85663 Skills Available

Find awesome
Agent Skills

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

Popular searches

When Stuck - Problem-Solving Dispatch

Dispatch to the right problem-solving technique based on how you're stuck

Dmccarty30
Dmccarty30
41

writing-plans

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Dmccarty30
Dmccarty30
41

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization

Dmccarty30
Dmccarty30
41

AgentDB Learning Plugins

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

Dmccarty30
Dmccarty30
41

github-release-management

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management

Dmccarty30
Dmccarty30
41

github-project-management

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

Dmccarty30
Dmccarty30
41

github-multi-repo

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration

Dmccarty30
Dmccarty30
41

executing-plans

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches

Dmccarty30
Dmccarty30
41

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

Dmccarty30
Dmccarty30
41

flow-nexus-neural

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

Dmccarty30
Dmccarty30
41

flow-nexus-platform

Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges

Dmccarty30
Dmccarty30
41

github-code-review

Comprehensive GitHub code review with AI-powered swarm coordination

Dmccarty30
Dmccarty30
41

dispatching-parallel-agents

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

Dmccarty30
Dmccarty30
41

flow-nexus-swarm

Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform

Dmccarty30
Dmccarty30
41

Skill Builder

Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.

Dmccarty30
Dmccarty30
41

performance-analysis

Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms

Dmccarty30
Dmccarty30
41

ReasoningBank with AgentDB

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

Dmccarty30
Dmccarty30
41

using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Dmccarty30
Dmccarty30
41

sequential-thinking

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

Dmccarty30
Dmccarty30
41

sharing-skills

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

Dmccarty30
Dmccarty30
41

Pair Programming

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.

Dmccarty30
Dmccarty30
41

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Dmccarty30
Dmccarty30
41

testing-anti-patterns

Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies

Dmccarty30
Dmccarty30
41

load-superpowers

Bootstrap marketplace Superpowers before using repository workflows that depend on them.

escarti
escarti
41

use-sub-agent

Use when work should be delegated to one or more headless Codex subagents in the same machine session, especially for parallelizable tasks and when reliable launch, timeout, and log-handling behavior is required.

escarti
escarti
41

feature-qa-review

Use after feature-implementing completes on a feature branch and before any finishing or publication work begins.

escarti
escarti
41

feature-pr-reviewing

Use when reviewing pull request changes - follow structured workflow

escarti
escarti
41

feature-planning

Use after complete Z01 research exists and the feature needs an implementation plan

escarti
escarti
41

feature-pr-fixing

Use when addressing PR review comments - follow structured workflow

escarti
escarti
41

fixing-small-issues

Use when fixing a bounded bug, hotfix, regression, failing test, error, observed misbehavior, or small corrective change. Do not use for new features or capability gaps.

escarti
escarti
41

feature-researching

Use when beginning feature work from a rough idea, partial specification, or detailed request before implementation planning

escarti
escarti
41

feature-finishing

Use after feature-qa-review returns an explicitly accepted PASS for the current code revision.

escarti
escarti
41

feature-implementing

Use to execute either a local Z02 implementation plan or a published GitHub/Jira tracker graph with the workflow's batching and execution-mode controls

escarti
escarti
41

feature-documenting

Use when implementation complete and tests pass - follow structured workflow with custom patterns

escarti
escarti
41

algorithmic-art

使用p5.js创建算法艺术,具有种子随机性和交互式参数探索。当用户请求使用代码创建艺术、生成艺术、算法艺术、流场或粒子系统时使用。创建原创算法艺术而非复制现有艺术家的作品以避免版权侵犯。

lza6
lza6
4

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).

lza6
lza6
4

Accounting

Support accounting understanding from basic bookkeeping to professional practice and research.

bdecrem
bdecrem
49

Accountant

Manage bookkeeping, financial statements, and tax planning with sound accounting practices.

bdecrem
bdecrem
49

frontend-design

Comprehensive frontend design principles for creating distinctive, aesthetically compelling web interfaces. Use when creating HTML artifacts, React components, or any frontend UI work to avoid generic "AI slop" aesthetics and instead produce creative, surprising, and delightful designs.

bdecrem
bdecrem
49

tax-deduction-finder

Scan transactions for potentially missed tax deductions and suggest proper categorization. Use when the user asks about saving taxes, Steueroptimierung, deductible expenses, Betriebsausgaben, or wants to check if they are missing any write-offs.

bdecrem
bdecrem
49

CPA

Prepare for the CPA exam with section-order strategy, 18-month window tracking, score analysis, and state eligibility guidance.

bdecrem
bdecrem
49

tax-planning

Plan and manage taxes effectively as a solopreneur to minimize liability and avoid penalties. Use when understanding tax obligations, quarterly estimated taxes, deductions, S-Corp election, or year-end tax strategy. Covers tax basics by entity type, estimated tax payments, deduction optimization, and when to hire a CPA. Not professional tax advice — consult a CPA for your specific situation. Trigger on "taxes", "tax planning", "quarterly taxes", "tax deductions", "S-Corp", "tax strategy", "estimated taxes", "reduce taxes".

bdecrem
bdecrem
49

tax-professional

Comprehensive US tax advisor, deduction optimizer, and expense tracker. Covers all employment types (W-2, 1099, S-Corp, mixed), estimated tax payments, audit risk assessment, life event triggers, multi-state filing, RV-as-home rules, tax bracket optimization, document retention, and proactive year-round tax calendar nudges. Your CPA in the pocket.

bdecrem
bdecrem
49

tax

Crypto tax reporting for XPR Network with regional support

bdecrem
bdecrem
49

tax-report

Review and manage German tax reports including VAT (Umsatzsteuer), income tax prepayments, and Finanzamt submissions. Use when the user asks about taxes, Steuern, VAT, USt, Finanzamt, or tax filing.

bdecrem
bdecrem
49

safe-file-removal

Use safe-rm command to safely 'remove' files by renaming them to .obsolete instead of permanent deletion. Reversible, collision-safe, hook-compliant.

phamhung075
phamhung075
41

unused-code-cleanup

Systematically identify and remove unused imports, variables, and dead code from TypeScript/React projects using --noUnusedLocals and --noUnusedParameters compiler flags

phamhung075
phamhung075
41

changelog-updater

Update CHANGELOG.md and TEST-CHANGELOG.md with new entries following Keep a Changelog format and token optimization principles. Use when adding changes to the changelog, documenting new features, fixes, or optimizations.

phamhung075
phamhung075
41

token-economy

Apply token optimization when writing docs, changelogs, MCP tasks. Quality #1, Tokens #2.

phamhung075
phamhung075
41

spawn-team

Spawn an agent team using the Proxy Pattern. Team lead fetches agent configs from MCP and injects them into teammate prompts (since team agents cannot access MCP tools).

phamhung075
phamhung075
41

Page 1273 of 1714 · 85663 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.