Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Deep anonymization sweep for double-blind paper submissions, plus clean de-anonymization for camera-ready. Use when a researcher says "anonymize my paper", "double-blind check", "blind this submission", "remove author names", "did I leak my identity" — or, after acceptance, "de-anonymize" / "restore authors for camera-ready". Sweeps the whole leak surface, \author/\affiliation/\email/\orcid/\thanks, acknowledgments and grant numbers, hyperref pdfauthor and compiled-PDF metadata, first-person self-citations (rewritten to third person), GitHub/dataset/homepage links vs anonymized mirrors, LaTeX comments, .bib annotations, home-directory paths, and supplementary material (.git dirs, notebooks, LICENSE/AUTHORS files). Bundles a stdlib-only scanner (scan_anonymization.py, check ids shared with preflight-check) and a reversible-edit workflow (toggle + manifest) so every change is cleanly undone at camera-ready. Advisory only; never submits anything.
Create and edit Bento presentations — single-file .bento.html decks whose document is plain JSON in a "#bento-doc" script block. Use whenever the user wants a slide deck or presentation: starting from NOTHING (it downloads the latest Bento app from bento.page automatically), from source material, or by improving an existing .bento.html. Maps content to the right feature (charts, morph transitions, state slides, ken-burns, motion paths) instead of static text slides, then writes the document JSON in place. Full schema + recipes at https://bento.page/agents.md.
Query Google NotebookLM notebooks for source-grounded, citation-backed answers from user-uploaded documents. Manages notebook library, handles Google authentication, and supports smart discovery. Works standalone via /blog notebooklm or internally from blog-write and blog-researcher for Tier 1 research data. Falls back gracefully when not configured. Use when user says "notebooklm", "notebook", "query notebook", "ask notebook", "notebook research", "source grounded research", "document query", "notebook library".
Browse and search the CawPlan knowledge base: list/create datasets, list/upload documents in a dataset, and search for information across one or all datasets. Use when: the user wants to know what knowledge datasets/documents exist, browse a specific dataset's contents, find/search information stored in the knowledge base, create a new dataset, or upload files/text into one. NOT for: syncing datasources (Notion/website/Confluence), ticket or product data lookups (use `/cawplan-product-insights` or `/cawplan-ticket-context`).
Audit financial models and Excel workbooks for A-share analysis. Adapts the original audit-xls skill for Chinese financial modeling standards, CAS conventions, and A-share-specific checks. Triggers on "A股模型审计", "财务模型核查", "audit model China", "audit xlsx", "模型QC", or "check model [company]".
Apply standardized formats for internal business communications. Use for status reports, company newsletters, FAQs, and leadership updates. Use proactively when consistency in corporate communication is required. Examples: - user: "Write a 3P update for the week" -> use Progress/Plans/Problems template - user: "Draft a company-wide announcement" -> use newsletter format - user: "Create an FAQ for the new project" -> use internal FAQ guidelines
Sweep a contracts folder and extract every renewal date, auto-renew clause, notice window, and price-escalation term into a renewal calendar -- then create calendar reminders ahead of each notice deadline via Cowork's calendar write tools. The skill that stops auto-renewals from ambushing you.
Cowork-style sweep of a folder of receipts, statements, and expense exports -- categorizes every transaction, matches receipts to statement lines, flags policy violations and anomalies, and outputs a clean expense report plus a findings memo.
Point Cowork at a folder of medical bills and insurance EOBs -- matches every bill to its explanation of benefits, catches duplicate charges, balance-billing, and bills that ignore your insurance, then drafts the dispute letters and phone scripts. Most medical bills contain errors; this finds them.
Build a quarterly business review from a client folder -- reports, usage exports, support tickets, meeting notes, emails. Extracts delivered value with receipts, surfaces risks before the client does, and drafts the QBR narrative plus expansion asks. For agencies, consultancies, and CS teams.
Generates or updates a resumable cold-start handoff package from an in-progress conversation, review, debugging session, or investigation, with transcript materialization, verified structured artifacts, update-mode backups, and bounded review repair. Use when the user says create a handoff doc, save this for later, document what we found, update the resumption file, or prepare a fresh agent to resume without chat history.
Creates and checks conference research posters and short poster-session pitches. Use when the user asks to make a poster, prepare a research poster, adapt a paper into a poster, fit a poster to A0/A1/36x48in, check a beamerposter or tikzposter file, reuse paper figures, or write a 2-minute or 5-minute poster pitch. Bundled scripts resolve poster dimensions, inventory reusable figures, lint print-day problems, and time spoken pitches.
