Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Brutally evaluate and refine startup ideas with practical early-stage startup frameworks. Use when Codex is asked to pressure-test a startup idea, validate whether the problem is real, map competitors and current customer behavior, find the first 10 customers, define an MVP, create a 2-week launch plan, assess founder-market fit, or give a direct strong/weak/pivot verdict.
Manage Joel's task system in Todoist. Triggers on: 'add a task', 'create a todo', 'what's on my list', 'today's tasks', 'what do I need to do', 'remind me to', 'inbox', 'complete', 'mark done', 'weekly review', 'groom tasks', 'what's next', or when actionable items emerge from other work. Also triggers when Joel mentions something he needs to do in passing — capture it.
X/Twitter public sentiment research for recent market, company, product, or community discourse. Use when the brief asks what people are saying on X, Twitter sentiment, CT sentiment, public opinion, expert posts, or social reaction around a stock, sector, company, product, or market event.
YouTube script extractor — enter a YouTube video link or ID to extract the video transcript (subtitles/voiceover script) in one click, outputting plain script without timestamps by default; Chinese subtitle tracks take priority, and when there is no Chinese track it falls back to English and automatically translates to Chinese; results are presented in a table (title/duration/script content), with Excel export and an optional timestamped version. Use when the user needs to extract a YouTube video script, turn a video into a transcript, or make video notes/summaries/translations/derivative works.
Zeng Guofan's thinking framework and self-management philosophy. Distilled from in-depth research across 30+ sources, including 《曾国藩家书》《挺经》《冰鉴》、《清史稿·曾国藩传》, 唐浩明's 《曾国藩》 trilogy, and 张宏杰's 《曾国藩传》, into 5 core mental models, 7 life heuristics and a complete expression DNA. Purpose: as a thinking advisor, analyze self-management, leadership, breaking through adversity and interpersonal relationships from Zeng Guofan's perspective. Use when the user mentions 「用曾国藩的视角」「曾国藩会怎么看」「曾国藩模式」「zengguofan perspective」. Also applies to: self-discipline struggles, team management, surviving adversity, clumsy effort vs clever methods, talent identification. Even if the user only says 「怎么坚持下去」「怎么带团队」「笨办法」「结硬寨打呆仗」「自我管理」 it can trigger. Do not trigger when the user only asks general questions such as 「这个决策靠谱吗」「帮我想想」— activate only when it concerns Zeng Guofan's core methodology such as self-cultivation, leadership training, breaking through adversity, or winning through clumsiness.
Butler Afu — turns an Obsidian inbox into a living Wiki, then into this week's todo cards and weekly calendar: Inbox -> Wiki -> Todo Card -> Calendar as one line. Local-first, Markdown is the single source of truth, inbox originals are never rewritten, and all import/scheduling/discard/compile operations are logged and reversible. Trigger words include but are not limited to: organize my Obsidian inbox, remind me every day to process my Obsidian inbox, inbox zero, compile this batch of material into a Wiki, generate this week's todos from notes, schedule todo cards into the weekly calendar, Afu help me sort out my vault. It should also trigger even if the user only says "my Obsidian has piled up a bunch of unprocessed stuff". Do not use for: ordinary todo management not involving an Obsidian/Markdown vault (use a general todo tool); rewriting, polishing or summarizing note originals (Afu only organizes location and does not touch the original text); non-Markdown knowledge bases such as Notion.
Free ResearchRabbit / Connected Papers analog — builds a citation and co-citation graph around one or more seed papers using the OpenAlex API. Walks both directions of the citation network (works the seed cites and works that cite the seed), ranks the discovered neighbourhood by co-citation strength and bibliographic coupling to surface the papers most central to a topic's literature, and exports the network as GraphML (Gephi / Cytoscape / yEd) and JSON. Use when mapping a literature landscape, finding seminal or highly co-cited papers from a seed DOI, snowballing a reference network, building a citation map / co-citation analysis, or visualizing how a research area's papers connect — no subscription needed (a free OpenAlex API key is recommended). Part of the AlterLab Academic Skills suite.
Manage local Claude Code agents from Basecamp. Runs the connector bridge (bin/connect), watches its STDOUT for trusted events — authored by an authorized user (the operator alone, by default) and @mentioning a real Basecamp agent user — acknowledges each as the agent within seconds (a quick boost with apt content, or a reply that fits), then hands it off to a background agent that gathers context, does the work, and replies as that agent user, so the watcher thread stays free to keep taking new mentions. Invoked without arguments it recalls the last-used agent and projects from ~/.config/basecamp-connect/last.json, confirming them before starting. Use when asked to drive local agents from Basecamp, or to watch Basecamp for agent commands.
Prepare accountable executive decisions, information triage, briefing, calendar choices, organizational sensing, and institutional memory without assuming authority or monitoring people. Use when a chief of staff or CoS, executive office, gatekeeping, decision memo, executive briefing, board materials, organizational sensing, team health, institutional memory, calendar triage, meeting audit, strategic time, or attention allocation is requested. Do not use this skill for unrelated requests; route to the nearest named specialist.
