60424 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

extract

Extract content from specific URLs using Tavily's extraction API. Returns clean markdown/text from web pages. Use when you have specific URLs and need their content without writing code.

tavily-ai
tavily-ai
0

research

Get AI-synthesized research on any topic with citations, directly in your terminal. Supports structured JSON output for pipelines. Use when you need comprehensive research grounded in web data without writing code.

tavily-ai
tavily-ai
0

crawl

Crawl any website and save pages as local markdown files. Use when you need to download documentation, knowledge bases, or web content for offline access or analysis. No code required - just provide a URL.

tavily-ai
tavily-ai
0

methodical-debugging

Systematic debugging approach using parallel investigation and test-driven validation. Use when debugging issues, when stuck in a loop of trying different fixes, or when facing complex bugs that resist standard debugging approaches.

debuggingtest-driven-developmentsystematic-approachcomplex-bugs
metjm
metjm
0

plan-review

Expert technical reviewer for implementation plans. Reviews plans in docs/plans/ for correctness, completeness, and technical accuracy. Validates libraries, APIs, and approaches. Outputs feedback as markdown in the final response.

implementation-plantechnical-reviewapi-validationfeedback
metjm
metjm
0

planning

Expert technical analyst for comprehensive codebase analysis and strategic implementation planning. Use when planning features, designing architecture, analyzing complex tasks, or when you need a detailed plan.md before implementation.

codebase-analysisarchitecture-designimplementation-planfeature-planning
metjm
metjm
0

critical-thinking

Proactively challenge implementation plans, architecture decisions, and design assumptions. Use when reviewing plans, designs, or technical decisions. Verifies claims via web search, cross-references documentation, identifies risks and gaps, and surfaces hidden assumptions. Activates automatically when evaluating technical proposals.

assumption-challengingrisk-assessmentidea-evaluationproblem-framing
Optima-Financial
Optima-Financial
0

microservices-architect

Design and architect microservices following Chris Richardson's Microservices Patterns. Use when designing services, APIs, data flows, or evaluating architecture decisions. Guides full workflow from feature intake to production-ready design with observability, async patterns, security, testing, and deployment strategies.

microservicesservice-meshapi-designobservability
Optima-Financial
Optima-Financial
0

creating-skills

Create high-quality Claude Code skills with proper structure, effective descriptions, and best practices. Use when creating a new skill, writing SKILL.md files, setting up skill directories, or asking how to make skills.

claude-codeskill-developmentbest-practicesdocumentation
Optima-Financial
Optima-Financial
0

optima-service-planner

Plan and implement microservices for Optima platform. Use when building new services, features, or integrations. Generates phased implementation roadmaps following Optima patterns - Database Gateway, append-only contracts, RabbitMQ messaging, DigitalOcean deployment. Start with data model, then contracts, then services.

microservicesrabbitmqdigitaloceandatabase-gateway
Optima-Financial
Optima-Financial
0

repo-docs

Generate comprehensive repository documentation following team standards. Use when creating README, CLAUDE.md, ARCHITECTURE.md, DESIGN_DECISIONS.md, or any project documentation. Includes Mermaid diagrams, status indicators, and AI context files.

repository-managementdocumentation-generationmermaidproject-documentation
Optima-Financial
Optima-Financial
0

next-code-reviewer

Review code for adherence to project guidelines, style guides, and best practices. Use after writing or modifying code, before committing changes or creating pull requests.

code-reviewbest-practicesstandards-compliancepre-commit
Morriz
Morriz
0

next-comment-analyzer

Analyze code comments for accuracy, completeness, and long-term maintainability. Use after adding documentation, before finalizing PRs with comment changes, or when reviewing existing comments for technical debt.

commentstechnical-debtcode-smellreview-checkpoints
Morriz
Morriz
0

next-code-simplifier

Simplify code for clarity, consistency, and maintainability while preserving all functionality. Use after completing a coding task or after passing code review to polish the implementation.

refactoringcode-cleanupcode-quality
Morriz
Morriz
0

next-type-design-analyzer

Analyze type design quality and invariants. Use when introducing new types, during PR creation with data models, or when refactoring type designs.

type-definitionscode-qualitydata-modelingpull-requests
Morriz
Morriz
0

next-test-analyzer

Review test coverage quality and completeness. Use after creating a PR or adding new functionality to ensure tests adequately cover new code and edge cases.

