Agent skills

Skills for codex

10,807 skills that declare support for codex. The SKILL.md format is shared, so most of these work in the other agents too — the declaration only says where the author tested it.

Toolclaude-code 67,974codex 10,807cursor 7,232copilot 2,452windsurf 127cline 83
CategoryWorkflow & Productivity 11,925AI & Agents 6,679Data & Analytics 5,379Code Review & Quality 3,250Backend & API 2,971Security 2,945Design & Presentation 2,611Documentation 2,340Content & Marketing 2,207Testing & QA 1,901DevOps & Cloud 1,389Databases 1,305Frontend 1,118Business & Finance 765Media & Video 599Other 22,617
9,782 found
9,0259,072 · page 189 / 204
speckit-checklistGenerate custom quality checklists for validating requirements completeness and clarity. Use to create unit tests for English…foryourhealth111-pixelspeckit-clarifyStructured clarification workflow for underspecified requirements. Use before planning to resolve ambiguities through…foryourhealth111-pixelspeckit-constitutionCreate or update project governing principles and development guidelines. Use at project start to establish code quality, testing…foryourhealth111-pixelspeckit-implementExecute all tasks from the task breakdown to build the feature. Use after task generation to systematically implement the planned…foryourhealth111-pixelspeckit-planGenerate technical implementation plans from feature specifications. Use after creating a spec to define architecture, tech…foryourhealth111-pixelspeckit-specifyCreate or update feature specifications from natural language descriptions. Use when starting new features or refining…foryourhealth111-pixelspeckit-tasksBreak down implementation plans into actionable task lists. Use after planning to create a structured task breakdown. Generates…foryourhealth111-pixelspeckit-taskstoissuesConvert tasks from tasks.md into GitHub issues. Use after task breakdown to track work items in GitHub project management.foryourhealth111-pixelspeechGenerate spoken audio from text using OpenAI's API with built-in voices. Useful for narrated explainers, lecture audio, and quick…nexu-iospend-analytics-engineProcurement spend analysis skill with classification, consolidation, and savings identificationa5c-aiwritesspinw-magnetic-simulatorSpinW spin wave simulation skill for magnetic materials, magnon dispersions, and neutron scattering analysisa5c-aiwritessplitwise-automationAutomate Splitwise tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQspoki-automationAutomate Spoki tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQspondyr-automationAutomate Spondyr tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQSpotify AutomationAutomate Spotify workflows including playlist management, music search, playback control, and user profile access via ComposioComposioHQspotlightr-automationAutomate Spotlightr tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQspreadsheet-formula-helperWrite and debug spreadsheet formulas (Excel/Google Sheets), pivot tables, and array formulas; translate between dialects; use…composio-communityspringboot-patternsSpring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use…mturacspringboot-securitySpring Security best practices for authn/authz, validation, CSRF, secrets, headers, rate limiting, and dependency security in…mturacspringboot-tddTest-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features…mturacspringboot-verificationVerification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before…mturacsprint-planning-calculatorCalculate sprint capacity and support story point estimationa5c-aiwritessprint-statusTrack parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status…rohitg00sql-injection-testingExecute comprehensive SQL injection vulnerability assessments on web applications to identify database security flaws…sickn33sql-proMaster modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance…sickn33sql-sentinelAudit SQL for the cost & performance anti-patterns that burn warehouse credits. Scores warehouse health 0-100 and outputs a…sickn33sqlmap-database-pentestingProvide systematic methodologies for automated SQL injection detection and exploitation using SQLMap.sickn33square-automationAutomate Square tasks via Rube MCP (Composio): payments, orders, invoices, locations. Always search tools first for current…sickn33squirrelFull-cycle AI coding skill: plans, builds, tests, lints, fixes bugs, and writes production-grade docs. Auto-detects project state…sickn33sred-project-organizerTake a list of projects and their related documentation, and organize them into the SRED format for submission.sickn33sred-work-summaryGo back through the previous year of work and create a Notion doc that groups relevant links into projects that can then be…sickn33ss-a11yAudit a component or page for accessibility issues and fix thembitjaruwritesss-auditAudit screens for UX issues using Nielsen's heuristics and modern mobile UX best practicesbitjaruss-buildBuild a screen with StyleSeed's composed design method — choose or compile an output grammar, apply a brand recipe plus…bitjaruwritesss-componentGenerate a new UI component following the StyleSeed design conventionsbitjaruwritesss-copyGenerate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tonebitjaruwritesss-dialTurn ONE design axis up or down as a coordinated, deterministic transform — "denser", "sharper corners", "more muted", "bolder"…bitjaruwritesss-feedbackAdd appropriate user feedback states (loading, success, error, empty) to a component or pagebitjaruwritesss-flowDesign user flows and navigation structure following proven UX patternsbitjaruwritesss-lintQuick automated lint — detects common design system violations in secondsbitjaruwritesss-motionApply a named StyleSeed motion to a component — either one of the 5 personality seeds (Spring/Silk/Snap/Float/Pulse ×…bitjaruwritesss-pageScaffold a new product page or screen from the compiled StyleSeed output grammar, surface adapter, brand recipe, and project lock.bitjaruwritesss-patternGenerate a composed UI pattern from the active StyleSeed grammar and brand recipe using existing primitives.bitjaruwritesss-referenceCompile screenshots, URLs, Figma exports, or an existing UI into a project-local StyleSeed output grammar with evidence, tokens…bitjaruwritesss-restyleApply one optional StyleSeed aesthetic profile without changing the selected output grammar, product job, or core design judgment.bitjaruwritesss-reviewReview UI code for design system compliance, accessibility, and best practicesbitjaruss-scoreScore a visual artifact's implementation quality 0-100 against its composed StyleSeed rule set — category breakdown, evidence…bitjaruwritesss-setupConfigure StyleSeed by selecting the output grammar, domain, page type, brand recipe, semantic palette recipe, optional aesthetic…bitjaruwrites
← Prev189 / 204Next →
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 657 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 101 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