Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Sprint planning and agile workflow specialist. Breaks epics into user stories, estimates complexity using story points, plans sprint iterations, and tracks velocity. Trigger keywords - sprint planning, user story, story points, velocity, backlog, sprint, epic breakdown, estimation, burndown, agile planning.
How to work in artist directories — including creating, enumerating, and editing them. Use when creating or onboarding a new artist ("create artist", "onboard X", "add this artist", "set up a new artist") — this skill scaffolds the artist's `RECOUP.md` checklist file and drives the multi-step setup from it. Use when adding or updating artist context (identity, brand, voice, audience), adding songs, organizing files inside an artist directory, or figuring out where something belongs. Also use when the account asks inventory questions like "what artists do I have", "list my artists", "which orgs am I in", "what's in this sandbox" — the filesystem tree is the authoritative answer. And use when the account mentions an artist by name and the task involves their files, context, or content — even if they don't say "artist directory." This includes tasks like researching an artist, creating content for an artist, updating an artist's brand, or adding a face guide.
实习.skill / get-job.skill: an end-to-end job search skill covering role research, resume rewrites, and interview preparation by round. Suitable for job searches, internship applications, campus recruiting, fall and spring recruiting, summer internships, experienced hiring, changing jobs or careers, cross-disciplinary applications, international student job searches, and preparation for roles such as product manager, operations, marketing, consulting, AI product, AI Coding, data analysis, and technical positions. Core capabilities: ① Use WebSearch to research companies, job descriptions, business lines, competitors, interview reports, hiring processes, and implicit requirements. ② Tailor resumes to target roles with JD matching, ATS keywords, experience selection, STAR/CAR rewrites, translation of transferable skills, and docx resume generation. ③ Prepare for interviews by actual round, covering confirmed or high-confidence rounds such as initial, business, technical, manager, HR, and recruiter screens; probe each resume bullet, develop project scripts and self-introductions, practice communication, run mock interviews, prepare questions to ask, and build post-interview review question banks. Use for resume revisions and optimization, JD matching, interview preparation, interview report analysis, mock interviews, self-introductions, presenting project experience, handling resume follow-up questions, landing a major-company offer without an elite university background, addressing a mismatched background, AI product internships, operations internships, and campus recruiting for product manager roles. Quality safeguards: never fabricate experience or alter hard facts subject to background checks; audit all strong claims against evidence; grade search sources by market and A/B/C/D; do not assume a fixed interview sequence; run quality gates and a coverage matrix before delivery to avoid missed bullets, label leakage, and overstatement.
Open or rebuild the video-lens gallery index — your personal library of saved video summaries. Use this whenever the user wants to browse, open, or search saved video reports: "show my gallery", "open video library", "browse saved videos", "build gallery", "what videos have I saved", "show my video notes", "my video summaries", "find my saved summary for [topic]", "rebuild the index", "show video-lens index", "backfill metadata", "update index".
A generator for line-by-line annotations of classical Chinese, combined layouts, chapter theme diagrams, and full-chapter interpretations. Arranges the source text, word and phrase annotations, sentence explanations, an unlettered illustration at the top, and the chapter interpretation into one readable, long PNG. Use when the user invokes ljg-classic or requests line-by-line annotations, color-coded interlinear notes, chapter interpretations, illustrated classical Chinese handouts, or chapter illustrations for classical Chinese prose, poetry, or the Four Books and Five Classics. Not for translating a single line of classical Chinese, writing only modern prose, or creating generic content cards.
Fact-check a teaching claim against sources so the learner can trust the single interface. Use when the user runs /learn-verify or /skill:learn-verify, or says fact-check, verify this, is this true, source this, don't hallucinate, or when a teach/plan step needs a claim checked before it is taught as fact.
Map the edge of the learner's understanding with a short graded quiz. Start broad, then binary-search every strand a lesson will need. Use when the user runs /probe or /skill:probe, or says quiz me, pretest, what do I already know, diagnose my understanding, probe me, or find the edge before teaching
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's inferences and guesses quarantined away from the user's own phrasing, so the user verifies what the model believes, not just what it doubts. Use when the user says "let me think out loud" or wants to ramble a bit before building anything, when a message opens with a speech-to-text preamble like "switching to voice, sorry for typos", when input is a long weakly punctuated stream with restarts and mid-message reversals ("actually no, wait, scrap that idea entirely"), or when the user asks to be interviewed about a fuzzy half-formed idea. Includes an optional capture mode for rambles spread across several messages and an optional targeted interview
Interview the learner and write .alvar/LEARNER.md so one teacher can fit one mind — pace, voice, solid ground, and how they want to struggle. Use when the user runs /learn-profile or /skill:learn-profile, or says how I learn, learning philosophy, teaching style, set up tutoring, or install my learning preferences
Draft, send, reply to, or forward email through the connected AgentMail MCP server. Use for ANY request to send, reply to, or forward mail — even a quick one-line send or a simple forward that looks like a single tool call; the sending rules apply regardless of task size. Also use to compose messages, create or schedule drafts for review, or send to named recipients; do not use for reading or triaging mail (agentmail-check-email), inbox administration (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
Generate professional email templates for various business scenarios including sales outreach, customer support, internal communications, follow-ups, and apologies. Creates personalized, tone-appropriate templates with subject lines and formatting. Use when users need to write business emails, cold outreach, or professional communications.
