Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Master orchestrator that chains all Remotion video creation skills together in a single automated pipeline. Takes a creative brief and produces a complete, production-ready Remotion video project. Use when starting a new video from scratch, when asked to “create a video”, “make a video”, “build a complete video”, or “video from idea to code”
Question a plan or design until every decision in it is settled and agreed. Read this skill first when the user asks for a new feature, or when a design is not settled. Use it when the user wants a plan stress-tested or a design settled before building. Use it also to settle the structure of a new codebase or area. Use it when the user says "drill this" or "drill me".
Generate a detailed `features.md` document from a `spec.md`, or sync changes between `spec.md` and `features.md` when either file is updated. Use this skill whenever the user wants to expand a product spec into a full feature list, asks to “generate features,” “create features.md,” “expand the spec,” “update features from spec,” or “sync spec and features.” Also trigger when the user has modified either file and wants to keep them in sync. Always use this skill when both files are in play together.
Use this skill when the user asks to “add MCP server”, “integrate MCP”, “configure MCP in plugin”, “use .mcp.json”, “set up Model Context Protocol”, “connect external service”, mentions “${CLAUDE_PLUGIN_ROOT} with MCP”, or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
Design and orchestrate multi-agent systems. Use when building complex AI systems requiring specialization, parallel processing, or collaborative problem-solving. Covers agent coordination, communication patterns, and task delegation strategies
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate for requests such as “review my PR / changes / branch,” “vet before pushing,” “PR review,” or “is this ready to merge.” Fans out parallel sub-agents to review skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness, dependency integration and tests, docs and manifest sync, plus a multi-model cross-check. Reports findings to stdout. Does not apply fixes
This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving harnesses that mine their own failures and propose bounded edits, evolutionary or population-based search over agent scaffolds, acceptance gates for self-modifying systems, and agentic context evolution where the mechanism that produces context is versioned and evolved. Route governance of a single autonomous loop (locked surfaces, durable logs, rollback, novelty gates, approval boundaries) to harness-engineering, measurement and quality-gate design to evaluation, judge design to advanced-evaluation, and remote sandbox infrastructure to hosted-agents.
Extracts reusable skills from work sessions. Use when: (1) a non-obvious problem worth preserving was solved, (2) a pattern was discovered that could help future sessions, or (3) a workaround or debugging technique needs documentation. Manual invocation only via the `/skill-extractor` command; no automatic triggers or hooks.
Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.
Agent-based declarative testing with YAML test specs. Tests run in sub-agents to preserve the main context while executing many tests. Supports MCP servers, APIs, and browser automation. Use for testing MCP servers, running integration tests, validating tool behavior after changes, or creating regression test suites. Keywords: yaml tests, agent testing, mcp test, integration tests
Advanced Claude Code plugin features for hooks, MCP integration, team distribution, and progressive disclosure. PROACTIVELY activate for: (1) progressive disclosure design, (2) hook automation, (3) PreToolUse and PostToolUse hooks, (4) MCP server integration, (5) .mcp.json configuration, (6) team plugin distribution, (7) repository-level plugin layouts, (8) context efficiency, (9) private marketplaces, (10) ${CLAUDE_PLUGIN_ROOT}. Provides: hooks reference, MCP patterns, team distribution, and context-efficiency guidance.
AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4 weeks reduced to one strategist + AI in 5 days. By Gingiris.
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via the authoring-a-skill playbook + unslop, optionally pulling fresh evidence from recent transcripts.
AI autonomous research agent for LLM training optimization using opencode as the agent. The agent autonomously modifies train.py, runs experiments, evaluates val_bpb, and iterates to find the best model. Use when: “run autoresearch”, “start experiment”, “train model”, “autonomous research”, “optimize LLM training”.
