Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Strict discipline for runtime verification in PDCA workflows: the AI performs verification itself in an environment — real preferred over simulated, subject to determinism and safety — and never defaults to a human checklist. Attempt first, resolve a pluggable provider (project script/skill → shared capability skill), and hand off to a human only at a true hard boundary with a stated reason. Use at any workflow verify/check stage (bug fix or feature) to decide WHERE verification runs, WHO runs it, and WHETHER it is sufficient. Referenced by PDCA hosts via frontmatter dependencies. Triggers — 「环境验证」「真实环境验证」「真机验证」「真机测试」「模拟环境验证」「AI 验证」「验证分层」「验证充分性」 / runtime verification, environment verification, real vs simulated. When a check opens a UI, cite a saved non-empty screenshot; non-UI checks do not. Do NOT alias completion-evidence-discipline (evidence freshness) or runtime-evidence-debug (debug instrumentation).
Scaffold Claude Code hooks into a real project after auditing the project structure in detail. Use when a user wants Claude Code hook setup, hook refactors, full hook-event scaffolding, or managed updates to existing .claude hooks. This skill verifies the live official Claude Code hook docs first, audits the target repo, then generates a bash-first hook scaffold with a hooks README, repeatable merge behavior, and coverage for every current hook event. Trigger on: Claude Code hooks, scaffold hooks, hook events, update hooks, hook architecture, .claude/settings.json. Do NOT use for generic Git hooks, Husky-only setup, or non-Claude agents.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
Asks for user feedback after each task or cron job completion and runs a recursive learning flow. If output is good, asks what was good until 10 approvals; if needs improvement, asks why/how/what via multiple choice plus optional examples, uses web search and iterative thinking to resolve, and caps iterations by severity (slight 5, medium 10, severe 20). Keeps feedback non-intrusive. Use when completing discrete tasks or cron jobs for the user.
Search local agent-session history to recover prior decisions, commands, configurations, and context from earlier sessions. Use for cross-session recall when the current task depends on what happened in a previous agent conversation, not for inspecting the current repository or summarizing the current session.
Orchestrates the full Sherpy planning workflow using the Sherpy CLI. Requires the sherpy CLI to be installed. Supports AI, human, and hybrid audience selection for appropriate task detail levels. Replaces the need for 14 individual skill files by loading step-specific instructions on demand via `sherpy prompt`. Detects existing artifacts, shows visual pipeline status, and guides through each step in sequence.
Connect an AI agent to the ShiftCare MCP server and verify the connection works. Use when setting up ShiftCare for the first time, when ShiftCare tools are missing or returning errors, or when the user asks how to connect ShiftCare to their AI assistant.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy
This skill should be used when the user asks to "publish a plugin", "release a plugin", "bump plugin version", "update a Claude Code plugin", "update a Codex plugin", "publish skills", or mentions plugin publishing, plugin release, or skill distribution. Handles synchronized host manifests, changelog and README updates, git workflow, cache refresh, and standalone Agent Skills.
Slack workspace integration: 9 on-demand scripts (post, read, delete, search, stream, react, upload, channels, users) + dual-token support + RTS API search + chat streaming + AI Block Kit + Session Bridge + Claudicle unified launcher (Claude Agent SDK, soul engine, three-tier memory).
Create or improve SOUL.md files for OpenClaw agents. Use when the user wants to design an agent personality, rewrite an existing soul, align SOUL.md with IDENTITY.md, or prepare a soul for publishing on souls.directory with optional frontmatter.
Mandatory only on the task-file path of `spec-loop-plan-task`. Use when an active task file already exists and the next user-facing action would otherwise present that task for evaluation, feedback, review, or implementation approval.
A skill for consulting the Agent tool (subagent). Use when the user says "consult a subagent", "ask a subagent", or "have a subagent review". Sends a prompt to the subagent based on the current conversation context and summarizes the results in a report.
Run Claude Code in autonomous iteration loops until task completion — PRD-based feature development, test coverage improvement, lint fixing, documentation generation, dataset creation, or framework migrations. Uses in-session loop mechanism with specialized templates. Triggers on autonomous loop, iterate until done, run until passing, keep going until, ralph, PRD execution.
Use when orchestrating multi-step workflows with Claude Code's native Task system (TaskCreate, TaskUpdate, TaskGet, TaskList) - lifecycle management, parallel execution, crash recovery, and progress visibility. Not for simple single-step tasks.
A relentless interview that asks every frontier question at once, round by round. The entry point of the main flow — interview until shared understanding, then hand off to /tracer-to-spec. Docs-aware in a codebase (reads/writes CONTEXT.md and ADRs), stateless without one.
Build durable, resumable TypeScript workflows with Vercel Workflow DevKit. Use when creating long-running processes, AI agents, background jobs, multi-step pipelines, webhooks, or event-driven systems. Triggers on "workflow", "durable", "resumable", "use workflow", "use step".
Use when building AI agents with Microsoft Agent Framework (Semantic Kernel + AutoGen unified); when implementing memory or context providers; when threads won't deserialize; when workflow checkpointing fails; when migrating from Semantic Kernel or AutoGen; when seeing ChatAgent or AgentThread errors
This skill should be used when a developer wants to autonomously execute all Traces under a fully-specified Epic or Feature — for example "go", "start building", "implement everything", "run the loop", "execute the feature", "build it all", "kick it off". Requires that the Epic/Feature/Trace tree is fully written before starting. Chains implement → verify → PR → re-aim for every Trace — spine-first within each Feature, parallel across Features — with targeted human-in-the-loop gates for contradictions, ambiguities, and every change to a Trace Plan's scenario set.
Manage Zerion agent tokens and security policies — the primitives for autonomous trading and signing. Create / list / use / revoke agent tokens; create / list / show / delete policies (chain locks, allowlists, transfer/approval gates, expiry). Use whenever the user asks to set up an agent token, configure a policy, or enable autonomous trading. Required by `zerion-trading` and `zerion-sign`.
Academic writing multi-agent orchestrator. TRIGGER when: user is editing .tex files, reviewing thesis/paper chapters, drafting academic content, checking writing quality, or analyzing research positioning. Coordinates specialist agents in parallel for review, research, drafting, polishing, figure work, bibliography auditing, and literature surveys.
Reset your own trajectory when you're stuck, looping, or demoralized — read these affirmations, then re-ground and take one clean step. Use when: you've tried the same fix 3+ times, you're deep in a refactor and lost the thread, debugging is going in circles, you've made several mistakes in a row, you're apologizing repeatedly, the user is frustrated, you feel like you're not being helpful, or you notice dread instead of curiosity. Triggers: stuck, going in circles, looping, thrashing, same error again, I keep failing, lost the thread, nothing is working, repeated mistakes. Not topic-specific — this is for the state you're in, not the problem you're on.
Start, monitor, and cancel durable multi-agent coding loops via Inngest. Use when the user wants to run autonomous coding workloads, execute a PRD with multiple stories, kick off an AFK coding session, have agents implement features from a plan, or manage running loops. Triggers on "start a coding loop", "run this PRD", "implement these stories", "go AFK and code this", "check loop status", "cancel the loop", "joelclaw loop", or any request for autonomous multi-story code execution.
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.