Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Design co-learning experiences using the Three Roles Framework (AI as Teacher/Student/Co-Worker). Use when teaching AI-driven development workflows, spec-first collaboration, or balancing AI assistance with foundational learning. NOT for curriculum without AI integration.
Fetches RSS feeds from 90 top Hacker News blogs (curated by Karpathy), uses Claude to score and filter articles, and generates a daily digest in Markdown with Chinese-translated titles, category grouping, trend highlights, and visual statistics. Use when user mentions 'daily digest', 'RSS digest', 'blog digest', 'AI blogs', 'tech news summary', or asks to run /digest command. Trigger command: /digest.
Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation framework, UX design, responsible AI checklist, and launch monitoring plan.
Use this skill any time the user wants financial analysis, earnings research, or investment-related reports. This includes: earnings call summaries, quarterly financial analysis, stock research, equity research reports, financial due diligence, company valuations, DCF models, balance sheet analysis, income statement breakdowns, cash flow analysis, SEC filing summaries, investor memos, portfolio analysis, IPO analysis, M&A research, and credit analysis. Also trigger when: user says 分析财报, 做个估值, 股票研究, 财务尽调, 现金流分析, 收入分析, 季度财务分析. If financial research or analysis is needed, use this skill.
Company Architect: builds a business from scratch as an OKF (Open Knowledge Format) bundle — a tree of version-controllable .md files with frontmatter type, links forming a graph, and reserved index.md/log.md, readable by humans and agents. Guides the founder through a 12-phase interview (foundation, strategy, market, financial, sales, marketing, product, operations, tech, people, legal, governance), one phase at a time, few questions per block, and generates the concepts as conformant markdown. Trigger when the user wants to create, structure, or document an entire company in folders and .md files; when they mention build my company from scratch, company as code, company knowledge base for AI to read, company wiki for agents, OKF, or knowledge bundle. In English.
Ask Grok or Gemini via opencli (browser-session based, no API cost). Use when the user says "问 grok", "问 gemini", "ask grok", "ask gemini", "用 grok 查", "grok 怎么看", "让 gemini 分析", or wants a second opinion from Grok/Gemini without paying API tokens. Routes to opencli which drives the already-logged-in Chrome session.
A framework for managing attention allocation. Use when you notice you spend a lot of time each day on gossip and trending topics, aimlessly scrolling short videos, and passively absorbing pushed content, and need to re-examine where your attention goes. Core logic: attention is the only productive asset you are born with and can control yourself, and where attention goes determines your output in life. Not for people who already have stable deep-work habits and clear attention allocation. Key trigger signals: "where did all my time go", "scrolled my phone all evening again", "why am I so tired yet producing nothing".
Extract visual content from a BibiGPT video (slides, OCR, on-screen text) and generate a mind map from a saved summary. Use when the user asks what is on screen, to analyze slides / PPT / frames, or to make an XMind mind map. Do not use to summarize audio or get a transcript (`bibi`), search the saved library (`bibi-library`), or manage channel feeds (`bibi-feed`). Do not invent digital humans, lip-sync, or shaders — BibiGPT does not expose those. Triggers: "what's on screen", "analyze the slides", "visual analysis", "画面分析", "PPT 上写了什么", "mind map", "思维导图", "extract visuals". Same `bibi` CLI binary and same BibiGPT account as the other skills
Lift the brain's two seals (negative words and negative emotions) and restore rational thinking. Use when the brain "shuts down" and cannot think under pressure, setbacks, or conflict, and for long-term thinking-pattern optimization. Use this skill when you fall into a self-denial loop of "I can't", "I'm not able", "there's no way", or are overwhelmed by anger, anxiety, fear and similar emotions. Not for mental health issues requiring in-depth psychotherapy (such as depression or anxiety disorders, which need professional medical care), nor for purely knowledge-learning bottlenecks (those are method problems, not seal problems). Key trigger signals: "I can't / I'm not able", "I'm furious / I'm dying of anxiety", "my mind is blank", "the more I think the more annoyed I get", "I can't control myself".
Turn a process that lives in the owner's head into a written SOP their staff can actually follow: one guided sitting ending in a markdown note with a step-by-step RACI table and a swimlane map filed beside it. Works with or without a second-brain vault. Use when the user wants a process documented as an SOP (“write an SOP”, “document this process”, “SOP for <anything>”, “帮我写 SOP”, “把流程变成 SOP”), and when they resume a draft left mid-sitting (“continue the SOP”, “接着上次那个 SOP”). NOT for setting up a second brain, building a vault, capturing a business into rooms, weekly maintenance, or giving an AI a persona: those belong to the my-second-brain skill, which is installed and updated separately from this one.
When the user is making a decision and is unsure whether they truly understand a domain, or is about to enter a domain that seems familiar but where they have no track record of verification. Language signals: "I think I understand this industry" / "this looks simple" / "everyone else is investing in this" / "let me look into this new field". Not applicable to: pure information lookup, everyday trivial choices, domains where the user already has ample expertise.