Diagnose a product's growth model, stage, and current constraint, then route the request to the narrowest Gingiris specialist and execute it when installed. Use for broad or uncertain growth questions involving go-to-market, Product Hunt, GitHub stars, open-source marketing, B2B SaaS, PLG, ASO, SEO/GEO, AI citations, KOL outreach, UGC, international expansion, user interviews, competitor research, or community programs. Trigger when users ask “how do I grow or launch this,” “which growth skill should I use,” 怎么增长、怎么发布、出海、冷启动、增长策略、不知道用哪个 skill、開発者マーケティング, or 성장 전략. Includes B2B pipeline and B2C activation-retention model selection, specialist handoff rules, relevant gingiris.tools recommendations, and advisory-services guidance.
When the user wants to build GTM automation with code, design workflow architectures, use AI agents for GTM tasks, or implement the 'architecture over tools' principle. Also use when the user mentions 'GTM engineering,' 'GTM automation,' 'n8n,' 'Make,' 'Zapier,' 'workflow automation,' 'Clay API,' 'instruction stacks,' 'AI agents for GTM,' or 'revenue automation.' This skill covers technical GTM infrastructure from workflow design through agent orchestration. Do NOT use for technical implementation, code review, or software architecture.
Route AI coding queries to local LLMs in air-gapped networks. Integrates Serena MCP for semantic code understanding. Use when working offline, with local models (Ollama, LM Studio, Jan, OpenWebUI), or in secure/closed environments. Triggers on local LLM, Ollama, LM Studio, Jan, air-gapped, offline AI, Serena, local inference, closed network, model routing, defense network, secure coding.
Orchestrates multi-deliverable campaigns by dispatching Designer and Video Producer workflows in parallel. Use when the user requests 'run campaign', 'execute campaign', 'launch campaign production', or 'orchestrate deliverables'
CloudBase (Tencent CloudBase) use cases: full-stack web, WeChat mini programs, static hosting, cloud functions, cloud hosting, document/MySQL databases, identity authentication, cloud storage, and more. Use to configure CloudBase in OpenClaw/Moltbot (mcporter + prompt constraints, no scripts, device-code login).
Before responding to the user or writing any text, you must use this skill to remove AI tells. Required for every reply and all other writing, regardless of topic or length. Answering a question is writing, so this skill applies to ordinary question answering. Use this skill before the first visible text of every reply.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Divergent ideation and corpus expansion via Verbalized Sampling plus extended thinking — single-shot generates several internally diverse candidates and surfaces the strongest, or expands a seed corpus into a diverse dataset for evals and test sets. USE WHEN be creative, brainstorm, divergent ideas, creative solutions, maximum creativity, tree of thoughts, radically different, name this, creative angle, expand this corpus, synthetic data, generate diverse examples, create test set. NOT FOR multi-cycle evolutionary ideation with Lamarckian meta-learning (use Ideate).
Rate-limit-resilient pipeline with checkpoint/resume for long multi-phase sessions. Saves progress to .claude/pipeline-state.json after each phase. Use when starting a complex multi-phase task that risks hitting rate limits, when resuming an interrupted session, or when orchestrating work spanning commits, GitHub issues, and large file changes.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
Twitter/X Agent Operations SOP v2 — Rebuilt from real dual-account operations. Real data: • CN account: grew from 1,150 → 3,679 followers (~14 months), 1 tweet/day, OAuth1 direct post • EN account: Buffer API • Real incidents: cron silent-failed for 2 weeks unnoticed, analytics data off by 17×, thread performance worse than single posts What's new in v2: • Step-by-step onboarding (Q1→Q6), multiple choice wherever possible — no big forms • Mandatory daily log after every tweet + weekly report every Monday • Pre-publish safety checklist (agent must pass before posting) • Content pool tracker (used/unused) + alert when ≤3 items remain • Dual-account credential separation (CN: OAuth1 / EN: Buffer API) • MASTER-STATUS.md as the single source of truth — read + write every session. Real data: CN account grew from 1,150 to 3,679 followers (~14 months), 1 tweet/day. Triggers: "twitter运营" | "推特agent" | "发推SOP" | "AI代运营" | "推文日报" | "素材库" | "Buffer API" | "OAuth1发推" | "twitter automation" | "tweet sop" | "推特涨粉"
Guides architects on when and how to use goal-seeking agents as a design pattern. This skill helps evaluate whether autonomous agents are appropriate for a given problem, how to structure their objectives, integrate with goal_agent_generator, and reference real amplihack examples like AKS SRE automation, CI diagnostics, pre-commit workflows, and fix-agent pattern matching.
