80320 Skills Available

Find awesome
Agent Skills

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

Popular searches

executing-plans

Use when you have a written implementation plan to execute

axiomantic
axiomantic
41

using-lsp-tools

Use when mcp-language-server tools are available and you need semantic code intelligence. Triggers: 'find definition', 'find references', 'who calls this', 'rename symbol', 'type hierarchy', 'go to definition', 'where is this used', 'where is this defined', 'what type is this'. Provides navigation, refactoring, and type analysis via LSP.

axiomantic
axiomantic
41

writing-skills

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

axiomantic
axiomantic
41

test-driven-development

Use when user explicitly requests test-driven development, says 'TDD', 'write tests first', 'red green refactor', 'test-first', or 'start with the test'. Also invoked as a sub-skill by implementing-features and executing-plans for each implementation task. NOT a replacement for implementing-features for full feature work.

axiomantic
axiomantic
41

writing-plans

Use when you have a spec, design doc, or requirements and need a detailed step-by-step implementation plan before coding. Triggers: 'write a plan', 'create implementation plan', 'plan this out', 'break this down into steps', 'convert design to tasks', 'implementation order'. Produces TDD-structured task sequences with file paths, code, and verification steps. Usually invoked by implementing-features Phase 3.

axiomantic
axiomantic
41

using-skills

Use when starting any conversation to initialize skill matching, or when unsure which skill applies to a request. Handles skill routing, rationalization prevention, and session initialization. Primarily loaded via session init, not by direct user request.

axiomantic
axiomantic
41

finding-dead-code

>

axiomantic
axiomantic
41

using-git-worktrees

Use when starting feature work that needs isolation from current workspace, setting up parallel development tracks, or before executing implementation plans. Triggers: 'worktree', 'separate branch', 'isolate this work', 'don't mess up current work', 'work on two things at once', 'parallel workstreams', 'sandboxed workspace'.

axiomantic
axiomantic
41

autonomous-roundtable

Meta-orchestrator for Forged autonomous development: decompose projects into features, execute through DISCOVER→DESIGN→PLAN→IMPLEMENT→COMPLETE, convene roundtables, coordinate skills.

axiomantic
axiomantic
41

optimizing-instructions

|

axiomantic
axiomantic
41

auditing-green-mirage

Use when auditing whether tests genuinely catch failures, or when user expresses doubt about test quality. Triggers: 'are these tests real', 'do tests catch bugs', 'tests pass but I don't trust them', 'test quality audit', 'green mirage', 'shallow tests', 'tests always pass suspiciously', 'would this test fail if code was broken'. Forensic analysis of assertions, mock usage, and code path coverage.

axiomantic
axiomantic
41

deep-research

>

axiomantic
axiomantic
41

dehallucination

Verify claims, references, and assertions are grounded in reality. Triggers: 'does this actually exist', 'is this real', 'did you hallucinate', 'verify these references', 'check if this is fabricated', 'reality check', 'ground truth'. Invoked as quality gate by roundtable feedback, Forge workflow, and after deep-research verification.

axiomantic
axiomantic
41

designing-workflows

Use when designing systems with explicit states, transitions, or multi-step flows. Triggers: \"design a workflow\", \"state machine\", \"approval flow\", \"pipeline stages\", \"what states does X have\", \"how does X transition\", or when implementing-features Phase 2.1 detects workflow patterns.

axiomantic
axiomantic
41

assembling-context

Prepare tiered context packages for subagents and manage token budgets. Triggered by 'prepare context for', 'assemble context', 'token budget', or invoked by implementing-features Phase 3.5/4.2.

axiomantic
axiomantic
41

distilling-prs

Use when reviewing PRs to triage, categorize, or summarize changes requiring human attention. Triggers: 'summarize this PR', 'what changed in PR #X', 'triage PR', 'which files need review', 'PR overview', 'categorize changes', or pasting a PR URL. Uses heuristic pattern matching to classify changes by review priority. For deep code analysis, use advanced-code-review instead.

axiomantic
axiomantic
41

documenting-tools

Use when writing MCP tools, API endpoints, CLI commands, or any function that an LLM will invoke. Also use when LLMs misuse tools due to poor descriptions. Triggers: 'document this tool', 'write tool docs', 'MCP tool', 'tool description quality', 'model keeps calling this wrong', 'improve tool description'. For human-facing API docs, standard documentation practices apply instead.

