Agent skills

Skills for codex

9,699 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 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
9,699 found
5,7135,760 · page 120 / 203
ca-initOpt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.arbiterForgeca-metricsRead-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs.…arbiterForgeca-new-skillAuthor a new codeArbiter skill: prove the gap is real, get the spec approved, then write it.arbiterForgeca-overrideSanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.arbiterForgeca-prOpen a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to…arbiterForgeca-previewZero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the…arbiterForgeca-pruneTrim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by…arbiterForgeca-reconcileSMARTS arbitration — reconcile architectural artifacts against the scaffold and prior decisions; every variance resolved by an…arbiterForgeca-refactorRestructure code with behavioral parity proven through unmodified pre-existing tests, then refactor. No behavior change.arbiterForgeca-releaseCut a release the only sanctioned way — SemVer bump from the commit log, a CHANGELOG section, an annotated tag. Takes the…arbiterForgeca-reviewReview a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound…arbiterForgeca-spikeExploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or…arbiterForgeca-sprintAutonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard…arbiterForgeca-standupDaily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only…arbiterForgeca-statusShow the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current…arbiterForgeca-taskThe sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID…arbiterForgeca-threat-modelOpt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change…arbiterForgeca-tribunalDeep, rarely-convened whole-codebase audit — eleven specialist lenses, a resumable on-disk audit log, findings filed as GitHub…arbiterForgeca-watchWatch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.arbiterForgecabinpanda-automationAutomate Cabinpanda tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcad-modelingExpert skill for parametric 3D CAD model development with design intent and configuration managementa5c-aiwritescal-automationAutomate Cal tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcal-com-automationAutomate Cal.com tasks via Rube MCP (Composio): manage bookings, check availability, configure webhooks, and handle teams. Always…sickn33calcSpreadsheet creation, format conversion (ODS/XLSX/CSV), formulas, data automation with LibreOffice Calc.sickn33calendarhero-automationAutomate Calendarhero tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcalendly-automationAutomate Calendly scheduling, event management, invitee tracking, availability checks, and organization administration via Rube…sickn33calendly-schedulingCalendly meeting scheduling integration for sales workflowsa5c-aiwritescaliber-testingWrites Vitest tests following project patterns: __tests__/ directories, vi.mock() for module mocking with vi.hoisted() for…caliber-ai-orgcalibration-analyzerHardware calibration data analysis skill for optimal qubit selectiona5c-aiwritescalibration-trainerProbability calibration training skill for improving forecast accuracy and reducing overconfidencea5c-aiwritescallerapi-automationAutomate Callerapi tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcallingly-automationAutomate Callingly tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcallpage-automationAutomate Callpage tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcamb-cosmology-calculatorCAMB cosmological perturbation skill for CMB power spectra, matter power spectra, and cosmological parameter estimationa5c-aiwritescampaign-auditAudit a brand's existing live campaigns across every active channel — paid, organic, email, social, content, SEO. Produce a…indranilbanerjeewritescampaign-cleaner-automationAutomate Campaign Cleaner tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcampaign-statusCheck active campaign status. Use when: cross-platform execution history, performance metrics, pending approvals.indranilbanerjeecampayn-automationAutomate Campayn tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcan-communicationCAN bus design, analysis, and diagnostics expertisea5c-aiwritescanary-watchUse this skill to monitor and verify a deployed URL or public OSS launch surface after releases — checks HTTP endpoints, SSE…mturaccanny-automationAutomate Canny tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcanva-automationAutomate Canva tasks via Rube MCP (Composio): designs, exports, folders, brand templates, autofill. Always search tools first for…sickn33canvas-automationAutomate Canvas tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcanvas-designCreate beautiful visual art in PNG and PDF documents using design philosophy and aesthetic principles for posters, illustrations…nexu-iocap-table-validatorValidates cap table accuracy, identifies issues, models option pool impacta5c-aiwritescapacity-constraint-analyzerProduction capacity analysis skill using Theory of Constraints principlesa5c-aiwritescapacity-plannerCapacity requirements planning skill with demand-capacity gap analysis and capacity strategy recommendationsa5c-aiwritescapital-budgeting-analyzerCapital investment appraisal skill with NPV, IRR, payback, and real options analysisa5c-aiwrites
← Prev120 / 203Next →
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