19837 Skills Available

Find awesome
Agent Skills

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

Popular searches

gmail-skill

Read, search, send, and draft Gmail emails and Google contacts. Use when the user asks to check email, find emails, search messages, send emails, create drafts, look up contacts, or find someone's email/phone. Supports multiple accounts.

gmailemail-managementgoogle-contactsmulti-account
idanbeck
idanbeck
0

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

mcpmcp-sdkfastmcpapi-integration
DYAI2025
DYAI2025
0

sequence-development

Station Service SDK를 사용한 테스트 시퀀스 개발 가이드. SequenceBase 패턴, emit 메서드, manifest.yaml 작성법 제공. 사용자가 시퀀스 개발, SequenceBase 구현, 테스트 자동화 코드 작성, manifest.yaml 설정, emit 메서드 사용법을 문의할 때 활성화. (project)

sdktest-automationsequence-developmentmanifest-yaml
Soochol
Soochol
0

devils-advocate

Use before design phase to challenge assumptions, scope, architecture, and design decisions in understanding documents or design docs

assumption-challengingdesign-docarchitecture-validationcritical-thinking
axiomantic
axiomantic
0

green-mirage-audit

Use when reviewing test suites, after test runs pass, or when user asks about test quality

test-qualitytest-reviewtest-suitestest-assessment
axiomantic
axiomantic
0

design-doc-reviewer

Use when reviewing design documents, technical specifications, or architecture docs before implementation planning

design-doctechnical-specificationsarchitecture-documentsimplementation-planning
axiomantic
axiomantic
0

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

parallel-executiontask-dispatchingconcurrencyindependent-tasks
axiomantic
axiomantic
0

async-await-patterns

Use when writing JavaScript or TypeScript code with asynchronous operations

javascripttypescriptasync-awaitasynchronous-programming
axiomantic
axiomantic
0

receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable

code-reviewfeedbackdeveloper-guidanceclarity-adjustment
axiomantic
axiomantic
0

emotional-stakes

Use when writing subagent prompts, skill instructions, or any high-stakes task requiring accuracy and truthfulness

prompt-engineeringaccuracytruthfulnesshigh-stakes
axiomantic
axiomantic
0

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work (merge, PR, or cleanup)

branch-managementmergepull-requestcode-integration
axiomantic
axiomantic
0

fun-mode

Use when starting a session and wanting creative engagement, or when user says '/fun' or asks for a persona

persona-creationsession-managementcreative-engagementfun-mode
axiomantic
axiomantic
0

merge-conflict-resolution

Use when git merge or rebase fails with conflicts, you see 'unmerged paths' or conflict markers (<<<<<<< =======), or need help resolving conflicted files

gitmerge-conflictsconflict-resolutionversion-control
axiomantic
axiomantic
0

nim-pr-guide

>

nimprogramming-languageguidedocumentation
axiomantic
axiomantic
0

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

pull-requestscode-qualitydeveloper-guidancemerge
axiomantic
axiomantic
0

brainstorming

Use before any creative work - creating features, building components, adding functionality, or modifying behavior

creative-thinkingproblem-framingideationfeature-planning
axiomantic
axiomantic
0

fixing-tests

Use when tests are failing, test quality issues were identified, or user wants to fix/improve specific tests

test-failurestest-qualitytest-improvementtest-fix
axiomantic
axiomantic
0

instruction-engineering

Use when: (1) constructing prompts for subagents, (2) invoking the Task tool, or (3) writing/improving skill instructions or any LLM prompts for maximum effectiveness

prompt-engineeringtask-toolinstruction-writingllm
axiomantic
axiomantic
0

subagent-prompting

>

subagentspromptingagent-coordinationagent-framework
axiomantic
axiomantic
0

implementing-features

|

feature-implementationdevelopmentsoftware-engineering
axiomantic
axiomantic
0

implementation-plan-reviewer

Use when reviewing implementation plans before execution, especially plans derived from design documents

implementation-planplan-reviewdesign-documentsexecution-preparation
axiomantic
axiomantic
0

instruction-optimizer

Use when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability

token-optimizationinstruction-optimizationprompt-engineeringconciseness
axiomantic
axiomantic
0

fact-checking

>

fact-checkinginformation-verificationaccuracy-validation
axiomantic
axiomantic
0

executing-plans

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

implementation-planreview-checkpointsplan-executiontask-tracking
axiomantic
axiomantic
0

debugging

Use when debugging bugs, test failures, or unexpected behavior. Supports --scientific and --systematic flags for direct methodology selection.

test-failuresbug-trackingsystematic-thinkingscientific-methodology
axiomantic
axiomantic
0

test-driven-development

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

test-driven-developmentunit-testingtest-first-developmentsoftware-testing
axiomantic
axiomantic
0

using-skills

Use when starting any conversation to establish skill discovery patterns

conversation-initiationskill-navigationdialogue-patternsuser-engagement
axiomantic
axiomantic
0

worktree-merge

Use when merging parallel worktrees back together after parallel implementation with interface contracts

git-worktreesmergeparallel-developmentinterface-contracts
axiomantic
axiomantic
0

