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
8,6898,736 · page 182 / 203
security-bounty-hunterHunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify…mturacsecurity-checklistReference document for monopoly security-checklist.sickn33security-patternsImplements authentication, authorization, encryption, secrets management, and security hardening patterns. Use when designing…CloudAI-Xsecurity-researchTeam Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in parallel…code-yeongyusecurity-reviewerDedicated security-audit route for OWASP-style risks, secret leaks, auth flaws, injection, unsafe input handling, SSRF/XSS, and…foryourhealth111-pixelsecurity-scanScan your OpenAI Codex configuration (.codex/ directory) for security vulnerabilities, misconfigurations, and injection risks…mturacsecurity-scanRun full security scans on the codebase using Ruflo security tools. Use when reviewing PRs for security regressions, auditing…ruvnetsecurity-scanning-security-hardeningCoordinate multi-layer security scanning and hardening across application, infrastructure, and compliance controls.sickn33security-scanning-security-sastStatic Application Security Testing (SAST) for code vulnerability analysis across multiple languages and frameworks 'sickn33securitytrails-automationAutomate Securitytrails tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsegment-audienceCreate audience segments. Use when: building or updating CRM or email platform segments for campaign targeting.indranilbanerjeesegment-automationAutomate Segment tasks via Rube MCP (Composio): track events, identify users, manage groups, page views, aliases, batch…sickn33segment-cdpExpert patterns for Segment Customer Data Platform including Analytics.js, server-side tracking, tracking plans with Protocols…sickn33segmetrics-automationAutomate Segmetrics tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQseismic-automationAutomate Seismic tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQseismic-enablementSeismic sales enablement platform for content and learninga5c-aiwritesseismic-hazard-analyzerSeismic hazard analysis skill for site classification, spectral acceleration, and design response spectrum generationa5c-aiwritesselenium-skillGenerates production-grade Selenium WebDriver automation scripts and tests in Java, Python, JavaScript, C#, Ruby, or PHP.…sickn33self-evalHonestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to…alirezarezvaniself-improving-agentRepo-local meta-skill for improving Xiaobai Skills over time. Use after significant project changes, user feedback, install…Tyutssem-eds-analyzerScanning Electron Microscopy with Energy Dispersive X-ray Spectroscopy skill for morphology and elemental analysisa5c-aiwritessemantic-scholar-searchAcademic literature search using Semantic Scholar API for citation-aware paper discoverya5c-aiwritessemantic-similaritySemantic similarity computation for content relationships and intelligent discoverya5c-aiwritessemanticscholar-automationAutomate Semanticscholar tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsemgrep-rule-creatorCreates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep…sickn33writessemgrep-rule-variant-creatorCreates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an…sickn33SEMrush AutomationAutomate SEO analysis with SEMrush -- research keywords, analyze domain organic rankings, audit backlinks, assess keyword…ComposioHQsend-email-campaignSend email campaigns. Use when: deploying via SendGrid, Klaviyo, Customer.io, Brevo, or Mailchimp with A/B testing.indranilbanerjeesend-notificationSend team notifications. Use when: pushing campaign updates, alerts, or approval requests via Slack or Intercom.indranilbanerjeesend-reportDeliver performance reports. Use when: sending KPI summaries via Slack, email, or Google Sheets with analysis.indranilbanerjeesend-smsSend SMS or WhatsApp messages. Use when: deploying marketing messages via Twilio or Brevo with compliance checks.indranilbanerjeesendbird-ai-chabot-automationAutomate Sendbird AI Chabot tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsendbird-automationAutomate Sendbird tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsendblue-apiSend and receive iMessage, SMS, and RCS from application code via the Sendblue HTTP API — text, media, group messages, send…sickn33sendblue-cliSend iMessage and SMS from the shell via the @sendblue/cli npm package — outbound sends, contact management, and account setup…sickn33sendblue-notifyText the user's phone when a long-running task, agent turn, or scheduled job finishes — via @sendblue/cli for outbound…sickn33sendfox-automationAutomate Sendfox tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsendgrid-automationAutomate SendGrid email delivery workflows including marketing campaigns (Single Sends), contact and list management, sender…sickn33sendlane-automationAutomate Sendlane tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsendloop-automationAutomate Sendloop tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsendspark-automationAutomate Sendspark tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsensibo-automationAutomate Sensibo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsensitivity-analysis-toolkitComprehensive sensitivity analysis for optimizationa5c-aiwritessensitivity-analyzerSensitivity analysis skill for identifying critical inputs and understanding model behavior under uncertaintya5c-aiwritessensor-librariesIntegrate and validate sensor libraries for embedded systems including IMUs, temperature, pressure, and proximity sensors.a5c-aiwritessentry-automationAutomate Sentry tasks via Rube MCP (Composio): manage issues/events, configure alerts, track releases, monitor projects and…sickn33sentry-triageDiagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and…composio-communityseo-aeo-blog-writerWrites long-form blog posts with TL;DR block, definition sentence, comparison table, and 5-question FAQ for SEO ranking and AEO…sickn33
← Prev182 / 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