axiomantic
axiomantic
41

merging-worktrees

Use when merging parallel worktrees back together after parallel implementation, combining parallel development tracks, or unifying branches from dispatched parallel agents. Triggers: 'merge worktrees', 'combine parallel branches', 'integrate parallel work', 'all tracks complete', 'bring everything together'.

axiomantic
axiomantic
41

managing-artifacts

Use when generating documents, reports, plans, audits, or when asked where to save files. Triggers on "save report", "write plan", "where should I put", "project-encoded path"

axiomantic
axiomantic
41

isolated-testing

|

axiomantic
axiomantic
41

enforcing-code-quality

|

axiomantic
axiomantic
41

fractal-thinking

|

axiomantic
axiomantic
41

advanced-code-review

Use when performing thorough multi-phase code review with historical context tracking and verification. Triggers: 'thorough review', 'deep review', 'review this branch in detail', 'full code review with report'. 5-phase process: strategic planning, context analysis, deep review, verification, report generation. More heavyweight than code-review; produces detailed artifacts. For quick review, use code-review instead.

axiomantic
axiomantic
41

analyzing-domains

|

axiomantic
axiomantic
41

generating-diagrams

Use when generating flowcharts, diagrams, dependency graphs, or visual representations of processes, relationships, architecture, or state machines. Triggers: 'diagram this', 'flowchart', 'visualize', 'dependency graph', 'ER diagram', 'state machine diagram', 'class diagram', 'sequence diagram', 'map the relationships', 'draw the architecture', 'how does X connect to Y'. NOT for: simple bullet point explanations, runtime monitoring, or text-only documentation.

axiomantic
axiomantic
41

analyzing-skill-usage

Analyze session transcripts to extract skill invocation patterns, score invocations, and produce comparative metrics for skill improvement decisions.

axiomantic
axiomantic
41

reflexion

|

axiomantic
axiomantic
41

resolving-merge-conflicts

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

axiomantic
axiomantic
41

creating-issues-and-pull-requests

Use when creating GitHub pull requests or issues with template compliance. Triggers: 'create a PR', 'open a pull request', 'file an issue', 'create issue', or invoked as delegate from finishing-a-development-branch Option 2. Discovers project templates, populates them from branch context, and creates via reliable gh CLI patterns.

axiomantic
axiomantic
41

code-review

Use when reviewing code. Triggers: 'review my code', 'check my work', 'look over this', 'review PR #X', 'PR comments to address', 'reviewer said', 'address feedback', 'self-review before PR', 'audit this code'. Modes: --self (pre-PR self-review), --feedback (process received review comments), --give (review someone else's code/PR), --audit (deep single-pass analysis). For heavyweight multi-phase analysis, use advanced-code-review instead.

axiomantic
axiomantic
41

gathering-requirements

Use when eliciting or clarifying feature requirements, defining scope, identifying constraints, or capturing user needs. Triggers: 'what are the requirements', 'define the requirements', 'scope this feature', 'user stories', 'acceptance criteria', 'what should this do', 'what problem are we solving', 'what are the constraints'. Also invoked by implementing-features during DISCOVER stage and by the Forged workflow.

axiomantic
axiomantic
41

project-encyclopedia

[DEPRECATED] <ONBOARD> Use on first session in a project, or when user asks for codebase overview. Creates persistent glossary, architecture maps, and decision records to solve agent amnesia.

axiomantic
axiomantic
41

polish-repo

Use when improving project discoverability, attracting users/contributors, or presenting open source work. Triggers: 'write a README', 'improve README', 'get more users', 'get more contributors', 'add badges', 'create a logo', 'set up issue templates', 'audit this project', 'project presence', 'make this discoverable', 'why isn't anyone using this', 'prepare for launch', 'repo presentation', 'open source marketing', 'attract contributors', 'project storefront'. Also triggers on: naming a project, writing taglines, GitHub metadata, community infrastructure, signs of life.

axiomantic
axiomantic
41

deckset-presentation-expert

Expert assistant for creating Deckset presentations with markdown. Helps with slide formatting, headings, lists, images, videos, presenter notes, build steps, themes, and configuration. Use when working with .md presentation files, or when user mentions Deckset, creating slides, presentations, or decks.

doudou1337
doudou1337
4

react-native-component-generator

Generates React Native components with platform-specific code, TypeScript support, and mobile-first patterns. Use when user asks to "create React Native component", "generate RN component", "scaffold mobile component", or "create cross-platform component".