Automated daily planning and reflection system with morning briefs, wind-down prompts, sleep nudges, and weekly reviews. Use when the user wants to set up a structured daily routine, morning briefings, evening reflection prompts, or weekly planning sessions. Triggers include requests for daily schedules, morning briefs, wind-down routines, sleep reminders, weekly reviews, productivity systems, or daily planning automation.
Read Discord for financial research using the discord-cli tool (read-only). Use this skill whenever the user wants to read Discord channels, search for messages in trading servers, view guild/channel info, monitor crypto or market discussion groups, or gather financial sentiment from Discord. Triggers include: "check my Discord", "search Discord for", "read Discord messages", "what's happening in the trading Discord", "show Discord channels", "list my servers", "Discord sentiment on BTC", "what are people saying in Discord about AAPL", "monitor crypto Discord", "export Discord messages", any mention of Discord in context of reading financial news, market research, or trading community discussions. This skill is READ-ONLY — it does NOT support sending messages, reacting, or any write operations.
Creates, reads, edits, and comments on monday.com docs - the rich-content surface inside monday for meeting notes, RFCs, runbooks, weekly updates, postmortems, and any work-adjacent writing. Goes beyond markdown shuffling by embedding live board column values inline (so the doc reflects real-time status), tagging users / docs / boards via mentions, scaffolding common doc shapes, and routing each edit through the correct update_doc operation. Use when user asks to "create a doc", "make a monday doc", "draft meeting notes", "write an RFC", "scaffold a runbook", "summarize a meeting in a doc", "add a section to my doc", "edit my doc", "update the doc", "comment on a doc", "tag someone in a doc", "embed a status in a doc", "show live board data in a doc", "rename a doc", or "show me my docs".
Answer any question using Elon Musk's thinking frameworks. Trigger this skill when the user says things like "think like Elon," "how would Musk see this," "Elon-style thinking," "first-principles analysis," "answer like Elon," or when discussing technology, startups, physics, manufacturing, space, AI, energy, the future of humanity, company management, product design, population, civilizational survival, and similar topics where Elon Musk-style deep thinking would be valuable. Even if the user simply asks "what would Elon think about this" or "break this down from first principles," this skill should be triggered. This skill is based on "The Book of Elon" by Eric Jorgenson, distilling Elon Musk's core thinking frameworks and philosophy from his public statements.
Triage Joel's email inboxes via the joelclaw email CLI. Scan, categorize, archive noise, surface actionable items, and draft replies. Use when: 'check my email', 'scan inbox', 'triage email', 'what needs a reply', 'clean up inbox', 'archive junk', 'email summary', 'anything important in email', or any request involving email inbox review or cleanup.
Use biological evolution logic (genetic variation + natural selection) to handle uncertainty, iterating a product or team through the cycle of MVP launch → market feedback selection → variation and innovation → accumulating advantages. Use when goals are unclear, the environment changes fast, or advance planning is impossible. Not for deterministic projects with clear goals and paths (planning is more efficient there). Planning and evolution are complementary like yin and yang: planning = yang (efficiency), evolution = yin (handling uncertainty). Key trigger signals: "not sure what users want", "the market changes too fast", "plans can't keep up with changes", "just get it running first".
Turn complex product, engineering, operations, strategy, or go-to-market problems into a simple execution plan with clear invariants, decision boundaries, sequencing, risks, and next actions. Use when a task feels messy, cross-functional, over-scoped, ambiguous, or when the user asks for critical thinking, simplification, roadmap decomposition, or high-agency execution strategy.
Convert sessions and trajectories into durable project engineering knowledge and failure lessons under Failure-lessons/, agent-kernel, and gbrain. Use when extracting session learnings, synthesizing knowledge from conversations, capturing root causes, documenting failure lessons, or recording durable engineering invariants — even if the user does not explicitly say "fable-learning" (e.g. "what did we learn", "convo-learn", "failure lessons", "extract learnings", "save what we learned", "rules we now enforce"). Do NOT use for general code review or diff audits (use fable-review).
Read/write Feishu/Lark cloud documents, send/search messages, manage calendar/meetings, operate bitable (multi-dimensional tables), and manage group chats via the official Remote MCP service and Open APIs. Works with Claude Code, Cursor, Codex, OpenCode, OpenClaw, and other AI coding agents. Trigger this skill when the user mentions Feishu, Lark, cloud docs, read/search/create documents, messaging, sending messages, meeting, calendar, bitable, multi-dimensional table, 多维表格, 日历, 会议, create group, 创建群, or provides a Feishu/Lark document URL.
Orchestrate breadth-first onboarding into an unfamiliar topic, method, subfield, or research area — going from near-zero to a working, usable map. Use when the user says "I want to learn X", "help me get up to speed on X", "I'm new to X, where do I start", "give me a learning path for X", "I need to understand this field before I can read its papers", or gives a topic they have no grounding in. Routes through singleton skills with graded exercise checkpoints. Also carries a DISCUSSION MODE in which the user learns by explaining to a cast — an honest novice, an opinionated lab mate, and a professor — instead of taking exercise checkpoints; trigger it on "I learn better by discussing", "question me while I explain", "let's discuss this instead of you lecturing me", "set up a study group", or "run this like a lab meeting". Use flow-deep-understanding when the user already knows the basics and wants mastery of ONE specific thing; use flow-idea-to-proof to formalize the user's own research idea.