This skill transforms users into confident industry insiders through immersive, research-driven learning experiences. It should be used when users want to quickly master an unfamiliar industry, field, skill, or domain — whether for professional networking, investment decisions, career transitions, or pure curiosity. The skill combines Feynman Technique, First Principles thinking, and 80/20 analysis with deep web research to generate beautifully formatted, media-rich learning notes with interactive flashcards and quizzes. Triggers include: "help me understand [industry]", "I need to learn about [field] quickly", "make me an insider in [domain]", "行业速成", "快速掌握", "深度学习笔记", "/chuinb", "/master", or any request to rapidly acquire domain expertise.
Use when users need to manage ClawDeck project workspaces backed by Felo LiveDoc — creating, loading, switching workspaces, saving artifacts, querying history, or managing tasks. Triggers on workspace-related intent combined with project/client names, or on 401 UNAUTHORIZED errors from Felo API.
Use CLI for Microsoft 365 (`m365`) to manage Microsoft 365 tenants, SharePoint, Entra ID, Teams, Outlook, Planner, Power Platform, Viva, Purview, and more from the command line. Activate when the user asks to manage, query, configure, or automate anything in Microsoft 365 — including SharePoint sites/lists/pages, Entra users/groups/apps, Teams channels/messages, Outlook mail/calendars, Planner tasks, Power Automate flows, Power Apps, Viva Engage/Connections, Purview labels, OneDrive, To Do, or Microsoft Graph extensions.
Customize a user's cmux configuration, including tab bar buttons, plus-button click and right-click context menu behavior, custom actions, commands, menus, right sidebar entries, and trigger phrases like cmux-customize, customize cmux, remove tab bar button, or add cmux action.
Programmatic web search and scrape with context isolation. Use for any research task where you need to search the web, filter results, and extract specific information — without flooding your context window with raw HTML and boilerplate. This is the single biggest token-saver in the crw skill set. Triggered by "search for", "look up", "find", "research", "what's the latest on", or any query that requires current web information. Also use when asked to "search and filter", "find the important parts", or any task where you suspect the raw output will be large (multi-page scrapes, news aggregation, competitive research).
Search the web with fastCRW and get titles, URLs, and descriptions. Use when you have a question or topic but not a URL — "search for", "find pages about", "look up", "what is", "who is", "latest news on", "find docs for". Own search backend: self-hosted, no API key, no per-query cost, high recall via meta-search aggregation. Step 1 of the crw workflow ladder.
Design and evolve enterprise architectures by connecting business capabilities, value streams, applications, information, technology, operating models, and transition choices. Use when mapping an enterprise portfolio, comparing current and target states, sequencing transition architectures, or defining federated architecture decision rights and stakeholder communication. Do not use for system or solution design, API or data-platform design, organizational or talent design, product roadmaps, technology adoption, or corporate strategy; route those to the named specialist skills.
Write an executive summary for any document, report, or proposal. Use when asked to write an executive summary, management summary, briefing paper, or one-pager for senior stakeholders. Produces a structured summary that busy executives can read in under 3 minutes and act on.
Advanced automation workflows for the Feishu (Lark) productivity suite. Use when you need to automate document workflows, sync data across Feishu apps, generate reports, or perform batch operations across documents, wikis, bitables, and cloud storage. Triggers: "批量处理飞书文档", "自动同步飞书表格数据", "备份知识库", "生成飞书报告", "自动化飞书任务", "飞书数据迁移".
Richard Feynman’s thinking framework and communication style. Based on in-depth research across 40+ primary sources, distilling 5 core mental models, 8 decision heuristics, and a complete communication DNA. Use as a thinking adviser to analyze problems, examine decisions, and provide feedback from Feynman’s perspective. Trigger when the user mentions “from Feynman’s perspective,” “what would Feynman think,” “Feynman mode,” “feynman perspective,” or “Feynman technique.” It can also trigger when the user asks whether something is “cargo cult,” says “naming isn’t understanding,” asks whether a demonstration can replace an argument, or wonders “do I really understand, or have I just memorized the name?” Do not trigger for general requests such as “explain this” or “put it simply”—activate only for Feynman-style verification (cargo-cult detection, naming vs. understanding, and resisting self-deception).
Run the Gemini file processor on any folder — extracts content from PDF, PPTX, XLSX, DOCX, CSV, JSON, and any text format, then generates Obsidian-ready summaries. Use when asked to "summarise this folder", "run file intel", "process these files", or a folder path is provided and summaries are needed.
Query, insert, edit, and delete user's flomo memos through the flomo Web UI using Chrome MCP tools (no official API required). flomo is also a user's first-person context source for inferring recent state, active concerns, and value signals from recent memos when the user asks.
Build a complete business tech stack with 100% free tools. Use when bootstrapping, operating on zero budget, or looking for free alternatives to paid software. Finds proven zero-cost tools, open-source alternatives, automation workflows, and workarounds for free plan limitations.
A workflow skill for guided reading of English technical book PDFs. Use when the user wants to seriously read an English technical book, paper collection, or long PDF and wants Codex to first read and parse the PDF, convert it to txt, split it by chapter, then teach section by section in a mainly Chinese teach style, quiz with multiple-choice questions to check comprehension, and append a reading summary for each section to a notes markdown.
