Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Kick off international expansion planning for a new country — gathers intake, runs EOR vs. entity framing, drafts cross-functional questions, surfaces country-specific flags, and creates a persistent tracker. Use when someone says "we're hiring in [country]", "expansion to [country]", or "first hire in [country]".
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Use when writing or formatting Jira descriptions, comments, or any text destined for Jira. Converts Markdown to Jira wiki markup, provides templates (bug reports, feature requests), and validates syntax before submission. Triggers on any Jira content authoring task.
Helps Leo watch videos. Use it when Leo drops a video link (YouTube/IG/TikTok) or a local video file and wants a summary, analysis, or breakdown of a reference to match — Claude cannot read video directly, so first use this tool to extract key frames + transcripts + camera movement rhythm + a timeline of voice/tone/gestures, then read it.
Update the status of an in-progress international expansion project — recalculates what is now unblocked, flags anything overdue, and surfaces the next priorities. Use when work has happened since the last session and the expansion tracker needs to reflect the current state.
Send text messages to a specified contact via the WeChat desktop app on macOS. Use when the user provides a contact name and message content, for example "send Zhang San a WeChat message: xxx", "open WeChat and send someone a message", or "send the specified text via WeChat". The WeChat desktop app must be installed beforehand, and the current terminal or Codex must have accessibility permission. Execution uses exact matching only: first search for the contact, then verify the current conversation title matches the target exactly; stop if the match fails, to avoid misdelivery.
Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use for feature prioritization, user research synthesis, requirement documentation, and product strategy development.
Professor's review queue — student output waits here for professor approval before going to clients or courts. Only active if "formal review queue" supervision style was chosen at setup; otherwise dormant. Use when the professor wants to see what's waiting for review, approve, edit-then-approve, or return an item.
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
Write a noun or concept into a usable understanding: first explain in plain language what it is and how it differs from neighboring concepts, then describe how it works and what judgments it changes, and finally give concrete handles for acting on it. Use when the user asks what X is, how to understand it, what it means, why it matters, or how to judge or use it later; especially suited to technical concepts, institutions, products, roles, methods, standards, and practices. Not for: simply looking up facts, proving formulas, step-by-step tutorials, deep vertical causal digging (use ljg-think), or motif structure (use ljg-structure).
Cross-functional what-if modeling for cascading multi-variable scenarios. Unlike single-assumption stress testing, this models compound adversity across all business functions simultaneously. Use when facing complex risk scenarios, strategic decisions with major downside, or when the user asks 'what if X AND Y both happen?'
Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or max rounds is reached.
Schema lifecycle management for Basic Memory: discover unschemaed notes, infer schemas, create and edit schema definitions, validate notes, and detect drift. Use when working with structured note types (Task, Person, Meeting, etc.) to maintain consistency across the knowledge graph.
End-of-semester case handoff memos — the mirror of /ramp. Produces per-case transition memos and a cohort summary so the departing cohort hands work to the incoming cohort cleanly. Reads deadlines, client-comms, and case history. Use when the professor or departing students need to wrap up the semester, build transition memos, or offboard a graduating/withdrawing student.
Analyzes meeting transcripts and recordings to surface behavioral patterns, communication anti-patterns, and actionable coaching feedback. Use this skill whenever the user uploads or points to meeting transcripts (.txt, .md, .vtt, .srt, .docx), asks about their communication habits, wants feedback on how they run meetings, requests speaking ratio analysis, mentions filler words or conflict avoidance, or wants to compare their communication across time periods. Also trigger when users mention tools like Granola, Otter, Fireflies, or Zoom transcripts. Even if the user just says "look at my meetings" or "how do I come across in meetings" — use this skill.
Generate a donor proposal pack (CERV first) with the full MEL stack: intake, a fixed roster delegated to Vi (evidence-synthesis, toc-builder, indicator-designer, the gender and safeguarding lens specialists, proposal-architect), then the seven-artefact branded pack with the AI-disclosure colophon. Use when Ane builds a grant proposal or runs '/proposal --donor cerv'; donor is an argument so Gates/OSF/UN are later --donor values. Does not fill Part A portal forms, submit, or sign off finance/legal. Distinct from donor-proposal-scoring (scores a written proposal) and implementation-pack (post-award).
