Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Remove signs of AI-generated writing from academic medical papers. Use when editing or reviewing manuscripts to make them sound more natural and professionally written. Based on Wikipedia's "Signs of AI writing" guide, adapted for medical literature.
Renders a Structurizr workspace as a Claude artifact or a static site, using the Renderizr CLI. Use when the user wants to see, share, publish or hand over a C4 architecture model — "show me the architecture", "turn this workspace into an artifact", "publish these diagrams" — or mentions Renderizr, workspace.json or artifact.html
Create Tufte-inspired data reports and infographic dashboards as standalone HTML files. Uses EB Garamond for text, Monaspace Argon for numbers, Chart.js for interactive charts, and inline SVG sparklines. Produces publication-quality reports with 2-column narrative+data layouts, status dashboards, scroll animations, and responsive mobile support. Use this skill whenever the user wants to create a data report, activity dashboard, infographic, personal analytics page, health tracker visualization, or any document that combines narrative text with interactive charts and tables. Also triggers for "make a report like Tufte", "create an infographic", "build a dashboard", "visualize my data", or requests for beautiful data-driven documents.
Generate business documents — contracts, proposals, SOWs, NDAs, MSAs — with jurisdiction-aware clauses for US, EU, UK, and DACH. Use when starting client engagements, writing proposals, drafting agreements, or needing GDPR-compliant DPAs
Create, edit, and analyze presentations. Use when Claude needs to work with presentations (.pptx) to: (1) create new presentations, (2) modify or edit content, (3) work with layouts, (4) add comments or speaker notes, or perform any other presentation task
This skill should be used whenever a plan for non-trivial work is being produced, presented, or proposed (a feature, design, refactor, migration, or any multi-step task), including in plan mode and together with whatever planning skill produced the plan. It is the default way to deliver a plan: instead of a wall of text, it renders the plan as MDX to a scannable, self-contained HTML page (diagrams, phases, file-change maps, comparisons) via the `vplan` CLI. It applies when the user says "plan this", "what's the approach", "how should we approach X", "show me the plan", "make a visual plan", "render this plan", or asks for a plan with diagrams/charts, and when they want to review, approve, sign off on, or give feedback on a plan. Skip only for a trivial one-step change or when the user explicitly asks for plain prose
Codex-only writing and layout overlay for AI Berkshire investment research reports. Use whenever Codex creates, rewrites, revises, or critiques company/industry/fund research reports, especially long-form Markdown reports that need financial rigor, readable business mechanics, contrarian analysis, valuation-to-action guidance, investor-specific recommendations, restrained typography, and clear buy/hold/sell signals. Do not use this to modify Claude Code slash-command sources.
Use when the user explicitly asks to “review a National Natural Science Foundation proposal,” “simulate an expert review,” or “review an NSFC application.” Simulates a domain expert’s perspective to assess the NSFC proposal across multiple dimensions and provide prioritized issues and actionable revision suggestions. Not applicable when the user only wants to write or revise a proposal section (use the nsfc-*-writer skill series), only wants to learn about review criteria (answer directly), or has no explicit intent to review.
Orchestrates the full résumé workflow, from importing an existing résumé or interview through master résumé creation, tailoring to a JD, quality audits, and local layout adjustments. Use when users want to create, update, submit, or maintain a résumé without choosing multiple résumé skills themselves. Uses only user-confirmed facts; never submits, pushes, or overwrites version history automatically
Review writing for its intended reader, check common AI writing patterns, revise, request a second pass from a different model family, and check again. Trigger on /slopmonster, "humanize this", "de-slop this", "does this sound like AI", "fix this copy".
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for investigational products.
A workflow for handling chapter screenshots and illustrations while writing a book. Use to identify the screenshots needed for a chapter, provide step-by-step Claude Code prompts, define screenshot filenames and figure-number mappings, fill in image locations in local Markdown, clean author notes from the reader-facing text, and sync chapters and images to the correct places in Feishu documents. Trigger when the user mentions "book screenshots", "chapter illustrations", "figure-number mapping", "put it in the original text", "upload to Feishu documents", or "use the workflow from earlier".
A read-only tool for searching and reading cloud documents, spreadsheets, multidimensional tables, and knowledge bases (Wiki) via the Feishu Open Platform API. Use it to search Feishu for documents, spreadsheets, multidimensional tables, knowledge base spaces, or nodes, and read their contents. Also activates for: Feishu search, Feishu search docs sheets base wiki, Lark docs sheets base wiki search, search Feishu docs spreadsheets multidimensional tables knowledge base
Reviewer role. Opens rendered HTML, inspects every slide visually, fixes problems in custom.css or slides.html and rebuilds through build-html.sh. Use whenever the user says "review", "QA", "check slides", "inspect", "audit", "proofread", or wants feedback on a rendered deck.
