Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Use for critical thinking, or when the user wants a claim, plan or decision checked for weak spots: "is this right?", "what am I missing?", "poke holes", "sanity check", "devil's advocate", "red team this". Skip for execution-only tasks and wording edits.
Self-improving knowledge wiki with a vault of raw sources. Use when the user mentions 'curiosity engine', 'wiki', 'vault', 'knowledge base', 'ingest', 'iterate', 'refine', 'improve', 'evolve', 'curator', 'lint', or wants to add sources, query accumulated knowledge, check wiki health, or run autonomous improvement. Also triggers on 'add to vault', 'what do I know about', 'improve wiki', 'set up knowledge base', 'new knowledge base', 'run curator'. Use even without explicit naming — if the user wants to file something for later or asks about accumulated knowledge, this is the skill.
Conduct in-depth online research on a given topic and gather material for later content creation. Automatically detects available web search tools (WebSearch or MCP search tools) and falls back to DDGS when none are available. Outputs a structured Markdown digest with source citations.
Using structure-mapping theory, find apt analogies and relational metaphors for a scenario or the differences between two objects, preserving key relationships and explaining the increment and boundaries of transfer. Use when the user says “find an analogy,” “give me an example,” “what’s an apt metaphor,” “explain the difference between the two with an analogy,” “understand it in another context,” or invokes ljg-analogy. Not for explaining an existing analogy, purely rhetorical polishing, theoretical definitions, or treating an analogy as proof of fact.
Trigger this skill when multiple related documents need comprehensive analysis, extraction of shared viewpoints, identification of conflicts, and a unified overview. Typical triggers include but are not limited to: - the user uploads multiple judgments or rulings and asks for a summary of adjudication gist in similar cases - the user provides multiple contract texts and asks for the similarities, differences, and key variations among clauses - the user provides multiple laws, regulations, and judicial interpretations and asks for the evolution of the rules and points of application - the user provides multiple pieces of evidence and investigation records and asks for an integrated factual thread - the user provides several academic papers or research reports and asks for the consensus and disagreements in the research - the user asks to compare the viewpoints across multiple legal opinions. The core value of this skill: not simply compressing a single document, but building cross-document relational analysis, identifying commonalities and differences, and generating new integrated insights.
Goal-driven conductor for the whole idea-to-published-paper lifecycle. Takes a research idea plus experiments and a target ("submit to NeurIPS 2026", or "help me pick a venue") and runs a goal->plan->execute->verify->reflect loop. It plans the stages, invokes the right lifecycle skills in order (literature-review, write-abstract, preflight-check, simulate-reviewers, and the rest), checkpoints with the author before each stage, and re-verifies the live CFP via parse-cfp rather than trusting a cached profile. Use when a researcher says "take my idea to a submitted paper", "run the whole pipeline", "orchestrate the paper for venue X", "what's the plan from here", or "what's done and what's next". Copilot, not autonomous author. It stops to ask at every stage gate, never fabricates results or citations, and never submits. Trigger words - orchestrate, pipeline, end to end, whole paper, idea to submission.
Pachca — managing chats, channels and conversations. Use this skill when the user wants to create a channel, create a conversation, list or archive chats, add or remove participants, change participant roles, export chat history, or check chat settings. NOT for sending messages or replying in a thread. Use when: create channel, create conversation, create chat, add participant, remove participant, archive chat, participant roles, export messages, list chats, all workspace chats, channels. NOT for: send message, reply in thread, upload file, → pachca-messages, → pachca-users, full-text search of chats by name → pachca-search.
Orchestrated review of a PM artifact (spec, PRD, OKRs, roadmap, prioritization, strategy). Routes by artifact type to the right audits, auto-runs the always-relevant assumption check, and returns one prioritized report. Trigger when the user asks for a full review of a PM document, "review my spec/roadmap/OKRs", "is this PRD solid", or general PM feedback—but NOT when they name a single specific audit.
Conducts blameless postmortems that transform failures into learning opportunities by documenting timelines, quantifying impact, performing root cause analysis (5 Whys, fishbone diagrams), and defining corrective actions with owners and deadlines. Use when analyzing failures, outages, incidents, or negative outcomes, conducting blameless postmortems, identifying corrective actions, learning from near-misses, establishing prevention strategies, or when user mentions postmortem, incident review, failure analysis, RCA, lessons learned, or after-action review.
Drive your personal Microsoft 365 inbox from agents — read, send, sync, and run offline triage analytics that... Trigger phrases: `what's in my inbox`, `find emails from X`, `send an outlook email`, `follow up on email I sent`, `stale unread in outlook`, `who's emailing me most`, `use outlook-email`, `run outlook-email`.
