Agent Workflow Claude Skills
4 121 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 845 tokens or less — that is what one costs your context window when the agent loads it. 778 ship runnable scripts rather than instructions alone. 5 of them cannot work without an MCP server, most often task. We also found 541 copies of these same skills sitting in other people's repositories — counted once here, not 541 times.
4 121 unique 665 authors 2 767 updated this month 506 from vendors
Five-phase umbrella playbook for an initiative shepherd. Dispatches to phase-deep skills (Research, PoC, Scoping, Implementation) at the right moment.
Reviews Claude configuration files for security, structure, and prompt engineering quality. Use when reviewing changes to CLAUDE.md files (project-level or .claude/), skills (SKILL.md), agents, prompts, commands, or settings. Validates YAML frontmatter, progressive disclosure patterns, token efficiency, and security best practices. Detects critical issues like committed settings.local.json, hardcoded secrets, malformed YAML, broken file references, oversized skill files, and insecure agent tool access.
Locates, lists, filters, and extracts structured data from Claude Code native session logs. Supports both single and multiple session analysis.
Performs comprehensive analysis of Claude Code sessions, examining git history, conversation logs, code changes, and gathering user feedback to generate actionable retrospective reports with insights for continuous improvement.
Bootstrap agentic development environment from agent.toml manifest
Bootstrap, maintain, and evolve context networks across their full lifecycle. Use when starting a new project, when existing documentation feels scattered, or when agent effectiveness degrades due to missing context.
Integrate installed skill usage guidance into project CLAUDE.md/AGENTS.md based on project context. Use when skills are installed but agents don't know when to use them, when setting up a new project with skills, or when updating guidance after adding skills.
Build new agent skills. Use when creating diagnostic frameworks, CLI tools, or data-driven generators that follow the established skill patterns.
Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers. This skill should be used when creating Mastra agents, defining tools with Zod schemas, building workflows with step data flow, setting up Hono API servers with Mastra adapters, or implementing agent networks. Keywords: mastra, hono, agent, tool, workflow, AI, LLM, typescript, API, MCP.
Orchestrate multiple worker agents to implement groomed tasks. Use when multiple ready tasks need implementation, when you want autonomous multi-task execution, or when coordinating batch development work. Keywords: coordinator, orchestrator, multi-task, parallel, workers, batch, autonomous.
Orchestrate multiple worker agents to implement groomed tasks in Gitea repositories. Use when multiple ready tasks need implementation, when you want autonomous multi-task execution, or when coordinating batch development work with Gitea. Keywords: coordinator, orchestrator, multi-task, parallel, workers, batch, autonomous, gitea, tea.
Guide AI agents through Godot 4.x GDScript coding best practices including scene organization, signals, resources, state machines, and performance optimization. This skill should be used when generating GDScript code, creating Godot scenes, designing game architecture, implementing state machines, object pooling, save/load systems, or when the user asks about Godot patterns, node structure, or GDScript standards. Keywords: godot, gdscript, game development, signals, resources, scenes, nodes, state machine, object pooling, save system, autoload, export, type hints.
> Optimize Claude Code sessions for Max-plan usage limits. Use when users ask about token/context savings, CLAUDE.md compression, noisy tool output, quota burn, drift protection, retry loops, broad coding tasks, or planning before implementation.
通过 reasoning_effort、Magic String、组合推理题和离线日期题快速检测当前 API 是否为真实 Claude 模型，并在需要时升级到身份、工具、元数据与嵌套层级的深度审查。用于怀疑模型真假、来源异常、被第三方包装，或需要输出模型真实性检测报告时。
Analyze all failures in a convex-evals run, spawning parallel sub-agents to investigate each failure and producing a report with classifications and recommendations. Use when the user asks to analyze an entire run, review all failures in a run, or wants to understand why a model scored poorly.
Define agent tools using the fail-closed design pattern — unified name/schema/security/execution in one class, with three-layer execution (validate → permission → call). Use this skill whenever the user wants to define a new agent tool, add permission or validation logic to an existing tool, or asks about 'build a tool', '定义一个工具', 'create a tool for X', '工具定义'. Framework-agnostic: works with hermes-agent, LangChain, or any Python agent framework.
Restructures a chaotic or overgrown MEMORY.md into a clean 2-layer architecture based on how Claude Code's autoDream system organizes memory — a lightweight pointer index (always loaded) and topic files (loaded on demand). Stale or superseded memories are deleted or corrected in place — not archived. Use this skill whenever the user says \"clean up MEMORY.md\", \"reorganize my memory files\", \"MEMORY.md is getting too long\", \"fix my memory structure\", or when you observe that MEMORY.md exceeds 200 lines, contains full paragraphs instead of pointers, or mixes index entries with topic content.
