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
7,4897,536 · page 157 / 203
llm-application-devBuilding applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered…MoizIbnYousafllm-configConfigure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptationruvnetwritesllm-evaluationMaster comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.sickn33llm-gateLLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before…rohitg00llm-providerAdds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in…caliber-ai-orgllm-trading-agent-securitySecurity patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits…mturaclmnt-automationAutomate Lmnt tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlms-adminConfigure and manage Learning Management System operations including courses, enrollments, compliance training, and learning…a5c-aiwriteslms-configuration-administrationConfigure learning management system settings, user roles, course templates, gradebooks, and third-party integrationsa5c-aiwritesln-11-plan-reviewerReviews implementation plans against repository evidence and current authoritative guidance. Use before execution to expose gaps…levnikolaevichln-12-delivery-reviewerReviews a completed scoped change and its affected runtime and contract paths. Use to find change-caused defects and verify…levnikolaevichln-21-documentation-auditorAudits documentation and code comments for structure, coverage, factual accuracy, and maintainability. Use for documentation…levnikolaevichln-22-codebase-auditorAudits cross-cutting code health across security, delivery, maintainability, dependencies, diagnosability, concurrency, and…levnikolaevichln-23-test-suite-auditorAudits whether an existing test suite proves important product behavior with strong, isolated tests. Use when test confidence is…levnikolaevichln-24-architecture-auditorAudits implemented architecture fitness, boundaries, contracts, dependencies, and configuration ownership. Use for system…levnikolaevichln-25-persistence-auditorAudits queries, transactions, data-path performance, and persistence resource lifecycle. Use when data correctness or scalability…levnikolaevichln-31-performance-optimizerOptimizes a measured latency, throughput, memory, CPU, or I/O problem through profiling and keep-or-discard experiments. Use for…levnikolaevichln-32-dependency-upgraderUpgrades dependencies across package managers with breaking-change research and rollback-safe verification. Use for dependency…levnikolaevichln-33-code-modernizerModernizes a bounded capability by removing obsolete custom mechanisms or reducing bundle and maintenance cost. Use for proven…levnikolaevichln-34-benchmark-comparatorCompares tools or implementations through reproducible A/B workloads, correctness oracles, and controlled measurements. Use to…levnikolaevichln-41-test-strategy-plannerDesigns a risk-based test strategy and prioritized scenarios without changing code. Use when requirements need a test plan; not…levnikolaevichln-42-acceptance-test-builderCreates and runs reproducible acceptance tests for stated requirements using project-native tooling. Use when executable…levnikolaevichln-51-opportunity-evaluatorEvaluates new product directions using current demand, acquisition, competition, economics, and validation evidence. Use before…levnikolaevichln-61-skill-reviewerReviews standalone skills and their configured distribution surfaces before publication. Use for skill release readiness; not for…levnikolaevichln-62-repository-publisherValidates, commits, pushes, and remotely verifies approved repository changes. Use when publication is requested; not for…levnikolaevichln-63-release-publisherPrepares and publishes a tagged GitHub release from repository evidence. Use for an explicit release request; not for ordinary…levnikolaevichln-64-community-announcerDrafts and publishes fact-checked GitHub Discussions announcements. Use for releases, updates, or project news; not for release…levnikolaevichln-71-system-design-baseline-builderCreates a project baseline of architecture drivers and constraints. Use before design or planning; not for target design, plan…levnikolaevichln-72-current-architecture-documenterDocuments implemented current-state architecture from repository evidence. Use for onboarding or migration baselines; not for…levnikolaevichln-73-system-design-proposal-builderCreates a decision-complete target system design from requirements and constraints. Use before implementation planning; not for…levnikolaevichln-74-architecture-decision-recorderRecords one architecture decision with context, alternatives, tradeoffs, and consequences. Use for a significant choice; not for…levnikolaevichln-75-architecture-diagram-builderCreates evidence-backed current or target architecture diagrams when the diagram is the primary deliverable. Not for UI design…levnikolaevichln-76-architecture-migration-plannerPlans a reversible architecture migration with compatibility, data movement, rollout, and rollback. Use for current-to-target…levnikolaevichload-combination-generatorLoad combination generation skill per ASCE 7 and AASHTO for ASD and LRFD design methodsa5c-aiwritesload-optimization-calculatorAI-powered load building and consolidation skill to maximize trailer utilization and reduce transportation costsa5c-aiwriteslocal-legal-seo-auditAudit and improve local SEO for law firms, attorneys, forensic experts and legal/professional services sites with local presence…sickn33local-llm-expertMaster local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM…sickn33local-seo-auditAudit local SEO health. Use when: reviewing GBP optimization, NAP consistency, local citations, or local pack rankings.indranilbanerjeelocalize-campaignLocalize campaigns for multiple markets. Use when: translating assets, adapting references, adjusting compliance.indranilbanerjeelock-free-data-structuresDesign and implement lock-free data structures — CAS-based queues, hazard pointers, epoch reclamation, and wait-free algorithms…a5c-aiwriteslodgify-automationAutomate Lodgify tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlogic-lensAI-powered Claude Code skill that performs deep code review using formal logic and reasoning frameworks to detect bugs…sickn33logistics-exception-managementCodified expertise for handling freight exceptions, shipment delays, damages, losses, and carrier disputes. Informed by logistics…mturaclogistics-kpi-trackerComprehensive logistics performance measurement skill with KPI tracking, benchmarking, and improvement recommendationsa5c-aiwriteslogline-writingCraft compelling one-sentence story hooks that capture protagonist, conflict, stakes, and unique appeal for film/TV pitchesa5c-ailogo-dev-automationAutomate Logo Dev tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlong-task-continuationUse when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.GanyuanRanlongbridge-contentLatest news articles, regulatory filings, community discussion topics for listed stocks, and SEC EDGAR filing analysis…sickn33
← Prev157 / 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