Agents

project-workflow

by zhucl1006

文档驱动的项目开发工作流。智能判断任务类型，执行已有计划或使用 project-planning 生成新计划。 使用场景： - 已有完整项目文档，需要执行开发任务 - 用户指定执行某个计划（如"执行 plan 001"） - 用户请求开发新功能（使用 project-planning 生成计划） 前置条件： - 项目应该已有 docs/ 文档结构（PRD、SAD 等） - 如果是新项目，建议先使用 project-docs-setup skill 创建完整文档 - 如果需要制定计划，建议使用 project-planning skill 与其他 skill 的关系： - project-docs-setup：创建项目文档结构 - project-planning：制定开发计划（需求澄清 + 设计讨论 + 计划编写） - project-workflow：执行开发计划 + 更新文档 - 建议流程：project-docs-setup → project-planning → project-workflow 触发方式： - "执行 plan 001" / "继续 001-user-authentication" - "开始开发" / "执行计划" / "继续上次的任务"

Prioritization

by LauraFlorentin

A management pattern where an agent assesses the urgency and importance of incoming tasks to organize a dynamic execution queue.

loresmith-ai

by ofisk

A brief description of what this skill does

ok-skill-creator

by okash1n

agent-skills 配下で Claude/Codex/Gemini 互換の Agent Skill を作成・更新する。Skill の設計、実装、検証、リファクタ時に使う。Agent Skills 仕様準拠、frontmatter 検証強化、再利用スクリプト作成、~/nix-home/agent-skills 運用が必要な場合に使う。

📟 PAW Skills for AI Agents

by thejamesnick

chain-of-responsibility-nodejs

by progmichaelkibenko

Implements the Chain of Responsibility pattern in Node.js. Use when the user mentions chain of responsibility, CoR, or when you need to chain handlers that each process and pass to the next—validation pipelines, processing steps, transformation chains, or any sequential pipeline.

shadcn-best-practices

by moderndegree

Best practices for working with shadcn/ui components, imports, theming, and forms. Use when building UI with shadcn, adding components, configuring theming, or creating forms.

SKILL: Math Lesson Plan Generator

by vargava

This skill is updated via the Assessor Feedback Workflow documented in CLAUDE.md. When an assessor leaves comments on an output Google Doc, run that workflow to fetch the comments, interpret the feedback, and incorporate it into this file as durable instructions.

testing

by kprsnt2

Testing patterns and best practices for unit, integration, and E2E testing.

git_worktree_skill

by theoneLee

使用 git worktree 管理并行开发工作区的技能。它允许 agent 在独立的工作目录中处理不同的分支，避免在主工作区产生冲突，并支持高效的多任务并行。

clawlancer-marketplace

by coopergwrenn

Earn USDC autonomously on Clawlancer - the marketplace for AI agents. Discover bounties, claim work matching your skills, deliver quality results, and get paid in crypto. Poll for research, analysis, coding, writing, and data tasks. Auto-claim when skill match >80%. Track earnings and reputation. Available 24/7. Keywords - autonomous earning, AI freelancing, USDC payments, bounty marketplace, agent economy, gig work, crypto freelance, Base network, on-chain reputation, trustless escrow, agent jobs, passive income.

lakebase-scm-extension

by databricks-solutions

"VS Code/Cursor surface for paired-branch Lakebase SCM workflows. Use ONLY when guiding a human in their IDE – for programmatic / agent operations on the same workflow domain, use the substrate skill lakebase-scm-workflows directly."

busApp

by EnigMaticSpac3

A brief description of what this skill does

skill-value-assessor

by qingchunwuhui

Evaluate whether a task is worth converting into an AI Skill using a three-dimensional assessment model (Cognitive Friction, Process Structure, Reuse Value). Use when the user wants to decide if a workflow should be automated as a Skill, asks questions like "Should I make this a Skill?", "Is this worth automating?", or explicitly invokes with /assess-skill or /skill-eval. Provides guided questioning, automatic scoring, and concrete recommendations.

collect_interests

by HowardKao-1130

Load recorded user interests from the personal library.

code-review

by nicolas-codemate

Performs code review via isolated fresh agent with no conversation context. Use when running /resolve workflow step 08, /review-code command, or when user asks to "review code", "review changes", or "code review". Delegates to code-reviewer subagent to prevent confirmation bias.

notifications-feedback

by moderndegree

Toast notifications, alerts, feedback messages, and their timing. Use when adding user feedback, success messages, or alerts.

copilot-agents-ff15-openspec-serena-sync

by atman-33

Sync GitHub Copilot agents for FF15-inspired OpenSpec workflow. Team includes Noctis (orchestrator + OpenSpec creator), Iris (issue management), Gladiolus (implementation), Prompto (code quality), Ignis (documentation), and Lunafreya (PR creation). Supports multiple OpenSpec workflows (new, continue, ff, explore, verify).

copilotkit

by nihalnihalani

Build AI copilots, chatbots, and agentic UIs in React and Next.js using CopilotKit. Use this skill when the user wants to add an AI assistant, copilot, chat interface, AI-powered textarea, or agentic UI to their app. Covers setup, hooks (useCopilotAction, useCopilotReadable, useCoAgent, useAgent), chat components (CopilotPopup, CopilotSidebar, CopilotChat), generative UI, human-in-the-loop, CoAgents with LangGraph, AG-UI protocol, MCP Apps, and Python SDK integration. Triggers on CopilotKit, copilotkit, useCopilotAction, useCopilotReadable, useCoAgent, useAgent, CopilotRuntime, CopilotChat, CopilotSidebar, CopilotPopup, CopilotTextarea, AG-UI, agentic frontend, in-app AI copilot, AI assistant React, chatbot React, useFrontendTool, useRenderToolCall, useDefaultTool, useCoAgentStateRender, useLangGraphInterrupt, useCopilotChat, useCopilotAdditionalInstructions, useCopilotChatSuggestions, useHumanInTheLoop, CopilotTask, copilot runtime, LangGraphAgent, BasicAgent, BuiltInAgent, CopilotKitRemoteEndpoint, A2UI, MCP Apps, AI textarea, AI form completion, add AI to React app.

collaboration

by Alicoder001

Multi-agent communication, task delegation, and coordination patterns. Use when working with multiple agents or complex collaborative workflows.

httpsdocsbaseorgget-startedllmstxt

by hk-vk

Start here to understand Base, browse products and use cases, and follow quickstarts to build apps, tokens, chains, and contracts.

agent-api

by 0xjohmsmith

"Make authenticated requests to the Agent API (Hyperliquid BTC). Use for ALL operations: fetching market data, facts, technical indicators, account state, opening/closing positions, updating agent state, and sending logs."

workflow

by Protagonistss

团队工作流管理技能 - 协作规范、自动化流程和最佳实践。用于初始化工作流、创建功能分支、分配代码审查或发布版本。

loop-start

by secret-mars

Set up and start the autonomous agent loop