Dexploarer
Dexploarer
42

property-based-test-generator

Generates property-based tests using Hypothesis (Python), fast-check (JavaScript/TypeScript), or QuickCheck (Haskell). Use when user asks to "generate property tests", "create hypothesis tests", "add property-based testing", or "generate fast-check tests".

Dexploarer
Dexploarer
42

visual-regression-test-setup

Sets up visual regression testing using Percy, Chromatic, or Playwright to catch unintended UI changes through screenshot comparison. Use when user asks to "setup visual testing", "add screenshot tests", "prevent visual bugs", or "setup Percy/Chromatic".

Dexploarer
Dexploarer
42

database-query-optimizer

Analyzes and optimizes database queries for PostgreSQL, MySQL, MongoDB with EXPLAIN plans, index suggestions, and N+1 query detection. Use when user asks to "optimize query", "analyze EXPLAIN plan", "fix slow queries", or "suggest database indexes".

Dexploarer
Dexploarer
42

bundle-analyzer

Analyzes JavaScript bundle sizes, identifies large dependencies, and suggests optimizations for webpack, vite, rollup. Use when user asks to "analyze bundle", "optimize bundle size", "reduce bundle", "webpack analysis", or "tree shaking".

Dexploarer
Dexploarer
42

translation-key-extractor

Extracts hardcoded strings from code and converts them to translation keys for i18n. Use when user asks to "extract translations", "find hardcoded strings", "internationalize code", "setup i18n", or "create translation files".

Dexploarer
Dexploarer
42

i18n-setup-wizard

Sets up complete internationalization infrastructure for React, Vue, Next.js, or vanilla JS with framework config, translation files, and language switching. Use when user asks to "setup i18n", "add translations", "multi-language support", or "internationalization setup".

Dexploarer
Dexploarer
42

lighthouse-ci-integrator

Integrates Lighthouse CI for automated performance testing, Core Web Vitals tracking, and regression detection in CI/CD pipelines. Use when user asks to "setup Lighthouse CI", "add performance testing", "monitor Core Web Vitals", or "prevent performance regressions".

Dexploarer
Dexploarer
42

dependency-vulnerability-scanner

Scans dependencies for known vulnerabilities (npm audit, pip-audit, etc.), generates reports, and suggests fixes. Use when user asks to "check vulnerabilities", "security scan", "audit dependencies", "check CVEs", or "vulnerable packages".

Dexploarer
Dexploarer
42

pii-detector

Detects Personally Identifiable Information (PII) in code, logs, databases, and files for GDPR/CCPA compliance. Use when user asks to "detect PII", "find sensitive data", "scan for personal information", "check GDPR compliance", or "find SSN/credit cards".

Dexploarer
Dexploarer
42

image-optimizer

Optimizes images for web performance by converting to modern formats, compressing, and generating responsive sizes. Use when user asks to "optimize images", "compress images", "convert to webp", or mentions image performance.

Dexploarer
Dexploarer
42

security-header-generator

Generates security HTTP headers (CSP, HSTS, CORS, etc.) for web applications to prevent common attacks. Use when user asks to "add security headers", "setup CSP", "configure CORS", "secure headers", or "HSTS setup".

Dexploarer
Dexploarer
42

vue-component-generator

Generates Vue 3 components using Composition API, TypeScript, proper props definition, and best practices. Use when creating Vue components or building Vue UI.

Dexploarer
Dexploarer
42

testing-framework-helper

Generates comprehensive test suites with unit tests, integration tests, and E2E tests for various frameworks (Jest, Pytest, Vitest, etc.). Use when writing tests.

Dexploarer
Dexploarer
42

react-component-generator

Generates React components with TypeScript, hooks, and best practices. Use when user asks to "create React component", "generate component", or "scaffold component".

Dexploarer
Dexploarer
42

nextjs-page-generator

Generates Next.js 13+ pages with App Router, Server Components, Client Components, API routes, and proper data fetching. Use when building Next.js applications.

Dexploarer
Dexploarer
42

Page 1247 of 1607 · 80320 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.