Get a deep critical review of research from a selected reviewer (Codex by default, Gemini, Grok, Claude Code, or manual). Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results
Schedules Claude Code tasks to run automatically at specific times using native OS schedulers (launchd on macOS, crontab on Linux, Task Scheduler on Windows). Handles one-time tasks like "today at 3pm remind me to deploy", "tomorrow morning run the test suite", "next Tuesday at 2pm review the API changes", "January 15th check the quarterly metrics". Also handles recurring tasks like "every weekday at 9am review yesterday's code", "daily at 6pm summarize what I accomplished", "every Monday at 10am check for security vulnerabilities", "every 4 hours check API health". Recognizes time formats like "at 9am", "at 1015am", "at 10:30pm", "at noon", relative times like "tomorrow", "tonight", "later", "next week", and dates like "January 15th". Use this skill instead of executing immediately whenever the user's request contains a time expression like "at Xam", "tomorrow", or any future time reference.
Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.
Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions and knowledge from chat context, formats them appropriately, and saves to wikis or databases with proper organization and linking for easy discovery.
/c-level-agents:office-hours [topic] — YC-style 6-question founder interrogation before any advice. Forces clarity on problem, customer, distribution, defensibility, capital, and founder fit. Use when a founder question is too vague to route—for example, “should we grow faster?”—or before drafting a strategy brief.
Founder onboarding interview that captures company context across 7 dimensions. Invoke with /cs-onboard setup for initial interview or /cs-onboard update for quarterly refresh. Generates ~/.claude/company-context.md used by all C-suite advisor skills. Use when setting up the C-suite advisors for the first time, or when company context is missing or more than 90 days old — e.g. after a fundraise or pivot.
The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording, a meeting recording, or a playlist/folder of videos — “watch this”, “summarize this video”, “what's in this recording”. Use this to actually watch the video — download, extract frames, OCR, transcribe, and index it — instead of guessing from the title or asking the user to describe it.
Cascades strategy from boardroom to individual contributor. Detects and fixes misalignment between company goals and team execution. Covers strategy articulation, cascade mapping, orphan goal detection, silo identification, communication gap analysis, and realignment protocols. Use when teams are pulling in different directions, OKRs don't connect, departments optimize locally at company expense, or when user mentions alignment, strategy cascade, silo, conflicting OKRs, or strategy communication.
Use when the user asks to capture a full-page screenshot, long screenshot, or complete page capture of a web page. Handles SPA scroll containers, lazy-loaded images, and very tall pages via Chrome DevTools Protocol with zero external dependencies
AI agent-friendly CLI RSS/Atom feed viewer with discovery, search, and OPML import/export. Use when an agent needs to manage RSS feeds, read articles, or run feed discovery from the terminal. Triggered by: "read RSS feeds", "view RSS", "RSS reader CLI", "rss-viewer", "discover RSS feeds", "import OPML", "search feeds", or "discover-search feeds".
Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations.
Aggregated news, regulatory filings, and Longbridge-community discussion for a single stock — classified into catalyst / regulatory / strategic / financial / opinion / other, with a fact-only key-takeaway summary and a sentiment skew. Falls back to WebSearch only when data is sparse or stale, and labels the source. Triggers: "X 最近新闻", "X 公告", "市场对 X 财报怎么看", "X 社区讨论", "X 公司动态", "市场情绪", "最近怎么了", "X 最近新聞", "X 公告", "市場對 X 財報怎麼看", "X 社區討論", "recent news", "company filings", "market reaction", "what is everyone saying about X", "community sentiment", "8-K", "港交所披露", "earnings reaction".
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
Use when handling Jira issues, sprints, boards, links, fields, worklogs, attachments, or users, or on any Jira intent without a key (\"create/find a ticket\", \"pick a project\"). Auto-triggers on Jira URLs and issue keys (PROJ-123). Also use when MCP Atlassian tools fail or are unavailable for Jira Server/DC.
Conduct an IPPF Member Association (MA) accreditation desk review against the IPPF EN Internal Guidelines Accreditation Review (Cycle 4 / ARV cycle, where ARV means Accreditation Review, NOT antiretroviral). Use when Ane assesses an MA self-assessment against accreditation principles, standards or checks, writes reviewer conclusions in the desk-review Word template, or prepares pre-interview document requests and interview questions, including on a bare principle, standard or check number ('do principle 8'). Not for literature reviews (evidence-synthesis), interview or survey guides (instrument-designer), indicator design (indicator-designer), or any clinical antiretroviral 'ARV' question.
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.