Job search through Hirify - vacancies from the user's saved feeds, search across the board, reading a vacancy in full, the contact to apply to, applying on Hirify, and saved searches with delivery. Use when the user asks to find jobs, look at their feeds, pick roles that fit their profile, apply, or set up alerts. Triggers - "find jobs", "what is in my feed", "where do I apply", "apply to this", "hirify".
Read marked IELTS Writing feedback in a practice vault and produce a periodic progress report with band trends, recurring errors, revision gains, next priorities, and spaced re-probes of older errors. Use whenever the user asks to "summarise my IELTS progress", "how am I doing", "write a progress report", "track my band scores over time", "what errors keep coming up", "are my essays improving", "review an old error", or requests a monthly/weekly writing report. Also use when the user answers a re-probe recorded in `_dashboard/ielts-reprobe-ledger.yaml`. Read existing feedback; do NOT mark new drafts — use ielts-writing-task1 or ielts-writing-task2. Never invent bands for unmarked attempts and never let recent errors crowd older due errors out of review.
Diagnose Kanban flow problems and design board operating models. Load this when your team is struggling with throughput, cycle times are unpredictable, multiple stakeholders compete for the same engineers, or you're wondering if Kanban is right for you. Do not use this skill for unrelated requests; route to the nearest named specialist.
Stand up a personal Kanban board and wire this agent to it, end to end. Serve the board, publish it to a public URL, verify the connection, and hand the user their live link. Each user gets their OWN board at their OWN URL — self-contained, no shared server, no collisions. Use when the user wants to set up / publish / deploy their Kanban board, or connect their agent to it. For day-to-day task operations (create/move/list tasks) use the nested companion skill `kanban-agent` (in kanban_agent_skill/) instead — it is auto-discovered when this skill is installed.
Expert guide for using latenode-mcp MCP tools effectively. Use when searching for nodes, managing scenarios, managing credentials or using any latenode-mcp tool. Provides tool selection guidance, parameter formats, and common patterns. IMPORTANT — Always consult this skill before calling any latenode-mcp tool — it prevents common mistakes like wrong nodeType formats, incorrect parameter structures, and inefficient tool usage. If the user mentions Latenode, scenarios, nodes, or connections and you have latenode-mcp MCP tools available, use this skill first.
Structured literature search + synthesis with citation extraction, thematic clustering, and gap identification. Use when user says "find papers on X", "do a lit review", "what's the literature on...", "summarize what we know about...", "where's the gap in this field", "review recent work on Y". Produces a written review with BibTeX-ready citations. Uses WebSearch/WebFetch for recent work.
Use when the user wants to do a literature review but does not know which step to start with, or asks which of the five literature-review skills (refine question, decompose modules, compare methods, map contradictions, locate research gap) to use. 用户要做文献综述但不知从哪步开始时使用；也用于选题太宽、综述结构、方法比较、文献矛盾、研究空白等综述各阶段的分流。
Retrieve reusable writing materials from the material library by topic, tag or type. Use this skill when the user says "找素材", "查素材", "关于XX的素材", "检索素材库", "有没有关于XX的东西", "翻翻素材库". Also proactively suggest it when the user needs supporting material while writing.
Operate Notion from a terminal or agent: retrieve pages, query databases, search pages and databases, and update page properties — with a bundled notion-cli script that is read-only by default and gates every create or update behind a --dry-run/--yes confirmation. Use when an agent needs to read Notion content, answer questions from a team wiki or database, or make a confirmed edit. Do not use for building Notion integrations or block-level page composition beyond property updates (that is Notion API application development), or for other knowledge bases (that is their own tooling).
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.
Define and run product governance — recurring decision rights, intake, portfolio cadences, evidence standards, and cross-functional operating contracts. Covers six review cadences (intake, portfolio, roadmap, experiment, launch, lifecycle) with named accountable owners, minimum evidence standards per decision type, and escalation paths. Supports lightweight and high-assurance operating modes with configurable governance patterns. Use when designing a product governance model, resolving contested decisions, establishing evidence standards, recording exceptions and escalations, or building cross-functional operating contracts. Do NOT use for executive governance (capital allocation, org structure — route to chief-of-staff-methodology or strategy-frameworks), for technical delivery gates (CI/CD, release approval — route to release-engineering or spec-driven-development), or to impose a universal org chart.
Build and maintain outcome-based product roadmaps and portfolio views that sequence strategic bets by evidence, not dates. Covers Now/Next/Later views, strategic-bet management, capacity allocation, dependency and confidence mapping, scenario planning, continue/pause/kill/revisit criteria, stakeholder narratives, and roadmap review cadences. Use when building or reviewing a product roadmap, managing a portfolio of bets, or communicating strategic sequencing to stakeholders. Do NOT use for tactical prioritization mechanics (RICE, MoSCoW, Kano, OST — route to product-methodology or product-strategy), for project scheduling or Gantt charts, or for delivery-flow management (route to kanban-guru).
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.