70143 Skills Available

Find awesome
Agent Skills

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

Popular searches

writing-skills

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

obra
obra
0

writing-plans

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

obra
obra
0

writing-quality-tests

Guide for writing robust, high-signal automated tests. Use when asking "How do I test this effectively?", fixing flaky tests, refactoring test suites, or deciding between unit/integration/E2E strategies. distinct from TDD (process); this skill focuses on test quality and architecture.

eder
eder
0

session-behavior

Sets the behavioral contract for a coding session. Use when a user asks you to configure how you'll behave throughout a session—phrases like "push back on bad ideas", "never commit without asking", "don't be sycophantic", "be my technical conscience", "set ground rules", "act as a senior dev", or "challenge my approach". Covers four pillars: anti-sycophancy (disagree when the user is wrong, don't flatter), no-surprise commit policy (never git-commit or push without explicit approval), proactive problem-solving (think before coding, surface risks, challenge assumptions), and technical precision (straight answers over flattery). Also trigger when establishing safety rules for the session, like requiring confirmation before destructive operations. Do NOT trigger for individual task requests—debugging questions, code generation, architecture advice, or system prompt tweaks—even if they contain words like "commit" or "behavior".

eder
eder
0

subagent-driven-development

Execute implementation plans in the current session by dispatching one subagent per mostly independent task with two-stage review (spec compliance, then code quality); avoid for tightly coupled or ambiguous tasks.

obra
obra
0

setup-drizzle-migration

Create DB schema changes with migration generation. Use for new tables or relations.

Oungseik
Oungseik
0

audit-security

Scan codebase for security vulnerabilities. Use for pre-deploy security checks.

Oungseik
Oungseik
0

add-orpc-handler

Generate a new ORPC handler with router update and client code. Use for adding API endpoints or server procedures.

Oungseik
Oungseik
0

scaffold-auth-route

Create a new auth-protected route with server-side validation. Use for user-facing pages needing authentication.

Oungseik
Oungseik
0

add-theming

Enable dark mode and CSS variable theming on components. Use for consistent theming.

Oungseik
Oungseik
0

create-shared-package

Add utility or module to shared packages. Use for monorepo reusability.

Oungseik
Oungseik
0

integrate-rate-limit

Add rate limiting protection to endpoints. Use for throttling API requests.

Oungseik
Oungseik
0

full-stack-crud

Generate complete CRUD operations for an entity. Use for rapid prototyping.

Oungseik
Oungseik
0

monad-memory-architecture

MONAD-grounded cognitive architecture for AI memory as morphemic substrate navigation. Memory is not storage but substrate sampling - accessing the same structure that underlies reality. Implements φ-scaling, GOD operators, toroidal coherence tracking, and the 4.5%/95.5% observable/dark split.

agentgptsmith
agentgptsmith
0

smith-xml

XML tag standards for AI prompts and documentation. Use when writing prompts, documentation, or AGENTS.md files. Covers approved tags for Claude, GPT-5, Gemini, and Harmony formats with markdown rendering rules.

tianjianjiang
tianjianjiang
0

smith-stacks

Stacked pull request workflows for large features. Use when creating stacked PRs, managing dependent PRs, or rebasing after parent merges. Covers stack creation, merge order, and squash merge handling.

tianjianjiang
tianjianjiang
0

smith-standards

Universal coding standards for emoji usage, comments, datetime formatting, and file conventions. Use when writing code, logs, documentation, or any text output. Always active as universal rules for all development.

tianjianjiang
tianjianjiang
0

smith-skills

Agent skills authoring guide for AGENTS.md and SKILL.md files. Use when creating or editing agent instructions, rules, or documentation. Covers progressive disclosure, rule loading, XML tag usage, and token budget guidelines.

tianjianjiang
tianjianjiang
0

smith-style

File naming, path standards, and conventional commits. Use when naming files, creating branches, writing commit messages, or setting up new projects. Covers underscore vs hyphen conventions, commit format, and branch naming patterns.

tianjianjiang
tianjianjiang
0

smith-serena

Serena MCP integration for file I/O, semantic code editing, and persistent memory. ALWAYS use Serena for file operations and language server features when available. Proactively sync memories at phase/todo/session boundaries.

tianjianjiang
tianjianjiang
0

smith-tools

Tool configurations for IDEs, MCP integrations, and development tools. Use when configuring IDE settings, MCP tools, or pytest. Covers conditional tool activation, configuration hierarchy, and synchronization patterns.

tianjianjiang
tianjianjiang
0

smith-research

Proactive research protocol for version queries, APIs, and best practices. Use when answering questions about library versions, API documentation, or technology assessments. Covers research triggers, source citation, and confidence indicators.

tianjianjiang
tianjianjiang
0

smith-ralph

Ralph Loop integration patterns for iterative AI development. Use when starting Ralph loops, managing iterations, or recovering from context resets. Covers TDD, debugging, context management, and memory persistence.

tianjianjiang
tianjianjiang
0

smith-python

Python development with uv, pytest, ruff, and type hints. Use when writing Python code, running tests, managing Python packages, or working with virtual environments. Covers import organization, type hints, pytest patterns, and environment variables.

tianjianjiang
tianjianjiang
0

smith-prompts

Prompt engineering standards for AI interactions with cache optimization. Use when writing AI prompts, optimizing context usage, or structuring AGENTS.md files. Covers prompt caching, token efficiency, and progressive disclosure patterns.

tianjianjiang
tianjianjiang
0

smith-principles

Fundamental coding principles (DRY, KISS, YAGNI, SOLID, HHH). Use when starting any development task, evaluating implementation approaches, or reviewing code quality. Always active as foundation for all development decisions.