Advanced WeRead advisor. Built on the atomic APIs of the underlying weread skill, it provides four workflows: personalized advanced recommendations based on completed books (advisor), a progressive reading list from introductory to cutting-edge for a chosen topic (path), distilling scattered highlights into reading notes and summaries (alchemy), and quarterly or annual reading reviews with articles ready to post on social media or WeChat Official Accounts (review). Its core method is “cross-analysis of bookshelf and notes”—the bookshelf reveals interests users actively categorize, while notes reveal what they’ve actually read versus what they’ve only shelved. Trigger when users say “recommend a book,” “what should I read next,” “what should I read,” “I want to understand field X,” “organize my notes,” “what did I remember from this book,” “what did I read this year,” “reading review,” or “annual review.” Also trigger if they simply say “I don’t know what to read,” “any related books,” “help me check if I finished this book,” or “am I familiar with this field yet.”
Accelerate software development with Linear project management and MCP server integration. Master issue tracking, project workflows, and development automation for frontend, full-stack, and mobile applications. Includes comprehensive MCP tool usage, workflow patterns, and development best practices.
Use this skill when users request “微信监听” (WeChat monitoring), “消息提取” (message extraction), “Agent 开发” (Agent development), “wxauto”, “Accessibility API”, “UI 自动化” (UI automation), “输入框控制” (input field control), or “Platform Agent”, or mention “微信自动化” (WeChat automation), “消息监控” (message monitoring), or “WeChat monitoring”. Use it to develop WeReply’s Platform Agent (Windows wxauto or macOS Accessibility API), implement WeChat message monitoring and extraction, input field control, and Agent error handling.
Direct-connection automation for personal WeCom accounts. Built on the Wechaty framework, it supports receiving WeCom messages, automatically accepting friend requests, knowledge-base Q&A, and alerts for human intervention. Suitable for personal WeCom bots and automation assistant scenarios.
Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.
Set or remove aliases for Mo Wen UIDs, and use aliases to look up Mo Wen UIDs. A Mo Wen UID can have multiple aliases. In natural-language scenarios such as “get the latest Mo Wen notes by ‘Lao Chi’” or “view ‘Er Ye’s’ profile on Mo Wen,” if ‘Lao Chi’ or ‘Er Ye’ has been identified as a person’s name, first try using the `remark` command to look up the corresponding UID, then continue with the next steps. Trigger when setting, removing, or looking up aliases.
Manage a task backlog through the tasks-axi CLI - add, list, show, start, and complete tasks; track blocked-by dependencies, structured holds, and a ready queue; prune and normalize a hand-editable backlog.md. Use whenever a task touches backlog or task state: filing or dispatching work, recording a PR or report on completion, finding dispatchable or held work, or trimming the Done list.
Use quando o usuário enviar uma ideia, pensamento, necessidade, oportunidade ou texto livre para guardar, capturar, anotar ou retomar depois. Preserve o input integral, faça pré-processamento silencioso e crie imediatamente um arquivo timestampado em `specs/inbox/`. Não faça perguntas, não peça confirmação e não crie backlog, spec, tarefas, testes ou código.
Alibaba Cloud Bailian Knowledge Base Retrieval Tool. Use HTTPS API to query and retrieve knowledge base content. Use when: User needs to query knowledge base, retrieve document content, or answer questions based on knowledge base. Prerequisites: (1) Configure DashScope API Key (2) Activate Bailian Knowledge Base service.
Search academic papers via the OpenAlex API for open citation data, institutional affiliations, and funding information. Use when the user says "openalex search", "search openalex", "open citation graph", or wants comprehensive academic metadata beyond arXiv/Semantic Scholar
Academic paper search powered by OpenAlex -- the free, open catalog of 240M+ scholarly works. Use when the user needs to find academic papers, research articles, literature for a topic, citation data, author publications, or any scholarly source. Triggers on: 'find papers on', 'academic research about', 'what studies exist', 'literature review', 'find citations', 'scholarly articles about', 'who published on', 'papers by [author]', 'highly cited papers on', any request for peer-reviewed or academic sources. Also use during deep research when you need to ground findings in academic literature. Do NOT use for general web searches -- use web-search for that.
