Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
This skill MUST be used for arXiv searches, arXiv URLs or paper IDs, and explicit requests to retrieve arXiv papers. It SHOULD be used as one source in general literature searches, preprint discovery, and related-work research when relevant to the topic. It MUST NOT treat arXiv as the only source for a general literature search. Triggers include arXiv, paper search, preprints, literature search, and related research.
Read and manage Asana tasks, projects, sections, comments, and workspaces. Use this whenever the user wants to list or search tasks, create or update a task, complete a task, comment on a task, move tasks between projects or sections, look up a project or workspace, or ask "what's on my Asana list" — even if they don't say "API". Also use it for any app.asana.com URL or an Asana task/project gid. Always start from this skill when interacting with this service — its bundled scripts and recipes are the fastest path.
Comprehensive retrospective analysis of 2025 for BidDeed.AI, Everest Capital USA, Life OS, and Shapira family achievements. Use when Ariel requests year-end review, 2025 analysis, annual retrospective, or wants to understand what was accomplished across all domains (business, family, technical) throughout 2025. Generates detailed analysis with metrics, visualizations, and insights across GitHub repos, Supabase data, Life OS tracking, and conversation history.
AI-native mentor and onboarding flow for the four independent Claude certification tracks in AI Engineering from Scratch. For learners who want to choose a Claude certification, prepare for CCAO-F, CCDV-F, CCAR-F, or CCAR-P, continue a certification path, interactively study the next lesson, run and verify hands-on labs, build and score artifacts, take a diagnostic or mock assessment, or shore up weak exam areas via Claude Code, Codex, ChatGPT, Cursor, or another agent on GitHub.
Fetches structured public web data through Crawlora's hosted REST API, including broad search, bounded web crawls, and durable cross-corpus research jobs. Calls require a user-provided API key and successful requests may consume credits. Use for public prices, listings, reviews, transcripts, SERPs, trends, financials, and places.
Generate daily Tech & GNSS news digest blog posts for cheng-blog. Use when user asks to create a daily news digest, generate tech news, or mentions "/daily-news". Sources news from Bloomberg Tech YouTube channel (primary), with 3-day lookback for weekend coverage. Creates MDX posts with Tech News and GNSS News sections. GNSS news sourced from Inside GNSS, GPS World, and major company newsrooms (Trimble, Hexagon, Topcon, etc.).
Use this skill when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or industries, or reviewing literature or studies and (2) synthesizing that research into a comprehensive, narrative report. If you're planning to search the web or internal knowledge bases, consider using this skill. This skill coordinates research subagents, so use it only when you have a tool for spawning subagents (the Agent or Task tool); otherwise, research the question directly.
Deep research expert for building comprehensive knowledge maps from first principles. Use when the user wants to deeply understand a topic — its origin, the problem it solves, the foundational theory, the architecture, and future trajectory — all grounded in primary sources.
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. This skill MUST be used instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. MUST NOT be used for content already served as Markdown; identify it by the response content type and actual body rather than the URL suffix, and read it directly with WebFetch or curl.
ElevenLabs speech-to-text with Scribe models and forced alignment via inference.sh CLI. Models: Scribe v1/v2 (98%+ accuracy, 90+ languages). Capabilities: transcription, speaker diarization, audio event tagging, word-level timestamps, forced alignment, subtitle generation. Use for: meeting transcription, subtitles, podcast transcripts, lip-sync timing, karaoke. Triggers: elevenlabs stt, elevenlabs transcription, scribe, elevenlabs speech to text, forced alignment, word alignment, subtitle timing, diarization, speaker identification, audio event detection, eleven labs transcribe
Feishu assistant: messages, documents, knowledge base, contacts, calendar, group chats, tasks, Bitable (Base), and email. Use this skill when the user mentions Feishu-related operations (sending messages, writing documents, searching the knowledge base, viewing group chats, managing tasks, working with Bitable, checking email, sending email, inbox).
A Feishu knowledge base document management tool. Supports viewing the knowledge base directory structure, creating and saving documents, and reading multidimensional table content. Triggers when the user says "save to Feishu", "write to the Feishu knowledge base", "publish to Feishu", "view the Feishu directory", "read a Feishu table". Suitable for syncing Obsidian documents to the Feishu knowledge base, or reading Feishu multidimensional table data.