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

writingskill-developmenteditingverification
axiomantic
axiomantic
0

writing-plans

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

specificationrequirementstask-planningworkflow
axiomantic
axiomantic
0

subagent-driven-development

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

subagentstask-managementimplementation-plansession-execution
axiomantic
axiomantic
0

using-lsp-tools

Use when mcp-language-server tools are available and you need semantic code intelligence for navigation, refactoring, or type analysis

language-server-protocolsemantic-analysisrefactoringcode-navigation
axiomantic
axiomantic
0

finding-dead-code

>

dead-codecode-analysiscode-cleanuprefactoring
axiomantic
axiomantic
0

using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans

gitversion-controlworkspace-managementfeature-branch
axiomantic
axiomantic
0

code-reviewer

Comprehensive multi-AI code review system for Python, JavaScript, and TypeScript. Use when reviewing code for quality, security, performance, or best practices. Includes automated analysis scripts, language-specific patterns, and AI collaboration workflows for complex decisions.

code-reviewstatic-analysiscode-qualitybest-practices
nikhillinit
nikhillinit
0

probes

Pre-built audit probes for Cloudflare services. Reference these query patterns when validating D1 indexes, observability metrics, AI Gateway costs, and queue health via MCP tools.

cloudflareaudit-probesmetrics-validationmcp-tools
littlebearapps
littlebearapps
0

media-streaming

Implement Cloudflare Stream for video delivery and Images for image transformations. Use this skill when building media platforms, implementing video players, generating signed URLs, or optimizing image delivery with transformations.

cloudflare-streamvideo-deliveryimage-transformationssigned-urls
littlebearapps
littlebearapps
0

patterns

Cloudflare architecture patterns for common problems. Reference when decomposing monolithic Workers, optimizing D1 writes, or adding external API resilience.

cloudflareworkerd1resilience-patterns
littlebearapps
littlebearapps
0

architect

Design industry-grade Cloudflare architectures with wrangler.toml generation, Mermaid diagrams, AND Edge-Native Constraint validation. Use this skill when designing new systems, planning migrations, evaluating architecture options, or when the user mentions Node.js libraries that may not work on Workers.

cloudflarewrangler.tomlmermaidedge-computing
littlebearapps
littlebearapps
0

custom-hostnames

Manage Custom Hostnames and SSL for SaaS applications on Cloudflare. Use this skill when building white-label platforms, implementing vanity domains for customers, managing SSL certificate lifecycle, or troubleshooting custom hostname verification issues.

custom-domainssslsaasdomain-management
littlebearapps
littlebearapps
0

guardian

Proactively audit Cloudflare configurations for security vulnerabilities, resilience gaps, cost traps, AND budget/privacy risks. Use this skill when reviewing wrangler configs, before deployments, investigating issues, or when ANY architecture decision involves Durable Objects, R2, Workers AI, or high-volume operations. This skill PROACTIVELY warns about cost impacts before users ask.

cloudflarecost-optimizationrisk-managementdurable-objects
littlebearapps
littlebearapps
0

implement

Scaffold Cloudflare Workers with Hono, Drizzle ORM, and TypeScript best practices. Use this skill when implementing new Workers, adding endpoints, or setting up database schemas.

cloudflare-workershonodrizzle-ormtypescript
littlebearapps
littlebearapps
0

scale

Recommend sharding, caching strategies, and read-replication patterns for Cloudflare architectures. Use this skill when preparing for growth, hitting limits, or optimizing for high traffic.

database-shardingcaching-strategyread-replicationcloudflare
littlebearapps
littlebearapps
0

zero-trust

Identify and remediate Zero Trust security gaps in Cloudflare deployments. Use this skill when auditing Access policies, checking staging/dev environment protection, detecting unprotected admin routes, or implementing mTLS and service tokens for machine-to-machine auth.

zero-trustcloudflareaccess-controlmTLS
littlebearapps
littlebearapps
0

optimize-costs

Analyze Cloudflare architecture and predict monthly costs with optimization recommendations. Use this skill when the user asks about costs, billing, pricing, or wants to understand their Cloudflare spend. Works with wrangler configs, observability data, and AI Gateway logs.

cost-optimizationcloudflarebillingpricing
littlebearapps
littlebearapps
0

rate-regime-adjustment

|

rate-adjustmentfinancial-regulationpolicy-managementpricing
colinalexander
colinalexander
0

ffuf-web-fuzzing

Expert guidance for ffuf web fuzzing during penetration testing, including authenticated fuzzing with raw requests, auto-calibration, and result analysis

ffufweb-fuzzingpenetration-testingauthenticated-fuzzing
prof-ramos
prof-ramos
0

feature-planning

Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.

feature-specificationtask-decompositionimplementation-planfeature-prioritization
prof-ramos
prof-ramos
0

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

branch-managementmerge-strategypull-requestcode-cleanup
prof-ramos
prof-ramos
0

file-operations

Analyze files and get detailed metadata including size, line counts, modification times, and content statistics. Use when users request file information, statistics, or analysis without modifying files.

metadatafile-analysisfile-statisticsread-only
prof-ramos
prof-ramos
0

Page 381 of 397 · 19837 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.