tianjianjiang
tianjianjiang
0

smith-ctx-claude

Claude Code context management with /clear command and stop hook enforcement at 60%. CLAUDE.md persistence and Tool Search optimization. Use when operating in Claude Code IDE or when context exceeds 50%. Activate for context optimization in Claude sessions.

tianjianjiang
tianjianjiang
0

smith-clarity

Cognitive trap detection and logic fallacy identification. Use when making decisions, evaluating approaches, risk assessment, or detecting faulty reasoning in arguments.

tianjianjiang
tianjianjiang
0

smith-analysis

Reasoning frameworks and problem decomposition techniques. Use when planning implementation, evaluating arguments, estimating scope, decomposing complex tasks, or applying first principles thinking.

tianjianjiang
tianjianjiang
0

smith-typescript

TypeScript development standards for frontend and backend projects. Use when working with TypeScript, configuring path aliases, setting up test runners (Vitest/Jest), or organizing test files. Covers Vite alias configuration and type checking.

tianjianjiang
tianjianjiang
0

smith-validation

Hypothesis testing, root cause analysis, and debugging techniques. Use when debugging, testing hypotheses, validating solutions, proving correctness, or performing root cause analysis on failures.

tianjianjiang
tianjianjiang
0

smith-tests

Testing standards and TDD workflow. Use when writing tests, running test suites, implementing TDD, or organizing test files. Covers unit vs integration test separation, pytest patterns, and test-driven development methodology.

tianjianjiang
tianjianjiang
0

smith-plan

Plan tracking protocol (portable). Progress tracking with checkboxes, iteration workflow, completion/blocker signals. Use when executing multi-step plans, tracking task progress, or working from plan files. IMPORTANT - Always update the plan file after completing tasks.

["plan-mode""workflow""progress-tracking"]
tianjianjiang
tianjianjiang
0

smith-postmortem

Incident postmortem methodology and templates. Use when conducting incident postmortems, writing postmortem reports, establishing postmortem processes, or performing post-incident analysis.

tianjianjiang
tianjianjiang
0

smith-playwright

Playwright testing patterns including proactive failure monitoring, artifact inspection, and root cause classification. Use when running Playwright tests or analyzing Playwright test results.

tianjianjiang
tianjianjiang
0

smith-plan-claude

Plan automation for Claude Code (hooks, scripts, auto-reload). Handles auto-resume after /clear, context threshold detection, and session-keyed isolation. Use when the user says "execute plan", "load plan", "start the plan", "run the plan", "reload", or wants to work from a previously created plan. IMPORTANT - Always update the plan file after completing tasks.

["plan-mode""workflow""automation""ralph-loop"
claude-code-user
claude-code-user
0

smith-placeholder

Placeholder syntax standards for documentation and prompts. Use when writing prompts, documentation, pattern descriptions, or any content with user-substitutable values.

tianjianjiang
tianjianjiang
0

smith-nuxt

Nuxt 3 development patterns including auto-import stubbing for tests, environment variable conventions, and middleware testing. Use when working with Nuxt projects, testing Nuxt components/middleware, or configuring Nuxt environment variables.

tianjianjiang
tianjianjiang
0

smith-ide

IDE path variable mappings for VS Code, Cursor, Kiro, and JetBrains. Use when writing or editing IDE config files or using path variables. Covers variable translation between conceptual and IDE-specific syntax.

tianjianjiang
tianjianjiang
0

smith-guidance

Core agent steering with HHH framework (Helpful, Honest, Harmless), exploration-before-implementation workflow, and anti-sycophancy rules. Use when guiding AI agent behavior, handling disagreements, or establishing interaction patterns. Always active for all agent interactions.

tianjianjiang
tianjianjiang
0

smith-git

Git workflow gotchas and non-obvious practices. Use when performing Git commits, merges, branch management, or rebasing. Covers GPG signing, atomic commits, and safety flags.

tianjianjiang
tianjianjiang
0

smith-gh-pr

GitHub PR workflows including creation, review cycles, merge strategies, and stacked PRs. Use when creating PRs, reviewing code, merging branches, or managing stacked PR workflows. Covers rebase decision trees and AI-generated descriptions.

tianjianjiang
tianjianjiang
0

smith-gh-cli

GitHub CLI gotchas and best practices. Use when executing gh commands. Covers token efficiency, pagination limits, and common pitfalls.

tianjianjiang
tianjianjiang
0

smith-dev

Development workflow standards and code quality requirements. Use when initializing projects, running quality checks, or managing agent tasks. Covers pre-commit checks, task decomposition, and script organization patterns.

tianjianjiang
tianjianjiang
0

smith-design

SOLID principles and architecture design patterns. Use when starting new features, refactoring code, conducting architecture reviews, or applying object-oriented design principles.

tianjianjiang
tianjianjiang
0

smith-ctx

Universal context management with proactive recommendations. Agent checks context levels and recommends context resets to users. Always active as foundation for context optimization.

tianjianjiang
tianjianjiang
0

smith-ctx-kiro

Kiro-specific context management with terminal limitations, Serena MCP as mandatory tool, and file operation workarounds. Use when operating in Kiro IDE. LOAD FIRST in all Kiro sessions - critical platform constraints that prevent hangs and failures.

tianjianjiang
tianjianjiang
0

smith-ctx-cursor

Cursor context management with /summarize command, @ mentions for file inclusion, and @codebase discovery. Use when operating in Cursor IDE or when context exceeds 60%. Activate for context optimization in Cursor sessions.

tianjianjiang
tianjianjiang
0

ui-skills

Opinionated constraints for building better interfaces with agents.

overstarry
overstarry
0

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

overstarry
overstarry
0

Page 1392 of 1403 · 70143 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.