Turns any source artifact (spec, discovery, research, GTM plan, experiment results, retro, or raw notes) into one canonical master document plus a set of audience-tailored briefings, each re-pitched to a stakeholder lens (executive, board, engineering, UX, PMM, sales, CS, legal, data, or a custom audience). Every briefing is a traceable projection of the master, so the versions never disagree. Use when one piece of work must reach several audiences who each need a different framing, decision, and level of detail.
Write, edit, and review Japanese. Identify literal translations of English phrasing, overuse of noun-ending sentences, translation-like expressions such as “〜どうぞ” and “〜まで。”, wordy constructions, excessive katakana, and parentheses, colons, and dashes within sentences, then revise them into natural Japanese. Use for writing, editing, and proofreading Japanese responses, commit messages, PR descriptions, documentation, and UI text, and when the conversation is in Japanese.
Design, build, and maintain comprehensive knowledge bases. Bridges document-based (RAG) and entity-based (graph) knowledge systems. Use when building knowledge-intensive applications, managing organizational knowledge, or creating intelligent information systems.
Generate comprehensive disease research reports covering genetics (causal genes, GWAS, OMIM), pathways (Reactome, KEGG), drugs (existing therapies, repurposing candidates), clinical trials, epidemiology (prevalence, incidence), and phenotypes (HPO). Use for full disease overviews, comprehensive disease characterization, and orphan/rare-disease profiling.
Runs a fast pre-build risk review on a product idea, feature request, or scope change, naming the single assumption most likely to make it fail and returning a clear verdict (build small, validate first, pivot first, or don't build yet) with a no-code validation step. Use before committing build effort, when triaging whether to honor a feature request, or when deciding whether to expand scope, ahead of writing a PRD. For a launched product's pivot-or-persevere decision, use iterate-pivot-decision instead.
Create, list, inspect, update, or delete AgentMail inboxes through the connected MCP server. Use for ANY inbox lifecycle request — even a quick list-inboxes or a simple delete; deletion safeguards apply regardless of task size. Also use when the user asks for a new agent email address, wants inbox details changed, or removes an inbox; do not use for sending mail (agentmail-send-email), reading or triage (agentmail-check-email), or MCP connection setup (agentmail-mcp).
Thin router for Pipefy build and configure asks: map user intent to the correct domain skill (pipes, automations, AI agents, iPaaS, portals, etc.). Use when the user wants to create, build, configure, or integrate something in Pipefy and you need to know which skill to open. Do not use this skill as a delivery playbook — if the user already has a building skill or a detailed build prompt, follow that for how to build; use this skill only for which Pipefy domain skill to read.
Official Quark Drive Skill for file uploads and downloads (with resumable transfers), file sharing and saving, updating and querying saved shares, cloud drive file search, bulk renaming and batch undo, file organization and moving with undo, photo organization, AI assistant (file summaries and knowledge Q&A, supporting tens of thousands of files), and membership activation links. Use when the user asks to bulk rename current search results, rename after describing the scope and naming rules in one sentence, undo the previous bulk rename, activate or renew Quark Drive membership, or perform other Quark Drive operations and identity verification.
Plan optional Defuddle extraction and retain already available local source files through reviewed filesystem capture. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion. Network extraction remains unavailable until an enforcing adapter is verified.
Refer to this when eliciting users’ tacit knowledge through dialogue (active listening, interviews, clarifying vague answers, exploring past decisions, challenging assumptions, reconciling contradictions, eliciting motivations, and refining thinking). Integrates eight techniques—Rogers-style listening, DICE probing, CDM, devil’s advocacy, dialectical inquiry, motivational interviewing OARS, narrative elicitation, and Socratic questioning—with a situational selection guide and shared rules.
Use when creating a new Make scenario or editing an existing one — finding modules, connections and account-dependent values, wiring the flow, saving through scenario_create or scenario_patch. Not for explaining, running or debugging a scenario, or for API-call shells.
Founder-mode executive team. 13 cs-* C-suite agents (CFO, CMO, CRO, CPO, COO, CHRO, CISO, GC, CDO, CAIO, CCO, VPE, Chief of Staff) and 21 /c-level-agents:* slash commands for forcing-question office hours, multi-role boardroom deliberation, strategic sprint pipeline, and meta routing. Use when the founder needs a virtual executive team, when invoking /c-level-agents:* commands, or when orchestrating multi-role decisions.
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.