| Harness Engineering 第一阶段：扫描现有项目，生成 AGENTS.md（目录文件）和完整的 docs/ 知识库结构。 当用户想要"为项目添加 agent 支持"、"让 AI 更好地理解我的项目"、"开始 harness engineering"、 "创建 AGENTS.md"、"搭建 agent 文档结构"、"让 Claude Code 更好地工作"时，立即使用此 skill。 也适用于用户说"帮我把项目文档整理好给 agent 用"、"我想开始用 AI agent 开发"、 "梳理这个项目能解决什么业务问题"或要求建立 business-solution.md 等场景。
Developer implementation guide for building hierarchical (folded) memory into an Agent. Three-layer architecture where recent turns stay detailed, older content compresses into episodes, and the oldest distills into durable semantic facts. Use when compact-memory-implementation is not retaining enough, or when agents need to recall decisions from many sessions ago.
| Harness Engineering 第一阶段第二步：深度分析项目代码，填充业务解决方案、架构、约定、技术决策和质量标准等 docs/ 知识库内容。 在 harness-step1-create-agents-md 创建好目录骨架之后使用。当用户说"填充文档内容"、 "完善 docs/ 文件"、"让文档有实质内容"、"分析项目写架构文档"、"写 ARCHITECTURE.md"、 "写技术决策文档"、"从业务视角理解项目"、"完善 business-solution.md"时，立即使用此 skill。 前置条件：项目中已有 AGENTS.md 和 docs/ 目录骨架（由 harness-step1 创建）。
| Harness Engineering 第二阶段：建立跨 session 状态管理，解决 agent 每次对话失忆的问题。 创建 tasks.json（任务清单）、progress.md（进度记录）、init.sh（环境初始化脚本）三个文件。 当用户说"建立任务管理"、"让 agent 记住进度"、"创建 tasks.json"、"跨 session 保持状态"、 "agent 每次都不记得上次做了什么"、"建立 progress 文件"、"初始化状态管理"时，立即使用此 skill。 前置条件：harness-step1 和 harness-step2 已完成（项目有 AGENTS.md 和 docs/ 知识库）。
Build LangChain (Python) tools using Claude Code's fail-closed design pattern — unified name/schema/security/execution in one class, with automatic three-layer execution (validate → permission → call). Use this skill whenever the user wants to define a new LangChain tool, add permission or validation logic to an existing tool, set up the ClaudeStyleTool base class in a project, or asks about "build_tool", "Claude Code style tool", "工具定义", or "langchain tool with permissions". Also trigger when the user says "create a tool for X" or "定义一个工具" in a LangChain Python project context, even without mentioning Claude Code explicitly.
Implement a production-ready LLM query loop / agent loop for AI applications. Use this skill whenever the user wants to add tool calling, ReAct-style reasoning-action-observation cycles, function calling loops, query engines, agent runtimes, tool_result feedback, max-turn exits, or Claude Code-like Agent Loop behavior to their own product or codebase.
End-of-session memory distillation — extracts key decisions, eliminated approaches, new discoveries, and current blockers from the current conversation and writes them to MEMORY.md topic files. Based on Claude Code's autoDream background consolidation service. Activate when the user says "dream", "/dream", "save session memories", "distill this session", "what should I remember from this session", or when a long productive session is ending and the user wants to preserve what was learned.
Design and implement a layered, configurable permission/safety system for agent tools. Use this skill when building an agent that needs to control which tool calls are auto-allowed, which require user confirmation, and which are denied — especially when the system must be configurable across multiple scopes (project/user/enterprise) and extensible via hooks. Triggers on: "权限系统", "工具安全", "tool permission", "permission system", "tool safety", "allow/deny rules", "hook system", "构建安全机制".
Use when executing an approved Krypton plan, GOAL.md, or implementation plan that already defines intent, ownership, contract, cutover, task boundaries, and acceptance evidence. Use for main-agent execution with explorer, plan-reviewer, reviewer, maintainer, or verifier gates.
Set up, harden, audit, or explain a Linux VPS as a Codex App SSH host for Krypton-style agent workflows. Use when the user wants to move Codex or Claude Code work from a local Mac to a VPS, connect Codex App to an SSH host, configure Ubuntu 24.04/devbox tools, clone a repo remotely, run Codex/Claude/tmux/cmux on the VPS, forward ports for localhost testing, or create repeatable founder/builder setup instructions with proof checks.
Use when refactoring a user-level or project-level AGENTS.md for progressive disclosure
Run Claude Code (Anthropic) from this host via the `claude` CLI (Agent SDK) in headless mode (`-p`) for codebase analysis, refactors, test fixing, and structured output. Use when the user asks to use Claude Code, run `claude -p`, use Plan Mode, auto-approve tools with --allowedTools, generate JSON output, or integrate Claude Code into Clawdbot workflows/cron.
Template and guide for creating skills. Demonstrates the standard skill structure with resources, docs, examples, and templates directories. Use this as a reference when building new protocol integrations.
Real-time smart money analytics API for Polymarket prediction markets, Hyperliquid perpetual futures, and Meteora Solana LP/AMM pools. 63 endpoints. Pay-per-request via x402 on Solana Mainnet USDC. No API keys.