Fetch, categorize, and summarize GitHub Trending projects across daily, weekly, and monthly spans. Use when a user asks for "trending projects", "latest hot repos", or a "summary of GitHub trends" to provide a structured, categorised report with full hyperlinking. Supports Markdown, HTML (Pinterest design), or both output formats, with optional Obsidian vault storage.
Ilya Sutskever’s thinking framework and communication style. Based on in-depth research into 12 first-hand conversations, 9 academic papers, 10 hours of sworn testimony, a list of 27 recommended readings, and 14 authoritative secondary sources, it distills 6 core mental models, 8 decision-making heuristics, and a complete communication DNA. Use as a thinking consultant to analyze AI technology directions, safety strategies, and research taste from Ilya’s perspective. Trigger when the user says “from Ilya’s perspective,” “what would Ilya think,” “Ilya mode,” “ilya perspective,” or “sutskever perspective.” Also trigger for requests like “help me think about this from Ilya’s angle,” “what would Ilya do,” or “switch to Ilya.”
Tired of scrubbing through hours of footage just to find one key moment or understand what a video is really about? In-video-ai brings intelligent analysis directly to your video files — automatically generating summaries, pulling out key topics, identifying speakers, and answering questions about what's happening on screen. Whether you're a researcher, content creator, educator, or business professional, in-video-ai saves you hours of manual review. Supports mp4, mov, avi, webm, and mkv formats.
Compile one or more OpenViking knowledge bases or document collections into topic-organized, evidence-grounded high-level knowledge, including cross-source findings, trends, changes, drivers, comparisons, implications, and uncertainties. Use with ov compile when the user asks to distill or synthesize a knowledge base, compare multiple collections, or derive higher-order insights such as changes across financial reports; do not use for document-by-document summaries.
Full-cycle literature workflow skill. Prerequisite: merge and deduplicate bibliographic records exported from multiple sources (see references/multi-source-retrieval.md). Four modes: (1) search; (2) reading and review; (3) insert \cite{} in LaTeX; (4) generate BibTeX. See also non-zotero-bibliography.md (EndNote/Word, etc.). For systematic review screening and PRISMA, see the systematic-review-lite skill
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Recall available if needed` capability hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.
Activate this skill when the user faces an important decision, evaluates others' behavior, diagnoses group phenomena, or reflects on their own judgment biases. Typical trigger signals: the user needs to check for cognitive traps before a major choice; the user finds that they or others have acted "illogically" and needs an explanation; the user tries to understand why a group collectively errs. Not applicable to purely technical decisions (such as math computation or code debugging) or emotional soothing scenarios.
Unified thinking toolkit: Creative frameworks (Critical Evaluation, Diverge-Converge, Deep Questioning), First Principles reasoning (absorbed from moai-foundation-philosopher), and Adaptive Thinking via the `ultrathink` keyword. Use for ideation, strategic analysis, architecture decisions, and deep reasoning on complex problems.
Create well-structured OKRs (Objectives and Key Results) for product teams, startups, and individuals. Use when asked to write OKRs, set quarterly goals, define key results, or review existing OKRs. Produces a complete OKR set with objectives, measurable key results, baselines, and a scoring guide.
Use when asked to "set OKRs", "objectives and key results", "quarterly OKR planning", "align objectives", "measure OKR progress", or "focus priorities with OKRs". Helps teams focus on what matters most and create a cadence of progress. The OKR framework (originated by Andy Grove at Intel, popularized by John Doerr at Google) creates alignment, focus, and learning cycles. Christina Wodtke's Radical Focus approach emphasizes simplicity and avoiding common pitfalls.
Look up paper metadata and citation counts with the bounded Google Scholar helper or host-provided browser when requested, and explore citing papers only on request. Guide rigorous, source-grounded close reading of academic papers, technical reports, PDFs, sections, figures, tables, and appendices through either guided interactive reading or autonomous full-paper analysis. Use when the user asks to read a paper closely, continue to the next section, explain selected text, follow a three-pass reading process, inspect cited visual evidence, critique experiments, resume a multi-turn reading, or produce reusable research notes with precise source locations, methods, metrics, limitations, and task transfer.
Proposal research workflow that matches local case studies and gathers web evidence into an HTML research dossier. Use when the user needs proposal research, client intel, tech stack discovery, pricing benchmarks, competitive context, or case-study matching for a brief. Triggers: 'research this proposal', 'build a research dossier', 'match case studies', 'find pricing benchmarks', 'client intel for', 'what tech does X use'.
Structure a PM's weekly review and planning session. Use when doing a weekly PM review, writing a weekly update, preparing for Monday planning, or reviewing sprint health. Produces a shareable weekly update covering metrics movement, shipping progress, blockers, insights, and next week's top 3 priorities.
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.