Compile an academic Markdown manuscript into a journal- or school-compliant Word (.docx): specified typography, native OMML equations, three-line tables, cross-references, per-section page numbers, CSL bibliographies (GB/T 7714, APA, Nature, IEEE), and pre- and post-export quality gates. Export an academic Markdown manuscript as a Word document compliant with journal or degree thesis requirements: abstract, numbered equations, three-line tables, captions, cross-references, table-of-contents fields, and references. Use when the user wants a submission-ready .docx — thesis-to-Word conversion, thesis formatting, journal submission formatting, prepare submission docx — or a readable copy of a manuscript. Not for PDF, HTML or LaTeX output, slide decks or grant forms.
Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck', 'slides', 'presentation', 'pitch', or references a .pptx filename.
Write and iteratively refine PRD/需求文档 with a story-driven structure and strict staged confirmations (journey map alignment, per-story single-point confirmation, final generation gate). Use when the user asks to 梳理/撰写/完善 PRD、需求文档、用户故事、验收标准，并希望用 ASCII 线框图与 Mermaid（流程图/状态图/时序图）来减少歧义、共同完成文档。
Use for any operation on WPS 365 / AirPage / 智能文档 / kdocs online documents: creating documents, reading or searching block structures, inserting or editing paragraphs and headings, operating tables (merging cells, inserting rows), uploading images, adding or querying comments, or converting Markdown/HTML into blocks. Triggered by natural Chinese requests mentioning kdocs, AirPage, 智能文档, or 365.kdocs.cn—for example, “帮我在那个 kdocs 文档里加一段”, “查一下文档的块结构”, “创建一个新的 AirPage 文档”, “把这段 markdown 插进去”, “合并表格单元格”, or “往文档里加评论”. Do NOT use for local .docx/.xlsx files, WPS desktop app issues, Notion, Google Docs, or generic browser/script automation.
Migrate an existing documentation site (Mintlify, Docusaurus, Fumadocs, Nextra, Starlight, VitePress, VuePress, Docus, MkDocs, mdBook, Fern, GitBook, ReadMe, Redocly, Docsify, Jekyll (Just the Docs), GitHub Wiki, or any docs framework) to Blume, the markdown-first docs framework on Astro. Translate the source config to blume.config.ts, restructure content into Blume's filesystem-derived navigation, rewrite JSX callouts to directives, convert icons to Lucide, and inline snippets. Use when the user asks to migrate/convert/port a docs repo to Blume, or when the repo has a docs.json/mint.json, docusaurus.config.*, meta.json with fumadocs, _meta.* with nextra, an astro.config.* with starlight(), a .vitepress/config.* or .vuepress/config.*, an mkdocs.yml or zensical.toml, a book.toml (mdBook), a fern/docs.yml, a GitBook .gitbook.yaml/gitbook-docs.yaml, ReadMe _order.yaml files in docs/ or reference/, a Redocly sidebars.yaml or @redocly/realm dependency, an index.html that sets window.$docsify, a docus or @nuxt-themes/docus dependency, a Jekyll _config.yml (Just the Docs theme), or a GitHub wiki clone (Home.md with _Sidebar.md, [[Page Name]] links).
Manage documents, folders, and content in DingTalk Cloud Docs. Use when users want to create documents or files such as spreadsheets, mind maps, whiteboards, presentations, or multidimensional tables; search documents; read or write document content; create folders to organize documents; traverse folder structures; or precisely edit document block elements. Also use when users mention keywords such as cloud docs, online docs, DingTalk docs, or 钉文档. Do not trigger when users need to manage schedules, send messages, or handle approval workflows.
Use this academic writing skill to polish or translate academic writing with an explicit Nature, IEEE, Elsevier, or neutral profile. Selects a profile by explicit venue, journal allowlist, then unambiguous domain; reports uncertainty instead of guessing.
AI-powered financial analysis suite. Generates executive CFO briefings from QuickBooks exports (P&L, Balance Sheet, General Ledger, Cash Flow, etc.) with anomaly detection, burn rate, runway analysis, and scenario modeling. Also estimates codebase development costs with organizational overhead and AI ROI analysis. Triggers on: 'CFO briefing', 'financial analysis', 'cost briefing', 'expense review', 'runway analysis', 'burn rate', 'cost estimate', 'how much would this cost to build', 'development cost', 'Claude ROI'.