Help writing PRDs, analyzing feature requirements, and planning roadmaps. Use when writing a PRD, analyzing feature requests, planning a roadmap, or when you need structured product thinking. Triggers on "PRD", "產品規格", "feature request", "roadmap", "功能分析".
Maintains project context and progress tracking across Claude sessions. Use at session start to load context, on session end to save progress. Triggers: load project context, save context, end session, what was I working on, switch to project, done for today.
Fetch WeChat Official Account articles (mp.weixin.qq.com) to local storage. Use when a user sends an Official Account link and asks to "fetch", "save", "store", "archive", "keep a record", or "convert to Markdown". Defaults to dual output: a cleaned-up Markdown version (for retrieval and citation) plus a fidelity archive of the original HTML (readable offline with a double-click, for retrospective verification). Defaults to zero-dependency direct HTTP fetching, falling back to a browser automatically on failure.
Research, score, and publish a weekly industry digest on any topic. Casts a wide net via web search (20+ candidates), verifies sources for AI-generated slop, scores each item on five parameters (Novelty, Relevance, Slopiness, Technical depth, Feasibility), selects the top items, and generates both markdown files and a Tufte-style HTML report. Use this skill whenever the user says "/weekly-digest", "run the weekly digest", "industry digest", "what's new in [topic]", "weekly roundup", "news digest on [topic]", "research what happened this week in [topic]", or any request to create a curated, scored summary of recent developments in a field. Also use when the user wants to monitor a topic area with quality filtering — the slopiness scoring is the key differentiator from a simple news search.
Create standalone beginner tutorial packages from a topic or supplied references, with adaptive research, course-style outline design, chapter visuals, and Markdown/DOCX/PDF/HTML exports. Use for textbook-like tutorials, course guides, teaching documents, or long beginner guides; not for quick answers, link summaries, pure diagrams, or file conversion.
Creates a new venue-profile YAML for venues/conferences/ from a conference CFP URL, validates it against venues/schema.yml, and preps the contribution PR. Use when the user wants to add a venue, contribute or refresh a venue profile, encode a conference's submission requirements (deadlines, page limits, blind level, template invocation, rebuttal format, submission system) as machine-readable YAML, copy a profile forward to a new year, or validate a profile before opening a pull request. Covers scaffolding the file, extracting facts from the live CFP, the DBLP/Semantic Scholar/Crossref alias table, the mandatory verified provenance block, schema validation, and PR-readiness checks.
Comprehensive survey and instrument design assistant supporting questionnaire construction, Likert scale design, question types (open/closed/matrix), response bias mitigation, sampling strategies (probability/non-probability), pilot testing, instrument validation (Cronbach's alpha, factor analysis), online survey tools (Qualtrics, REDCap, Google Forms), interview protocol development, focus group facilitation, mixed-mode surveys, and cultural adaptation of instruments. Use when designing a survey or questionnaire, building Likert scales, planning a sampling strategy, pilot testing, validating an instrument (Cronbach's alpha, factor analysis), developing an interview protocol, improving response rates, or working in Qualtrics or REDCap. For analyzing interview/focus-group data use alterlab-qualitative-methods; for qual+quant integration alterlab-mixed-methods; for test selection/power analysis alterlab-statistical-analysis; for IRB/consent alterlab-research-ethics. Part of the AlterLab Academic Skills suite.
Supervises theses and dissertations end to end — structure guidance from proposal through defense, chapter-by-chapter writing support (introduction, literature review, methodology, results, discussion), supervision strategies, committee management, defense and viva voce preparation, timeline planning, feedback integration, examiner-expectation guidance, and formatting (APA 7, Chicago, university styles). Use when the request mentions thesis, dissertation, supervision, defense preparation, viva, proposal defense, thesis structure, thesis chapter, literature review chapter, methodology chapter, results chapter, discussion chapter, thesis timeline, committee, thesis formatting, or dissertation proposal. Part of the AlterLab Academic Skills suite.
Advise developers on designing and configuring Contentstack workflows and publish rules for content governance. Cover stage design, transition restrictions, approval flows, publish governance, automation hooks, and common pitfalls. Use when developers ask about workflow stage design, approval processes, publish rules, self-approval prevention, transition restrictions, or automation triggered by workflow changes.
Build an insurance-grade home inventory from a folder of photos and receipts -- identifies items, pulls values from receipts, estimates replacement costs, organizes by room, and outputs the documentation an insurance claim actually requires. Update mode keeps it current after new purchases.
