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
8,5938,640 · page 180 / 203
saas-multi-tenantDesign and implement multi-tenant SaaS architectures with row-level security, tenant-scoped queries, shared-schema isolation, and…sickn33saas-mvp-launcherUse when planning or building a SaaS MVP from scratch. Provides a structured roadmap covering tech stack, architecture, auth…sickn33safe-modePrevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict…rohitg00safety-assessmentSkill for structured safety assessment following ARP4761 guidelinesa5c-aiwritessafety-critical-testingImplement safety-critical testing for embedded systems per IEC 61508, ISO 26262, or DO-178C standards.a5c-aiwritessafety-guardUse this skill to prevent destructive operations when working on production systems or running agents autonomously.mturacsafety-scanScan inputs for prompt injection, unsafe content, and adversarial attacks using AIDefence. Use when processing untrusted input…ruvnetwritessafety-stock-calculatorDynamic safety stock and reorder point optimization skill based on demand variability, lead times, and service level targetsa5c-aiwritessafetyculture-automationAutomate Safetyculture tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsage-automationAutomate Sage tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsage-math-interfaceSageMath for comprehensive mathematical computationa5c-aiwritessales-automatorDraft cold emails, follow-ups, and proposal templates. Creates pricing pages, case studies, and sales scripts. Use PROACTIVELY…sickn33salesforce-automationAutomate Salesforce tasks via Rube MCP (Composio): leads, contacts, accounts, opportunities, SOQL queries. Always search tools…sickn33salesforce-connectorBi-directional Salesforce CRM integration for sales data managementa5c-aiwritessalesforce-developmentExpert patterns for Salesforce platform development including Lightning Web Components (LWC), Apex triggers and classes…sickn33salesforce-marketing-cloud-automationAutomate Salesforce Marketing Cloud tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsalesforce-service-cloud-automationAutomate Salesforce Service Cloud tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsalesloft-cadencesSalesLoft cadence and sales engagement integrationa5c-aiwritessalesmate-automationAutomate Salesmate tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsalmon-quantifierSalmon pseudo-alignment skill for fast and accurate transcript quantificationa5c-aiwritessample-skillUse when validating the SkillForge validator itself - exercises every supported frontmatter feature: boolean user-invocable, an…tripleyakwritessamtools-bam-processorBAM/SAM file manipulation skill for sorting, indexing, filtering, and extracting alignment dataa5c-aiwritessandbox-claude-insideRun Claude Code INSIDE a ca-sandbox box (`--with-claude`). Routed to when the user wants an agent loop running against an…arbiterForgesandbox-lifecycleThe lifecycle gate for a local Codespace-equivalent sandbox. Routed to when the user invokes /ca-sandbox:sandbox to pull an…arbiterForgesanity-testingDesign and execute sanity test suites to verify core system functionality after builds or deployments before broader test runs.a5c-aiwritessanta-methodMulti-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.mturacsap-successfactors-automationAutomate SAP SuccessFactors tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsast-configurationStatic Application Security Testing (SAST) tool setup, configuration, and custom rule creation for comprehensive security…sickn33sast-configurationConfigure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when…wshobsonsatismeter-automationAutomate Satismeter tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQsatoriClinically informed wisdom companion blending psychology and philosophy into a structured thinking partnersickn33save-knowledgeSave brand knowledge to memory. Use when: persisting campaign learnings, guidelines, or competitive intel for retrieval.indranilbanerjeesave-learningSaves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from…caliber-ai-orgsave-load-systemsDesign and implement game save and load systems — serialization, versioning, cloud saves, and save-state integrity.a5c-aiwritessaxs-waxs-analyzerSmall/Wide Angle X-ray Scattering skill for nanostructure size, shape, and organization analysisa5c-aiwritesscaffold-design-optimizerTissue engineering scaffold design optimization skill for pore size, porosity, and mechanical propertiesa5c-aiwritesscala-proMaster enterprise-grade Scala development with functional programming, distributed systems, and big data processing. Expert in…sickn33scalaLanguage-specific super-code guidelines for scala.sickn33scale-benchmarksReference document for monopoly scale-benchmarks.sickn33scale-up-analyzerProcess scale-up analysis skill for dimensional analysis, similarity criteria, and pilot-to-production transitionsa5c-aiwritesscale-up-process-analyzerProcess engineering skill for analyzing and optimizing nanomaterial synthesis scale-up from lab to productiona5c-aiwritesscanScans the codebase to generate project-doc.md and AGENTS.md. Use when bootstrapping a new agent-driven repo, refreshing project…wshobsonscanning-toolsMaster essential security scanning tools for network discovery, vulnerability assessment, web application testing, wireless…sickn33scanpyScanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete…sickn33scenario-modelerMonte Carlo simulations for exit scenarios, return distributionsa5c-aiwritesscenario-narrative-generatorScenario narrative generation skill for creating vivid, consistent future scenario descriptionsa5c-aiwritesscenario-simulationScenario-based simulation for ADAS/AD validationa5c-aiwritesscene-writingWrite individual screenplay scenes with proper industry formatting, visual action, and dramatic structurea5c-ai
← Prev180 / 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