Review a resume like a professional resume writer AND an ATS (Applicant Tracking System) — produce an ATS score (0-100), a level detection (fresher / mid / senior), a breakdown of what's working, what's failing, the 7 Deadly Sins check, priority fixes, concrete before→after bullet rewrites, and missing keywords. Use this skill whenever the user asks to review, audit, critique, score, rate, roast, or improve a resume or CV, or types /resume-review, or drops a resume PDF with a job description. Trigger EVEN IF the user just says "look at my CV", "check my resume", "is this resume good", "why am I not getting interviews", "roast my resume", or shares a resume file without explicit review instructions — any interaction involving a resume file or CV should invoke this skill. Especially strong for DevOps, SRE, Cloud, Platform, and Infrastructure engineering resumes, but works for any technical resume.
Manage daily operations for Israeli freelancers (osek murshe, osek patur) - invoice aging with collection reminders, utility bill collection via browser automation, tax deadline alerts (VAT, Bituach Leumi, mkdamot, annual report), osek patur threshold monitoring, and organized accountant packages (havila). Use when a freelancer needs help tracking invoices, preparing documents for their accountant, monitoring their osek patur revenue ceiling, or staying on top of Israeli tax filing deadlines. Prevents missed VAT filings (which trigger automatic penalties), forgotten invoice follow-ups, and disorganized handoffs to accountants. Do NOT use for VAT return preparation (use israeli-vat-reporting), e-invoice generation (use israeli-e-invoice), or payroll/employee management.
Create high-quality Markdown weekly reports, work reports, summaries, introductions, and similar documents. If there is no draft, search the web and summarize; if there is a draft, organize, polish, and supplement it. Use when the user mentions a weekly report, work report, summary, introduction, performance review, or retrospective.
Captures conversations and supplied notes as Notion wiki pages, how-to guides, FAQs, decision records, or retrospectives. Use when saving or updating durable knowledge from existing context; use research-documentation when new source discovery and synthesis is the main task
GitHub dark-purple gradient deck — GitHub-dark #0d1117 + purple-blue radial ambient light + 60px grid mask, centered layout, purple pill labels, tricolor gradient title (#a855f7→#60a5fa→#34d399), GitHub-style code palette, purple left-border highlight blocks. Suited to developer workflow / MCP / Agent / dev tool tutorials, similar to GitHub Blog / Linear Changelog.
Generate and standardize an undergraduate system-design thesis from a real program/project. Use when the user provides source code, a repo, database/API evidence, screenshots, a school template, or asks for thesis drafting, chapter generation, Visio thesis diagrams, three-line tables, or thesis workspace checks
Manage DingTalk product capabilities, including AI tables, calendar, contacts, documents, bots, tasks, email, meeting notes, AI apps, approvals, logs, and DingTalk Drive. Use when users need to work with spreadsheet data, manage schedules and meetings, look up contacts, send message notifications, handle approval workflows, view meeting-note summaries, create apps, systems, admin backends, or business tools, view daily or weekly reports, or manage DingTalk Drive files.
Dark-terminal honest-review deck — #0a0c10 black background + 56px cyber grid + CRT vignette + scanlines, window traffic-light chrome, `$ prompt` command-line title, mint-green #7ed3a4 headlines, JetBrains Mono, stroke-only bar charts, blinking cursor, amber/green/red tier tags, dark code blocks. For CLI / agent / dev tool reviews (including trace, diff, benchmark).
A dark-background knowledge graph deck — #06060c→#0e1020 deep-night gradient, floating blur orbs, a cover SVG force-directed graph, rainbow-gradient titles, JetBrains Mono command-line highlights, and glass-morphism cards. Suited to launches for dev tools, CLI, knowledge graphs, and data visualization, with an “AI-native + sci-fi + warm colors” feel.
A cream blueprint architecture deck — cream-paper #F0EAE0 background, a single rust-red #B5392A accent, 48px blueprint grid mask, hard cards with 2px black borders, pipeline step boxes (one raised), a rust-red insight callout on the right, large Playfair serif text, and an SVG dashed feedback loop. No gradients or soft shadows; serious and print-friendly.
A soft macaron slow-living deck — cream #fef8f1 background with three soft-glow blobs, Playfair italic serif display titles paired with sans-serif body text, 28px rounded macaron cards (peach/mint/sky/purple/lemon/rose), Playfair italic 01-04 numbering, an SVG donut chart, and a chip+page top bar. Suited to lifestyle, personal growth, slow living, and emotional content, with a “magazine, handmade, not too techy” feel.
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.