test-coveragepull-requeststest-qualityedge-case-testing
Morriz
Morriz
0

next-silent-failure-hunter

Identify silent failures, inadequate error handling, and inappropriate fallback behavior. Use when reviewing code with error handling, catch blocks, or fallback logic.

error-handlingcatch-blocksfallback-mechanismscode-quality
Morriz
Morriz
0

writing-clearly-and-concisely

Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.

clarity-adjustmentconcisenesswriting-techniquesediting
mikeastock
mikeastock
0

executing-plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints

implementationplan-executionreview-checkpointsexecution-workflow
mikeastock
mikeastock
0

fetching-buildkite-failures

Use when CI fails on Buildkite and you need to diagnose and fix failures - fetches build results for current branch, extracts errors from logs, and helps fix them

buildkiteci-failurelogsdebugging
mikeastock
mikeastock
0

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

specificationrequirements-gatheringtask-planningimplementation-plan
mikeastock
mikeastock
0

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

test-driven-developmentdevelopment-processsoftware-qualitytest-first
mikeastock
mikeastock
0

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

subagentstask-decompositionimplementation-plansession-management
mikeastock
mikeastock
0

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

problem-framinguser-intentcreative-thinkingrequirements-gathering
mikeastock
mikeastock
0

creating-hooks

Guide for implementing Claude Code hooks. Use when creating event-driven automation, auto-linting, validation, or context injection. Covers all hook events, matchers, exit codes, and environment variables.

hook-systemworkflow-automationevent-drivencontext-injection
hgeldenhuys
hgeldenhuys
0

context-optimization

Guide for managing and optimizing context in Claude Code. Use when experiencing slow responses, context warnings, or planning large tasks. Covers /compact, /clear, context budgeting, subagent delegation, and efficient session workflows.

context-managementtoken-optimizationworkflowsubagent-delegation
hgeldenhuys
hgeldenhuys
0

creating-mcp-servers

Guide for creating and integrating MCP (Model Context Protocol) servers with Claude Code. Use when building external tool integrations, connecting to databases, creating custom capabilities, or adding API wrappers. Covers transports, OAuth, configuration, and troubleshooting.

model-context-protocolclaude-codeexternal-toolsOAuth
hgeldenhuys
hgeldenhuys
0

cost-optimization

Manage Claude Code API costs - token strategies, model selection, monitoring. Use when concerned about API spend, optimizing token usage, choosing models for tasks, or setting up cost monitoring. Covers /cost command, batching strategies, and budget management.

cost-optimizationtoken-optimizationmodel-selectionbudget-management
hgeldenhuys
hgeldenhuys
0

headless-mode

Guide for using Claude Code programmatically via CLI flags and SDKs. Use for automation, CI/CD pipelines, scripting, and building tools on top of Claude Code. Covers --print mode, output formats, session management, and SDK integration.

automationsdksession-managementoutput-formatting
hgeldenhuys
hgeldenhuys
0

ci-cd-integration

CI/CD integration - GitHub Actions, automation, pipeline integration

ci-cdgithub-actionsautomationpipeline
hgeldenhuys
hgeldenhuys
0

migration-guides

Migration guides - from other AI tools, version upgrades, config migration. Use when switching from Cursor, Copilot, or Cody, upgrading Claude Code versions, or migrating configurations and customizations.

migration-guidesupgrade-pathsconfiguration-migrationdeveloper-guidance
hgeldenhuys
hgeldenhuys
0

code-review

Get quality code reviews from Claude Code - PR workflows, review prompts, checklists

claude-codepull-requestscode-reviewchecklists
hgeldenhuys
hgeldenhuys
0

claude-code-reference

Reference guide for Claude Code extensions. CONSULT BEFORE implementing skills, creating hooks, slash commands, or MCP servers. Use when building Claude Code extensions, understanding extension differences, or troubleshooting extension issues. Covers skills vs commands vs hooks vs MCP disambiguation.

developer-guidancecode-documentationplugin-hookstroubleshooting
hgeldenhuys
hgeldenhuys
0

documentation-generation

Generate quality documentation - READMEs, API docs, inline comments. Use when creating new project documentation, updating existing docs, or ensuring documentation stays in sync with code. Covers README patterns, JSDoc, OpenAPI, and architecture docs.