Make dense or complex information easier to understand, navigate, remember, and act on through clear layers, concrete examples, and visible progress. Use when the user explicitly invokes Focus Friendly; requests focus-oriented simplification, chunking, pacing, mapping, or reorientation; reports overwhelm, trouble reading or focusing, task-initiation difficulty, or losing their place in the current task; asks whether those difficulties prove ADHD; or asks for help navigating long, structurally complex material that genuinely needs a map. Do not invoke merely because a request mentions ADHD or asks for summarization, teaching, planning, research, or routine coding; those tasks need an explicit focus or navigation signal.
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
Searches Indeed job postings and pulls single job listings via the Crawlora API — keyword + location search, location autocomplete, and job detail by job key — returning clean JSON. Use when the user wants to search Indeed for jobs, look up location suggestions for an Indeed search, or fetch the full detail of a specific Indeed posting.
Use when you need to act on a known political landscape — building coalitions, persuading specific people, or maneuvering to get a decision approved. Assumes you already know who the stakeholders are (if not, use stakeholder-discovery first to map them).
Initialize a structured Obsidian-style workspace for learning, research notebooks, papers, academic applications, talks, test preparation, theory, and similar note-centric knowledge work. Use when the user asks to set up, start, initialize, scaffold, or bootstrap a vault/workspace for work organized primarily through notes and written artifacts. Do not use for software repositories, software applications, experiment codebases, or other coding projects. Ask one short intake batch covering the work and its definition of done, project title plus confirmed target directory, and any differences from the typical case. Then use a ready template as-is, adapt the closest template while keeping its contract internally consistent, or synthesize a lean bespoke vault when none fits. Write only into the confirmed target vault; never modify this skill's templates during a run. This skill creates structure and routing, not the downstream content itself.
Use when a task needs a real iPhone — operating iOS apps that have no API (Apple Health, banking, IM apps), exporting on-phone data, tapping/typing/scrolling on the phone, or taking phone screenshots. Replays saved per-app flows from the iphone-use-flows registry in one call and offers to save new ones after multi-step tasks. Drives the iphone-use daemon through its custom XCTest device runner, HTTP agent API or MCP server.
Answer from the knowledge bundle. Use when the user asks what they/the project know about something, wants to look something up, explore connections, or compare things that live in a knowledge/ bundle — and when any task would be informed by an existing bundle, consult it here before answering from scratch. Navigates by progressive disclosure and files valuable answers back so the bundle compounds.
Use KMSG to read, watch, and send KakaoTalk messages safely from a coding agent. Use whenever the user mentions KakaoTalk or kmsg and wants chat discovery, recent messages, monitoring, text or image delivery, setup checks, or CLI troubleshooting. Do not use for other messaging platforms or private KakaoTalk protocol work.
Linear API integration with managed OAuth. Query and manage issues, projects, teams, cycles, and labels using GraphQL. Use this skill when users want to create, update, or query Linear issues, search for tasks, manage projects, or track work. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Requires network access and valid Maton API key.
Read, analyze and summarize academic literature (PDF papers), producing structured literature summary notes. Core capabilities: paper metadata extraction, research question identification, methodology review, experimental result analysis, personal evaluation generation, and cross-comparison of multiple papers. Supports Chinese and English papers, single-paper close reading, and batch literature reviews. Use this skill when the user provides PDF paper files, asks to read literature, summarize a paper, do a literature review, paper summary, close reading of a paper, paper summary, paper review, read a paper, read paper, take a look at this paper, analyze this article, what is this paper about, what is the paper's method, make literature notes, batch read papers, or compare these papers. Handles .pdf files.
Use when the user wants a structured, saturating literature survey on a question — not a one-shot summary, but an evidence/contradiction matrix (sources × claims) built by iterative search until coverage stops growing. Each round expands the search (new sub-topic queries plus citation-graph walks), admits new sources, extracts their claims with verbatim snippets, and records where every source stands on each claim (supports / contradicts / qualifies); the feedback signal is how many new matrix-changing sources a round adds, and it stops at saturation, patience, or budget. The output is the matrix plus a synthesis of consensus, disputes, and gaps, every cell backed by a real citation. Not for grading a written proposal against the literature (that is a proposal-evaluation task) and not for generating new hypotheses — this maps what the literature already says.