Point Cowork at your invoices and payments records -- builds an AR aging report, drafts escalating follow-up emails matched to each invoice's age and the client relationship, and runs as a weekly scheduled task so nothing slips past 30 days unnoticed.
Call DingTalk Open Platform APIs to search users or get user details, manage departments (search, details, sub-departments, user lists, parent department), send robot one-to-one messages, send group messages, list bots in a group, and query resignation records. Use when needing to search DingTalk users or departments, get user/department details, send robot messages, list group bots, or query resigned employees.
Provides structured formats and techniques for running productive group sessions, from standups to multi-day workshops. Covers format selection, agenda design, participation management, decision methods, and handling difficult dynamics. Use when running meetings, workshops, brainstorms, design sprints, retrospectives, or team decision-making sessions, or when user mentions facilitation, workshop design, meeting patterns, session planning, or effective collaboration.
Manage Linear.app work from the command line with the linearis CLI (bins linearis / linear), which outputs JSON: issues/tickets, projects, cycles (sprints), milestones, initiatives (roadmap), documents, labels, teams, users, and issue discussions/comments. Use when the user mentions Linear, a ticket identifier like ENG-42 or ABC-123, sprints, triage, or the roadmap, or asks to create, read, search, update, assign, comment on, or otherwise manage Linear issues and projects.
Write annual project applications for the National Social Science Fund of China (NSSFC), based on the 2025 official template of the National Office for Philosophy and Social Sciences, covering four categories: key projects (A), general projects (B), youth projects (C), and western projects (X). Provides a staged writing workflow: data tables, topic description (300 characters), topic rationale, research content, innovations, research foundation, budget estimate, anonymization of the loose-leaf form, and other modules; includes built-in social science literature search strategies and a quality self-check list. Tool-neutral, works with Claude Code / Cursor / Codex / OpenClaw / Gemini CLI. Trigger words: 国家社会科学基金、国社科、社科基金、NSSFC、哲学社会科学、重点项目、一般项目、青年项目、西部项目、社科申报、活页
Help with templates/snippets for the Obsidian Templater plugin. Use to help generate Obsidian templates from natural language, understand and debug existing tp.* snippets, and adapt vault notes and workflows to Templater when users mention Templater, tp.*, templater syntax.
Navigate and use the OpenAgreements legal content library — source-cited practice guides, review checklists, 50-state law surveys, and fill-ready agreement templates. Look up state-by-state legal guides, checklists, and law surveys, or fill standard templates (NDAs, cloud service agreements, SAFEs) into signable DOCX files. Supports Common Paper, Bonterms, and Y Combinator templates. Use when the user needs a practice guide, a review checklist, a law survey, to draft a legal agreement, create an NDA, fill a contract template, or generate a SAFE. Includes lawyer-reviewed practice guides; see openagreements.org/editors.
Orchestrated, idea-to-plan PM workflow. Establishes context once, then composes the PM generative ladder in order — problem → discovery → users → riskiest-assumption test → prioritization → spec → metrics — gating each step, enforcing evidence before the spec, and handing the result to product-review. Trigger when the user wants to go from a raw idea to a build-ready plan ("take me from problem to plan", "I have an app idea, where do I start", "turn this idea into a product plan", "plan a new product end to end") — but NOT when they ask for one specific PM artifact (let that skill trigger directly), and NOT for the strategy/launch arc (vision, competitive analysis, roadmap, GTM — offer those next).
Write or critique a product problem statement — turning a vague prompt, signal, or feature request into a clear, evidence-grounded, testable statement of the real problem before any solution. Separates the problem from solutions, symptoms, goals, and constraints; applies the always-true core (gap not feature, root cause not symptom, specific and measurable, grounded in evidence, bridges user and business) and gates context-dependent decisions (which definition tool, how much measurability, reasoned vs. validated cause, scope). Trigger when asked to write a problem statement, define or frame a problem, identify the "real/true problem," turn a request or metric into a problem, or sharpen a vague product prompt before solving.
Create or critique a product roadmap — outcome-oriented, theme-based, confidence-aware (Now-Next-Later) roadmaps tied to strategy, instead of dated feature lists. Gates format and detail by audience and planning horizon. Trigger when the user asks to build, write, review, or restructure a product roadmap, quarterly/annual plan, Now-Next-Later view, or roadmap presentation.