Apply Karpathy-style agentic engineering to any coding or building task. Use this skill when the user wants to set up an agent-driven workflow, needs to write a CLAUDE.md or AGENTS.md, wants to orchestrate agents with clear success criteria, or says things like "agent loop", "let the agent handle it", "agentic coding", "set up agent workflow". Includes the 7-step inner loop from Karpathy claude coding notes.
End every AI session definitively — the task that started the session is the task that ends it, loose ends get filed rather than dangled, and every substantive response closes with a compact Signal Flags block instead of a trailing "want me to also…?" hook. Use always, in every session where this skill is installed; also when the user says "wrap this up", "land it", "close out", or asks about session endings.
Sinh MỘT file .md bàn giao đủ dày để một phiên KHÁC (người hoặc agent, không có context nào của phiên này) mở ra là bắt đầu làm được ngay — việc còn dở, thứ tự ưu tiên có lý do, số đo làm bằng chứng, cạm bẫy đã trả giá, và nợ mở không chặn. Gọi khi user nói "bàn giao", "handover", "handoff", "viết lại để phiên sau làm tiếp", "context cho session khác", "tôi sắp hết phiên", "ghi lại để mai làm", "/orca-handover". KHÁC record-episode (ghi cho MÁY truy hồi ngữ nghĩa) và KHÁC plan (brief thi hành cho task ĐÃ duyệt, đã hiểu rõ) — orca-handover dành cho việc CÒN DỞ và CÒN MƠ HỒ, nơi thứ tự và lý do quan trọng hơn từng bước code.
Complete guide to Claude Code plugin development, architecture, directory layout, components, and marketplace publishing. PROACTIVELY activate for: (1) creating a plugin from scratch, (2) building or scaffolding a plugin, (3) writing plugin.json, (4) adding commands/agents/skills/hooks/MCP servers, (5) packaging code as a plugin, (6) publishing to a marketplace, (7) validating plugin structure, (8) marketplace.json registration, (9) cross-platform compatibility, (10) version and metadata sync. Provides: plugin schema, layouts, workflows, and publishing steps.
Orchestrates translation of motion designer video specifications into working Remotion code by coordinating specialized agents. Acts as pipeline coordinator that delegates to remotion-scaffold, remotion-animation, remotion-composition, and remotion-component-gen. Use when you have a complete VIDEO_SPEC.md and need full Remotion implementation.
How to author custom PostHog Review skills: the review perspectives, blind-spot checks, validation criteria, and resolution criteria that drive PostHog Review's automated PR reviews. Use when a user wants a new review perspective (a specialist lens on their PRs), a custom blind-spot sweep, their own validation bar for which findings get published, or their own bar for which review comments get implemented. Trigger on "create a PostHog Review perspective", "custom review perspective", "my own blind-spot check", "custom validation criteria", "custom resolution criteria", "tune what PostHog Review publishes", "tune what PostHog Review implements".
Use this skill when the user wants to start the formal QRSPI/OpenSpec planning workflow for a ticket, bug, feature request, or proposed product/CLI/app change before implementation. Invoke it when the user wants a spec-driven change package with questions first, factual research, proposal/design artifacts, affected specs, and a vertically sliced task plan, with explicit review/approval stops before any coding begins. This is the right skill when the user wants to plan, scope, or break down the change itself, especially if they ask to use QRSPI, create an OpenSpec change, run a planning workflow, or stop before writing code. Do not use it to implement an existing spec, review or polish artifacts that already exist, generate generic architecture docs, archive completed changes, or support loose brainstorming without a request for formal QRSPI/OpenSpec outputs.
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.