Conduct market research, competitive analysis, investor due diligence and industry intelligence, with source citations and decision-oriented summaries. Use this skill when the user needs market sizing, competitor comparisons, fund research, technology scans, or research to support business decisions.
Use the "demand-signal backward inference" method to find part-time or side-hustle opportunities in the AI era — don't search for "teach you to make money" posts (those are polluted sources from course sellers fishing for followers), but instead look at interest-neutral demand signals such as industry reports, hiring data and procurement data, infer opportunities an individual could supply, and cross-validate with multiple independent signals; each opportunity then goes through an anti-scam + timeliness rubric. Trigger words: "help me find opportunities" / "find AI part-time work" / "what can make money" / "money find" / "find side hustles". Prerequisite: requires .money-state.json (if absent, first route to money-init).
Status dashboard for the cheat-on-money skill. Shows the user profile, candidate opportunities and their anti-scam verdicts, currently executing opportunities and progress, review records, and suggested next steps. No side effects; can be called at any time. Trigger words: "money status" / "my current progress" / "dashboard" / "money status" / "what should I do now".
Query the user's own Mio Note meeting minutes: group list, minutes list (filter by time/keyword/group), minute details (AI summary/key points/conclusions/user notes/speakers), and original transcripts (speaker-separated, segment-by-segment transcription, usable for re-summarising, extracting action items, and quoting exact words). Applies to scenarios such as the user asking "which meetings did I have last week", "summarise this month's meetings in group XX", "search for meetings about xx", "what were the exact words said about X in the meeting", or "help me re-extract the action items/decisions from this meeting".
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. This skill MUST be used when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. This skill MUST be used when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.
Mandatory protocol for operating the MyObsidian vault with the Obsidian CLI. Whenever the user mentions Obsidian, vault, knowledge base, notes, Daily, recording, save to, search my, help me find, note down, save, organize notes, view notes, in my knowledge base, this skill must be used. Do not use file tools to operate the vault directly — the CLI handles wikilinks, frontmatter, and Daily paths automatically.
This skill should be used when the user asks to "manage Obsidian vault", "create a daily note", "move notes without breaking links", "search vault content", or "organize Obsidian notes". Automatically activates when working with Obsidian vaults, markdown notes with [[wiki-links]], daily notes, templates, or tags. Not for general markdown editing outside Obsidian vaults.
Karpathy-style LLM Wiki with multi-vault sqlite registry and Socratic wizard. Also addressable by the short alias OMW. Manages multiple knowledge vaults (markdown or Obsidian). On invocation, infers user intent from registry state — first-time users get a setup wizard, returning users go straight to operations. Supports memo-mode (lightweight notes) and wiki-mode (Karpathy's raw/wiki/index/log pattern with ingest/query/lint). Trigger phrases — English "open my wiki", "ingest this", "find a note about X", "what does my wiki say about X", "omw", "use omw", "/omw"; Korean "위키 열어줘", "이거 정리해줘", "X 관련 노트 찾아줘", "위키에 물어봐", "오엠더블유", "오엠더블유 켜줘". Also fires when the user pastes long-form content and asks to save it.
Academic writing specialist for publication-grade English prose. Drafts, revises, and audits essays, reports, analysis sections, executive summaries, conclusions, and literature reviews while enforcing sentence-structure variation, high-frequency academic verbs, calibrated hedging, and anti-AI stylistic compliance. USE for academic writing, essay polish, paragraph rewrite, prose revision against any rubric tier (HD/D/C, A/B/C, top-band/mid-band, etc.), anti-AI audit, reverse outlining, claim-evidence mapping, and rubric enforcement on assignments.
TRIGGER THIS when conducting performance reviews, writing manager feedback, creating self-assessments, building peer feedback, developing PIPs, creating development plans, or handling difficult performance conversations. Helps write constructive, specific, actionable feedback that develops performance and documents performance management appropriately.
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.