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
1,2011,248 · page 26 / 62
self-improverReview affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to improve…Affitorsemantic-kernelCreate, update, refactor, explain, or review Semantic Kernel solutions using shared guidance plus language-specific references…majiayu000sepsis-3-cohortIdentify Sepsis-3 patients in MIMIC-IV using the consensus definition (SOFA >= 2 + suspected infection). Use for sepsis cohort…majiayu000session-inspectorThis skill should be used when inspecting, analyzing, or querying Claude Code session logs. Use when users ask about session…majiayu000setting-profilesUse this skill when switch model profile for kata agents (quality/balanced/budget). Triggers include "set profile", "set profile".majiayu000writesseuratclusterstatsGenerates comprehensive cluster statistics and visualizations for Seurat objects, including dimension reduction plots, gene…majiayu000shellcheck-configurationMaster ShellCheck static analysis configuration and usage for shell script quality. Use when setting up linting infrastructure…wshobsonsite-content-catalogCrawl a website's sitemap and blog index to build a complete content inventory. Lists every page with URL, title, publish date…majiayu000skill-authorThe authoring gate for new skills. Routed to when the user invokes /new-skill "<gap>". Five gated phases — gap evidence, scope…arbiterForgeskill-injection-defenseAudits legal AI skills, prompts, workflows, MCP/tool instructions, and agent packages for prompt injection, malicious…lawve-aiskill-judgeEvaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or…softaworksskill-portingInstall skills from external ecosystems into this agent's agent_state/skills/ — resolve Claude Code plugin marketplaces, the…Prism-Shadowslides-as-codeBuild research slides with text-first source (Slidev/Marp/Reveal/Quarto) and reproducible export (PDF). Includes structure…foryourhealth111-pixelwritessocket-programmingDeep integration with socket APIs for TCP/UDP programming across platforms. Execute socket operations, analyze socket options and…a5c-aiwritessoftware-engineeringComplete software-engineering tasks — investigate and review code, implement bug fixes, features and refactors with minimal…Prism-Shadowspec-execution6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress…a5c-aiwritesspeckit-analyzePerform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task…majiayu000specstory-session-summarySummarize recent SpecStory AI coding sessions in standup format. Use when the user wants to review sessions from…majiayu000split-pdfDownload, split, and deeply read academic PDFs. Use when asked to read, review, or summarize an academic paper. Splits PDFs into…brycewang-stanfordwritesstakeholder-communicationCommunicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates…rampstackcostartup-review-miningSystematic extraction of pain points, feature gaps, switching triggers, and opportunities from review sources (B2B review sites…majiayu000statement-coachCoach a statement of purpose or personal essay to admission strength — structural diagnosis, specific feedback, and revision…mohitagw15856stock-pickerScreens and selects stocks based on customizable quantitative criteria including value, growth, quality, and momentum factorsmajiayu000story-outline-evaluatorProfessionally evaluate story outlines, judge and score from dimensions of market potential, innovation attributes, and content…majiayu000storyboard-previsualizationProvider-independent storyboard and previsualization direction for AI agents turning briefs, scripts, treatments, ads, films…calesthiostructured-debugAI DevKit · Guide structured debugging before code changes by clarifying expected behavior, reproducing issues, identifying…codeaholicguysuede-agent-teamsSplit complex work into coordinated agent lanes with WIP checks, quality gates, rollback plans, and handoffs that prove what…JasonColapietrosuede-full-sendOutcome-bound router for broad, authorized work. Use for full send, max effort, max agents, max agent teams, spare no compute…JasonColapietrosuede-visibility-graderGrade a public page for launch appeal: findability, first-screen clarity, CTA pull, proof quality, and AI citation readiness.JasonColapietrosurvey-generatorCompile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of…majiayu000writessystem-reviewdeeply review a system/architecture area and propose a simplification plan (Elon’s Algorithm).majiayu000systematic-literature-review当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。AI 自定检索词,多源检索→去重→AI…majiayu000systematic-literature-review当用户需要做系统综述/文献综述/related work/相关工作/文献调研时使用:AI 自定检索词,多源检索→去重→AI 逐篇阅读并评分(1–10分语义相关性与子主题分组)→按高分优先比例选文→自动生成"综/述"字数预算(70% 引用段 + 30%…majiayu000talking-head-podcast-recutProvider-independent production workflow for recutting long talking-head, podcast, interview, webinar, panel, lecture…calesthiobio-metabolomics-targeted-analysisTargeted metabolomics analysis using MRM/SRM with standard curves. Covers absolute quantification, method validation, and quality…majiayu000taskAI DevKit · Track dev-lifecycle / structured-debug progress on a durable task with the ai-devkit task CLI. Use to record phase…codeaholicguyteam-communication-protocolsStructured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures…wshobsonteam-performance-reviewCompare your sales reps side by side on outreach volume, engagement rates, and meetings booked to identify top performers and…majiayu000tech-writing-lintAutomated technical writing style and quality enforcement. Lint documentation with Vale, check for inclusive language, enforce…a5c-aiwritestech-writing-linterLint technical documentation for style, consistency, and readabilitya5c-aiwritestechdebtFind and fix technical debt including duplicated code, dead code, outdated patterns, and code smells. Run at the end of sessions…brycewang-stanfordtechnical-researchExplore ideas, validate concepts, and research broadly across technical, business, and market domains. Preliminary phase before…majiayu000testing-accessibilityUse when testing accessibility is required during quality work, especially when the result must be traceable, independently…casioreview20-glitchtesting-concurrent-behaviorUse when testing concurrent behavior is required during quality work, especially when the result must be traceable, independently…casioreview20-glitchtesting-end-to-end-flowsUse when testing end to end flows is required during quality work, especially when the result must be traceable, independently…casioreview20-glitchtesting-performance-budgetsUse when testing performance budgets is required during quality work, especially when the result must be traceable, independently…casioreview20-glitchtesting-platform-compatibilityUse when testing platform compatibility is required during quality work, especially when the result must be traceable…casioreview20-glitchtesting-production-loadUse when testing production load is required during quality work, especially when the result must be traceable, independently…casioreview20-glitch
← Prev26 / 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