Agent skills

Skills for cursor

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
6,852 found
3,4573,504 · page 73 / 143
case-study-writeupWrite a client case study that sells future work — challenge, approach, results. Use when asked to write a case study, a client…mohitagw15856cash-flow-forecastBuild a short-term (13-week) cash flow forecast to see if you can cover what's due. Use when asked to build a cash flow forecast…mohitagw15856castingwords-automationAutomate Castingwords tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcategory-designerDefine a new category where your product wins by default. Reframe the buying decision. Triggers on: "create a category"…Affitorcategory-page-briefPlan an e-commerce category / collection page that ranks and merchandises well. Use when asked to design a category page, a PLP…mohitagw15856category-page-generatorWhen the user wants to create, optimize, or audit e-commerce category pages or listing pages. Also use when the user mentions…kostja94cats-automationAutomate Cats tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcavemanUltra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy.…shobcodercc-skill-backend-patternsBackend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and…sickn33cc-skill-clickhouse-ioClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical…sickn33cc-skill-coding-standardsUniversal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.sickn33cc-skill-frontend-patternsFrontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.sickn33cc-skill-security-reviewThis skill ensures all code follows security best practices and identifies potential vulnerabilities. Use when implementing…sickn33cdk-patternsCommon AWS CDK patterns and constructs for building cloud infrastructure with TypeScript, Python, or Java. Use when designing…sickn33cdr-platform-automationAutomate Cdr Platform tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcensus-bureau-automationAutomate Census Bureau tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcentralstationcrm-automationAutomate Centralstationcrm tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcertifier-automationAutomate Certifier tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQchange-management-planCreate a structured change management plan for any organisational change. Use when asked to write a change management plan…mohitagw15856change-order-writerDraft a defensible construction change order with entitlement basis, scope delta, itemised pricing, and schedule impact. Use when…mohitagw15856change-quizAfter a working session, produce a report on what changed plus a quiz the user must pass before merging. Use when the user asks…Neeeophyteechangelog-for-humansWrite changelogs and release notes readers actually benefit from — changes translated to so-whats, grouped by reader impact…mohitagw15856changelog-from-commitsWrite a human changelog from the REAL commit history — read the actual commit range via the GitHub connector, not a template. Use…mohitagw15856devops/changelog-generation自动生成 CHANGELOG,基于 git 提交历史和 pipeline 产物信息,遵循 Conventional Commits 和 Keep a Changelog 规范echoVicchangelog-generatorAutomatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming…MoizIbnYousafchangelog-page-generatorWhen the user wants to create, optimize, or structure a changelog or release notes page. Also use when the user mentions…kostja94changelog-writerTurn a list of changes, commits, or PRs into clean release notes / a changelog entry. Use when asked to write release notes, a…mohitagw15856channel-hygieneFix a team's chat sprawl — the channel map with one purpose per channel, the naming scheme that makes purpose findable, the…mohitagw15856chargeback-dispute-responseWin a chargeback dispute — read the reason code, assemble the evidence packet, and write the rebuttal that actually persuades the…mohitagw15856chart-choicePick the chart the data and the point actually need — the question-to-chart mapping (comparison, trend, composition…mohitagw15856chart-data-extractorExtract pixel-level data from an image of a chart or graph and produce a structured data table. Use when asked to extract data…mohitagw15856chartTurn numbers into a chart — bar, line, area, pie, or doughnut. Use when asked to chart or graph data, visualize…mohitagw15856chaser-automationAutomate Chaser tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQchat-widgetBuild a real-time support chat system with a floating widget for users and an admin dashboard for support staff. Use when the…sickn33chatbotkit-automationAutomate Chatbotkit tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQchatfai-automationAutomate Chatfai tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQchatwork-automationAutomate Chatwork tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcheckRun the unified pre-publish quality gate on marketing content — hallucination detection, claim verification, brand voice scoring…indranilbanerjeewriteschinese-code-review中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。jnMetaCodechinese-commit-conventions中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式…jnMetaCodechinese-documentation中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。jnMetaCodechinese-git-workflow国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。jnMetaCodechmeetings-automationAutomate Chmeetings tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQchrome-devtoolsBrowser debugging, performance profiling, and automation via Chrome DevTools MCP. Use when user says "debug this page", "take a…tech-leads-clubchrome-extension-developerExpert in building Chrome Extensions using Manifest V3. Covers background scripts, service workers, content scripts, and…sickn33churn-riskAssess customer churn risk. Use when: churn scoring, at-risk segment identification, intervention playbook generation.indranilbanerjeeci-cd-and-automationAutomates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate…addyosmanici-cd-and-automationAutomates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate…sickn33
← Prev73 / 143Next →
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