEvaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating RAG…majiayu000evaluating-machine-learning-modelsEvaluate trained machine learning models with the right metrics and comparison logic. Use for benchmark review, threshold…majiayu000writesevaluating-new-technologyCreate a Technology Evaluation Pack (problem framing, options matrix, build vs buy, pilot plan, risk review, decision memo). Use…majiayu000evaluating-trade-offsHelp users make better decisions between competing options. Use when someone is weighing pros and cons, comparing alternatives…majiayu000evaluation-methodologyPluginEval quality methodology — dimensions, rubrics, statistical methods, and scoring formulas. Use this skill when…wshobsonevaluation-to-growthSystematic content evaluation framework progressing through Critique → Reinforcement → Risk Analysis → Growth. Use when reviewing…majiayu000evaluatorEvaluate TappsCodingAgents framework effectiveness and provide continuous improvement recommendations. Use for analyzing usage…majiayu000event-detection-temporal-intelligence-expertExpert in temporal event detection, spatio-temporal clustering (ST-DBSCAN), and photo context understanding. Use for detecting…majiayu000writesevidence-gradingGrade the quality and strength of veterinary evidence using a veterinary-specific evidence hierarchy. Textbooks carry more weight…majiayu000evo-retrospectivePost-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic…majiayu000evolution-reporterGenerate comprehensive ecosystem progress reports showing skills built, efficiency gains, quality metrics, learnings captured…majiayu000writesexa-searchWeb toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or…majiayu000executing-plansUse when you have a written implementation plan to execute in a separate session with review checkpoints between batches.a5c-aiexploration-debugInteractive debugging through conversation. HOUSTON guides through 4 phases, asks questions, and suggests agents for…majiayu000external-tool-coordinationCoordinate external AI tool integration (OpenAI Codex, Google Gemini) for cross-model adversarial review and delegated…a5c-aiwritesfal-model-guide| Category | Fast/Cheap | Balanced | Best Quality |majiayu000FastMCP DevelopmentUse when creating or modifying Model Context Protocol (MCP) servers with FastMCP framework - guides through tools, resources…majiayu000fastmcpFastMCP TypeScript framework patterns for MCP servers. Auto-loads when building MCP servers, creating tools/resources/prompts…majiayu000fastq-analysis-pipelineGuide through omicverse's alignment module for SRA downloading, FASTQ quality control, STAR alignment, gene quantification, and…FreedomIntelligencebio-fastq-qualityWork with FASTQ quality scores using Biopython. Use when analyzing read quality, filtering by quality, trimming low-quality…majiayu000bio-fastq-qualityWork with FASTQ quality scores using Biopython. Use when analyzing read quality, filtering by quality, trimming low-quality…majiayu000feature-flagsGenerate feature flag infrastructure with local defaults, remote configuration, SwiftUI integration, and debug menu. Use when…rshankraswritesfeedback-reviewAggregate feedback signals across all active loops. Reports health, trajectory, overdue checks, regression warnings, and…majiayu000feedback-reviewAggregate feedback signals across all active loops. Reports health, trajectory, overdue checks, regression warnings, and…majiayu000fetch-pr-commentsFetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR…majiayu000fetch-pr-commentsFetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR…majiayu000fetch-pr-feedbackFetch unresolved review comments from a PR and evaluate with receive-feedback skillmajiayu000finance-reportQuarterly / monthly financial report — masthead with KPIs, revenue and burn charts, P&L summary table, top-line highlights, and…nexu-ioform-filler-operatorFill long web forms and applications through a computer-use agent — from a fact sheet you approve, field by field, with a full…mohitagw15856fpf-reviewArchitecture review using FPF (Functional Programming Framework) methodology. Evaluates codebases through functional, practical…majiayu000fpf-reviewArchitecture review using FPF (Functional Programming Framework) methodology. Evaluates codebases through functional, practical…majiayu000fpga-debuggingOn-chip debugging skill with ILA, VIO, and related FPGA debug toolsa5c-aiwritesfreerideManages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit…majiayu000
← Prev17 / 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