Step-by-step camera-ready prep for accepted papers — the error-prone final stage before publication. Use when a researcher says "camera-ready", "final version", or "my paper got accepted, now what", or mentions ACM eRights / rights form / TAPS / ORCID / DOI block, IEEE PDF eXpress / conference ID / eCF copyright form / Xplore, OpenReview final upload, de-anonymization, or extra camera-ready pages. Resolves the venue's rail from a machine-readable profile and walks it end to end across ACM eRights, ORCID, rights/DOI block, TAPS source upload, IEEE PDF eXpress, conference IDs, file naming, eCF exact-title match, registration/no-show, NeurIPS-style [final] recompile, and OpenReview upload. Generates an ordered checklist with deadlines and +page rules, and lints the final .tex for leftover anonymization and missing rights blocks via bundled stdlib-only scripts. Advisory — it prepares, explains, and lints, but never completes a form or submits anything.
Renders the paper-workspace (outputs + lifecycle progress) into a single self-contained HTML dashboard the author can open in a browser, and refreshes it on request. Use when a researcher says "show me an HTML view", "give me a dashboard", "can I see my progress in a browser", "visualize what's been done", "make an HTML report", or "update the dashboard". Offered as an option whenever a visual overview would help (it is opt-in, not generated unprompted), and re-run after each significant change so the page stays current. The output is one local dashboard.html with inline CSS — no network, no external assets, light/dark aware — listing every generated artifact by stage with clickable links and a recent-activity timeline. Trigger words - html, dashboard, browser view, visualize progress, html report, update the html.
Enterprise-grade autonomous research paper generation skill for AI coding agents — full papers, literature reviews, theses, whitepapers, surveys, policy briefs — with rigorous methodology, statistical validation, multi-style citations (Harvard / APA / IEEE / MLA / Chicago / Nature / arXiv-numeric), and rich visualizations. Activates on slash commands (`/research`, `/paper`, `/literature-review`, `/whitepaper`, `/thesis`, `/survey`, `/policy`) and on natural-language academic-writing requests. Runtime-neutral — works with Claude Code, OpenCode, Cursor, Cline, Codex, Aider, Amp, Antigravity, and 50+ agents via the `npx skills` installer.
Strategic roadmap management for GitHub repositories. Syncs ROADMAP.md with GitHub Issues and labels, bootstraps roadmap files from scratch, runs brainstorming sessions with boundary checking, and provides quick status summaries. Use when managing project planning, syncing roadmap state, or exploring feature ideas.
Reviews scientific documents for logical clarity, argument soundness, and rigor by auditing hypothesis-data alignment, claim-evidence chains, quantitative precision, hedging calibration, and terminology consistency across any document type. Use when reviewing scientific argumentation, checking claims vs evidence, auditing terminology, or when user mentions check clarity, review logic, scientific soundness, hypothesis-data alignment, or claims vs evidence.
Operate any desktop software using "screenshots + coordinate grid": capture a screenshot with a grid, let any multimodal LLM read out the target's coordinate numbers, then call click/type/keypress APIs to simulate how humans visually operate software. It can also record an operation once and save it as a reusable scenario template for direct reuse next time. Does not rely on the target software providing an API or CLI. Use it when: - Automating Windows desktop software (WeChat, heavily risk-controlled web pages such as Xiaohongshu/Douyin, phone emulators, games, any Windows program), especially software or elements that Playwright/CDP/CLI/application APIs cannot cover (such as hidden buttons, game screens, CAPTCHAs) - The user says things like "help me operate/click/type XX", "automate XX", "simulate clicks", "desktop automation", "RPA", "record operations", "save as a template", "run automatically next time" - Operating desktop elements or cross-process, cross-window elements (desktop icons, taskbar, tray, Start menu, file selection dialogs, cross-window drag and drop) As long as the target is a Windows desktop program that can be seen on screen and requires mouse and keyboard operation, this skill should be tried first even if it has no API, no dedicated skill, or an unclear automation path.
Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.
How to work in a Writing Pipeline project (the `writing-pipeline` starter pack): a three-stage drafting flow, ideas → drafts → published. Read when the project has these folders, OR when asked to capture an idea, start or revise a draft, review a piece before it ships, or publish it. Carries the stage flow and review behaviors so that guidance does not live inside template bodies or folder descriptions. Complements the platform `open-knowledge` skill; does not replace it.
Yandex search via the Yandex Cloud Search API v2 with substantive excerpts from the pages found (smart snippets) — material for an answer, not just links. Synchronous and asynchronous modes, result caching. Triggers: yandex search api, поиск в яндексе, выдача яндекса, serp яндекс, парсинг выдачи, smart snippets, смарт-сниппеты, инфоконтексты, выдержки страниц, найди в яндексе, что пишут в рунете.
Conduct deep research on any topic — get comprehensive reports with citations, key findings, and actionable insights in minutes. Use when user wants to "deep research", "research this", "investigate", "analysis report", "深度研究", "调研", "リサーチ", "심층 연구".
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.