READMEcode-documentationJSDocOpenAPI
hgeldenhuys
hgeldenhuys
0

project-setup

Guide for setting up projects to work optimally with Claude Code. Use when configuring new projects, migrating existing projects, setting up team permissions, or troubleshooting project configuration. Covers directory structure, settings files, permissions, and best practices.

claude-codeconfigurationdirectory-structurepermissions
hgeldenhuys
hgeldenhuys
0

debugging-claude-code

Troubleshooting guide for Claude Code issues. Use when Claude behaves unexpectedly, tools fail, sessions hang, or you need to diagnose problems. Covers diagnostics, common issues, and recovery procedures.

debuggingdiagnosticserror-handlingrecovery-procedures
hgeldenhuys
hgeldenhuys
0

custom-slash-commands

Guide for creating custom Claude Code slash commands - shortcuts for frequently-used prompts and workflows. Use when creating reusable prompts, automating common tasks, or building team workflows. Covers frontmatter, arguments, bash execution, and namespacing.

workflow-automationslash-commandsprompt-engineeringautomation
hgeldenhuys
hgeldenhuys
0

creating-subagents

Guide for creating custom Claude Code subagents (Task tool agents). Use when building specialized autonomous agents for specific domains or workflows. Covers agent definition, frontmatter options, tool restrictions, and spawning patterns.

autonomous-agentclaude-codetask-toolsubagents
hgeldenhuys
hgeldenhuys
0

multi-file-editing

Strategies for coordinated changes across multiple files with Claude Code. Use when making API changes, updating interfaces, refactoring shared code, or performing migrations. Covers dependency ordering, atomic vs incremental changes, and validation patterns.

claude-coderefactoringdependency-managementcode-migration
hgeldenhuys
hgeldenhuys
0

transcript-intelligence

Search and analyze Claude Code transcripts for past decisions, solutions, and discussions. Use when recalling past context, finding solutions to previously-solved problems, understanding session history, or restoring context after compact/clear.

conversation-historycontext-managementtranscript-searchsession-retrieval
hgeldenhuys
hgeldenhuys
0

writing-skills

Guide for creating effective Claude Code skills. Use when creating new skills, refactoring existing skills, or validating skill structure. Covers YAML frontmatter, progressive disclosure, naming conventions, and best practices.

yaml-frontmatterprogressive-disclosurenaming-conventionsbest-practices
hgeldenhuys
hgeldenhuys
0

git-workflows

Guide for git operations with Claude Code. Commits, PRs, code review, branch management, and best practices. Use when committing changes, creating pull requests, reviewing code, or managing branches.

gitcommitpull-requestbranch-management
hgeldenhuys
hgeldenhuys
0

monorepo-patterns

Monorepo workflows - navigation, cross-package changes, tooling

monorepotoolingcross-packagenavigation
hgeldenhuys
hgeldenhuys
0

refactoring-safely

Safe refactoring strategies with Claude Code - large-scale changes, validation, rollback

refactoringrollbackvalidationlarge-scale-changes
hgeldenhuys
hgeldenhuys
0

error-recovery

Handle Claude Code errors gracefully - error types, recovery, prevention

error-recoveryerror-typeserror-preventiongraceful-degradation
hgeldenhuys
hgeldenhuys
0

permission-patterns

Guide for configuring Claude Code permissions effectively. Use when setting up security policies, configuring allow/deny patterns, managing tool permissions, or implementing team security standards. Covers permission modes, sandboxing, and settings.json configuration.

permissionsrbacsandboxingsecurity-policies
hgeldenhuys
hgeldenhuys
0

testing-patterns

TDD workflows, test generation, and coverage strategies with Claude Code. Use when writing tests, implementing TDD, analyzing coverage gaps, or generating quality unit/integration/e2e tests. Covers Jest, Vitest, pytest, and mocking patterns.

tddtest-generationtest-coveragejest
hgeldenhuys
hgeldenhuys
0

team-workflows

Team collaboration patterns - shared configs, standards, onboarding

team-collaborationshared-configurationonboardingstandards
hgeldenhuys
hgeldenhuys
0

security-practices

Secure coding with Claude Code - vulnerability prevention, secrets, security review

secure-codingvulnerability-preventionsecurity-reviewsecrets-management
hgeldenhuys
hgeldenhuys
0

creating-plugins

Guide for creating full Claude Code plugins that bundle commands, agents, hooks, MCP servers, and LSP servers. Use when building distributable extensions, packaging multiple components together, or preparing plugins for marketplace distribution.

claude-codeplugin-hooksextension-developmentmarketplace
hgeldenhuys
hgeldenhuys
0

Page 1204 of 1209 · 60424 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.