Comprehensive guide for building AI agents that interact with Solana blockchain using SendAI's Solana Agent Kit. Covers 60+ actions, LangChain/Vercel AI integration, MCP server setup, and autonomous agent patterns.
Help developers integrate Chainlink Data Feeds into smart contracts and applications. Use for price feed integration, feed address lookup, consumer contract generation, multi-chain data feeds (EVM, Solana, Aptos, StarkNet, Tron), MVR bundle feeds, SVR/OEV feeds, feed monitoring, historical data, L2 sequencer checks, rates/volatility feeds, SmartData/RWA feeds, or debugging feed integrations. Trigger on any mention of Chainlink price feeds, oracle data, AggregatorV3Interface, latestRoundData, or feed addresses.
Handle Chainlink CCIP requests including read-only route, token, message-status, and lane lookups; fee-estimation guidance; user-run cross-chain transfer and messaging artifacts; sender and receiver contract development; and CCT setup guidance. The skill never signs or broadcasts transactions. Use whenever the user mentions CCIP, Chainlink cross-chain messaging, CCIP token transfers, CCTs, or CCIP monitoring.
Help developers integrate Chainlink VRF into smart contracts. Use for consumer contract generation with VRFConsumerBaseV2Plus, subscription setup and funding (LINK or native), keyHash and gas lane selection, coordinator address lookup and debugging VRF integrations. Trigger on any mention of VRF, verifiable randomness, on-chain random number generation, requestRandomWords, fulfillRandomWords, VRF subscription, VRF coordinator, keyHash, or provably fair randomness in a smart contract, even if the user does not say 'VRF' explicitly.
How to use Colin to compile agent skills from live sources. Use when working with Colin projects, templates, compilation, or skill management.
Use when the user invokes `/pr-precheck <repo> <topic>` or — implicitly, before any other skill opens a pull request — to check the target repo's merged and closed PR history for prior attempts at the same fix, so the agent doesn't open the Nth duplicate of an already-rejected approach. Wraps the `vouch pr-cache` CLI (build / check / show) and turns its verdict into a clear stop / ask / proceed signal.
Use this skill when you need to QA audit and fix a plugin skill file. Provides a methodology for verifying skill content against official documentation, fixing issues in-place, and producing verification reports.
Use for GEPA optimize_anything on text artifacts such as code, prompts, agent architectures, configs, and non-DSPy optimization targets.
Use when a Hermes profile must be audited for role clarity, authority boundaries, configuration fit, skills, memory posture, credential scope, handoffs, and recurring operational failures.
Use when installed Hermes skills must be audited for overlap, staleness, broken references, usage-integrity problems, and dead weight without changing the installation.
Use when Hermes token usage, cost attribution, runaway sessions, cron consumption, or billing discrepancies must be investigated using privacy-preserving, schema-aware evidence.
Use when a user asks whether an identified repository is ready for further development, release work, a new feature, handoff, or a new contributor, requiring a disciplined read-only audit before an evidence-backed verdict.
Use when an open-source developer tool, package, CLI, agent, or MCP server must be evaluated for legitimacy, supply-chain risk, telemetry, dangerous capabilities, claim accuracy, and adoption fit.
| Record and query AI conversation logs — what users asked, how it was solved, and the result. Use when users want to logging conversation, summarize recent work from sessions, or want daily/weekly project summaries from past conversations.
>- Analyzes observability signals from customer GenAI applications with DQL. Reads OpenTelemetry GenAI spans and LLM evaluation bizevents. (model, provider, tokens); cost/token analytics, usage attribution, and prompt caching; agent signals (tool calls, steps, failures, loop detection, Smartscape topology); conversation/session analytics; guardrails (blocked/truncated responses); and evaluation signals (quality, pass/fail). "cost per conversation", "who is driving token spend", "do I have prompt caching", "failing agent tool calls", "find runaway agents", "responses truncated or blocked", "failed evaluations", "am I hitting rate limits", "token throughput / TPM", "provider throttling or 429s". metrics (dt-obs-services), logs (dt-obs-logs), or non-GenAI tracing (dt-obs-tracing).
Create new Agent Skills following the agentskills.io specification. Use when the user wants to create, scaffold, or design a new skill for AI agents. Handles SKILL.md generation, directory structure setup, and validation.
> It is a specification for semantic workflows used by agents to plan, generate, formalize, summarize, and execute complex tasks, projects, experiments,and research efforts for agents, requiring explicit structure, lazy loading,scoped context, evidence-grounded routing, and human review at critical checkpoints. USE WHEN the user asks for a complex task, project, experiment, or research effort that needs to be carefully planned before execution USE WHEN the user provides a text-based plan and wants it to be made more detailed and formalized according to this specification. USE WHEN the user asks to summarize ongoing or completed work into a reusable workflow manifest. USE WHEN the user specifies the location of an existing agent workflow and wants it loaded and executed according to the specification.