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.
Referee-side skill for Nature Portfolio manuscripts: write a referee report, inventory every ask and sub-ask in received comments, grade drafted replies, and test reply readability. Check methodology, statistics, reporting, reproducibility and data/code availability. Preserve referee wording, numbering and order; require one reply per ask with a direct opening answer and a manuscript location or explicit no-change rationale. Use for review this manuscript, what will reviewers attack, turn comments into a checklist, answer each comment, did I miss a point, would this reply satisfy the reviewer, 审稿、写审稿意见、模拟审稿、拆解审稿意见、逐个回复、逐条对照、有没有漏回、审稿人会不会接受、以审稿人视角检查回复、回复够不够直白. Use rebuttal-response to choose response stances, calibrate claims and assemble or audit the whole letter.
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".
Runs a two-pass paper reflection loop with a Researcher pass and a Writer pass. Use when the user asks to reflect on a paper, improve a draft, run a research-agent and writer-agent review, critique the paper before submission, find both technical and writing issues, or produce a revision plan. The Researcher pass checks claims, citations, evidence, venue fit, missing related work, and reviewer risk; the Writer pass checks framing, structure, abstract, related work, prose, tables/figures, and response clarity. Outputs a merged action plan with evidence, priority, owner, and next skill to run.
Generates annotated screenshot documentation for web apps and websites — local dev servers or live sites. Use when asked to "screenshot the app", "document the app", "visual docs", "screenshot documentation", "show me the app", "screenshot <url>", or "document this website".
Use this skill when a user asks how to generate, integrate, or implement a Word-like document editor in ASP.NET Core using Syncfusion. Trigger it for requests involving the Syncfusion ASP.NET Core Document Editor, ASP.NET Core-based editor integration, document editing and formatting, comments and track changes, working with tables and images, managing headers and footers, applying document protection, and building end-to-end document workflows in ASP.NET Core applications.
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.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like “the xlsx in my downloads”) — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
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.
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.
Decode a commercial lease before signing or renewing -- true all-in occupancy cost (base rent plus NNN/CAM plus escalations), the clauses that hurt small tenants (personal guarantees, relocation, restoration), and the negotiation asks landlords routinely grant. The lease is most SMBs' biggest fixed cost and least-read document.
Converts Excel (.xlsx) workbooks into Markdown so their contents can be accurately analyzed, summarized, searched, or extracted from. Use this skill whenever the user shares, references, or asks about a .xlsx file — even if they don't say "convert" or "markdown" explicitly. This includes requests to "read", "summarize", "review", "extract data from", "compare", "chart", or "analyze" a spreadsheet, workbook, budget, data export, or tracker. Always run the bundled conversion script to produce Markdown first; do not attempt to parse .xlsx content directly or write ad-hoc extraction code. Also use this skill for batch requests involving a whole folder of Excel workbooks. IMPORTANT: When the user references a folder or set of documents containing multiple file types (.pdf, .docx, .xlsx), invoke ALL three sibling skills — convert-pdf-to-md, convert-word-to-md, and convert-excel-to-md — so no file type is silently skipped.
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.
Fill in Word document form templates (.docx) with user-provided data. Reads a template containing tables with label→value cell pairs, detects all fillable fields, and outputs a completed document. Handles CJK/Latin mixed text with proper font switching. Use this skill when the user wants to fill in a form template, complete an application form, populate a Word table form, or automate document filling. Also trigger when the user mentions "填表", "填写表格", "fill form", "fill template", "表格填写", "申请表", "登记表", or has a .docx template with blank fields to fill.
Unified document parsing tool — converts DOC, DOCX, XLS, XLSX, PPT, PPTX, PDF, HTML/URL to Markdown. Supports full-text output, word count, line count, heading extraction, section extraction, and regex search. Use when the user asks to "read/parse/open a document", uploads .doc/.docx/.xls/.xlsx/.ppt/.pptx/.pdf/.html files, or provides a URL.
Convert text content into polished magazine-style HTML pages, with support for professional typography and multiple visual styles. Trigger scenarios: (1) the user wants to convert text/an article into magazine-style HTML, (2) the user mentions "magazine typography," "magazine design," "article layout," "professional typesetting," "text beautification," or "magazine layout," (3) the user needs an elegantly typeset HTML page, (4) the user needs to export the designed content to PDF. Supports 12 distinct visual styles and uses Tailwind CSS.
Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes. Covers renderer target selection, registry mapping, and platform APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output for several platforms or creating PDF reports, email templates, demo videos, or social images from one component spec.
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
Analyze HM Desktop PRD documents: extract requirement information, verify completeness, check chapter order (requirement source → requirement background → requirement value analysis → competitive analysis → requirement description), check KEP definitions, detect requirement conflicts, and generate a structured analysis report. Use for user requests to: (1) analyze or review PRD documents, (2) extract a KEP list from requirements, (3) check PRD completeness or consistency, (4) map requirements to module architecture, (5) verify PRD format compliance, (6) verify the completeness of the competitive analysis section. Keywords: PRD analysis, requirement extraction, KEP verification, completeness check, chapter order validation, competitive analysis check, analyze PRD, requirement extraction, completeness check, chapter order validation
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.
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.
Use when reading, adding, updating, or removing PDF annotations (highlight, free-text, stamp) or page objects (path/text/image) with Android's platform PDF APIs, or when saving those edits back to disk — the editing surface added in API 36.1 (PdfRenderer.Page) and SDK extension 18 (PdfRendererPreV.Page on API 31+), android.graphics.pdf.component. Covers the version gate, the open-edit-write workflow, and the id/render-flag/save contracts. Not for display-only PdfViewerFragment work, PdfDocument creation-from-scratch, form filling, or third-party PDF SDKs (iText, PDFBox, PSPDFKit).
STEP 1 of the PPTX-from-layouts pipeline. Profile a PowerPoint template to discover its real slide-master layouts and emit a layout catalog + render config. Use when the user wants to "use my own PowerPoint template", "see what layouts my deck has", "onboard a template", "profile this pptx", or before authoring slides against a custom (non-Inner-Chapter) template. Pairs with pptx-author (Step 2) and pptx-from-layouts (Step 3).
The reflection agent. Use it right after another skill produces an artifact such as a rewrite from polish-prose, a rebuttal, an abstract, a preflight fix, or a tailored draft to critique that output against the stated goal, the paper's .paper-memory/profile.yml, the relevant rubric, and past .paper-memory/lessons.md, then decide whether it actually improved. Trigger words include reflect, self-critique, did this get better, did my edit help, regression check, review my own output, iterate, refine, second pass, sanity-check the rewrite, and "is the new version actually better". Runs a bounded self-refine / Reflexion loop, guards against regressions, and appends durable, deduplicated, dated lessons to .paper-memory/lessons.md via a stdlib script so the toolkit gets sharper each paper. Reflection adds cost; it only pays off when there is a measurable target.
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.
Write and review technical text with project-aware ASD-STE100 Issue 9 guidance. Use for technical documentation, code comments, procedures, software text, safety instructions, and controlled-language reviews. Do not use for creative writing, casual conversation, or general translation.
Diffs a paper draft against a machine-readable venue profile and produces a four-part tailoring plan - contribution reframing for the chosen track (research vs applications/industry vs demo vs short/vision), a page-budget cutting plan, a template/documentclass switch plan (acmart, IEEEtran, NeurIPS-style, llncs), and an anonymization sweep matched to the venue's blind level. Use when the user wants to adapt, retarget, resubmit, or port a paper to a different conference, journal, or track; fit a paper into a page limit ("cut to 10 pages"); switch LaTeX templates ("convert IEEEtran to acmart"); anonymize for double-blind review; or asks "make this fit SIGSPATIAL/NeurIPS/ICDE/KDD", "which track should this go to", or "retarget my rejected paper".
Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when: reviewing academic papers, conducting literature reviews, writing research summaries, analyzing methodologies, formatting citations, or when the user mentions academic research, scholarly writing, papers, or scientific literature.
Convert Word (.doc/.docx/.docm), PowerPoint (.ppt/.pps/.pot/.pptx/.pptm/.ppsx/.ppsm), Excel (.xls/.xlsx/.xlsm/.xlsb), OpenDocument (.odt/.ods/.odp), RTF, EPUB, CSV, and PDF documents to clean GitHub-Flavored Markdown locally with the Any Doc CLI (npx -y @firecrawl/[email protected]): headings, GFM tables, slide structure, and footnotes in one pass. Use when a task needs the contents of an office document, spreadsheet, presentation, ebook, or PDF you cannot read directly. Do not use for generating, editing, or validating documents (use documents), for ebook packaging (use epub). For scanned or image-only PDFs, use hosted OCR only when the user explicitly authorizes whole-document upload; otherwise route to local OCR tooling.
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.