Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Generate various documents based on the current project or code, including thesis sections, project overviews, key issues, and resume project descriptions. Use when users ask to generate thesis sections, project overviews, technical challenges, or resume project descriptions. For onboarding documents for new colleagues (new-hire guides, architecture docs, code walkthroughs, onboarding), use project-docs.
Multi-expert parallel analysis workflow that selects 3-5 domain expert subagents to analyze datasets in parallel, synthesizes findings into interactive HTML reports with charts, and exports to PowerPoint with one click. Requires Python packages: pandas, openpyxl, tabulate, chardet.
Product and technical document creation through guided discovery, including project PRDs, feature PRDs, feature design docs, audit reports, positioning docs, Design Docs, and ADRs, plus archiving of feature folders. Use when defining requirements, consolidating findings from external audits, feature proposals, strategy, trade-offs, or architecture decisions, or when archiving a feature. Not for running audits, UI design, implementation, or meeting notes.
Chinese Word document formatting toolkit for .docx/.doc/.wps workflows. Use when Codex needs to diagnose document formatting, fix mixed Chinese/English punctuation and spacing, apply official/academic/legal/custom presets, normalize tables and page numbers, preserve or output Word revision marks, convert plain text or Markdown into formatted DOCX, or batch/script document cleanup for Chinese official documents.
Structural and accuracy review of documents: gaps, clarity, completeness, organization, and claims checked against the code. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the next workflow step. For exploring new ideas from scratch, use brainstorming instead.
Translate local PDFs, including safe prose on image-only scans, into Vietnamese or another supported Latin-script language while preserving layout, formulas, tables, and figures. Use for PDF translation, OCR-assisted scan translation, batch translation, terminology-sensitive handoff translation, or diagnosing incomplete output. Do not use for targets requiring CJK, right-to-left, or complex-script shaping.
Show the user the agent's work on a research project and save iterations on the user's behalf. Scaffold rendering and deploy infrastructure (Quarto today, GitHub Pages, dev container), show the rendered output, save iterations. Doesn't handle research execution (use `asta-flows`).
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Claude needs to work with professional documents (.docx files), including creating new documents, modifying content, working with tracked changes, or adding comments.
Draft, revise, polish, humanize, and quality-check Chinese official documents and government-style practical writing (公文、党政机关公文、事务文书、申论应用文、人民日报风格政务表达), producing deliverable drafts with correct document type, format, restrained institutional tone, concrete facts, People's Daily-inspired expression discipline, humanizer-style AI-pattern cleanup, and reduced AI-flavored phrasing. Use when the user asks for 通知、通报、报告、请示、批复、函、纪要、决定、通告、议案、倡议书、工作方案、工作计划、工作总结、简报、讲话稿、发言稿、汇报材料、调研报告、宣传稿、公开信、感谢信、信访回复、理论评论、政策解读, or asks to 一键生成/润色/改写/降AI味/减少AI味/人味/自然表达/人民日报风格/检查格式/生成可交付公文.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Technical reference for writing or editing open-slide pages — file contract, 1920×1080 canvas, type scale, layout, palette/visual direction, assets, speaker notes, stepped reveals, page transitions, and morph transitions. Consult this whenever you are about to write or modify any file under `slides/<id>/`, including from inside the `create-slide` or `apply-comments` workflows, or for any ad-hoc slide edit. Triggers on phrases like "edit slide", "tweak this page", "fix the layout", "change the palette", "reveal one by one", "add a transition", "morph transition", "write the speaker notes", "generate the script / talk track", "preview / screenshot a page", "check how it looks", "investigate the slide framework", "how do slides work here".
Formats plain text or Markdown files by adding frontmatter, titles, summaries, subheadings, bold text, lists, and code blocks. Use when the user requests “format markdown,” “polish an article,” “add formatting,” or improve article layout. Outputs to {filename}-formatted.md
Load, validate, and use a user's private personal profile from Bitwarden CLI for form filling, PDF completion, applications, and identity/contact/employment/housing reuse. Use when an agent needs stable personal data backed by Bitwarden, language-aware profile values, a bundled schema for personal facts, or a safe workflow that materializes real profile values outside Git.
Create evidence-aware, interactive visual explainers as self-contained offline HTML. Use when a user asks to explain a concept, repository module, engineering trade-off, or incident with a diagram, walkthrough, ELI5 treatment, data/request trace, failure view, or teach-back. Do not use for a plain short answer, ordinary prose rewrite, generic website implementation, or unsupported claims presented as facts.
Clone any .pptx into your own deck — OpenAI gpt-image-2 mimics the layout, you supply the content. 10 bundled styles. Turn any .pptx template into your own PPT: gpt-image-2 mimics the layout, and you replace the content. Includes 10 curated styles. Claude Code / OpenClaw skill.
Convert Markdown to styled HTML with themes compatible with WeChat Official Accounts. Supports code highlighting, mathematical formulas, PlantUML, footnotes, callout boxes, and infographics. Use when the user asks for “markdown to html,” “md转html,” or “convert to html.”
A tool for generating Chinese software copyright application materials. Outputs the application form directly in Markdown and generates the source code, user manual, and design specification in LaTeX, compiling them into PDFs. Automatically analyzes project code and generates four documents: 60 pages of source code (30 pages each at the beginning and end), a user manual and design specification with headers and footers, and a Markdown application form. Checks consistency across information, including version numbers, bidirectional module coverage, and word limits. Suitable for software projects such as WeChat mini programs, web applications, mobile apps, and desktop apps. This Skill must be used when users mention software copyright, copyright applications, or copyright registration. It should also be used when users need copyright materials or documents prepared for any software project.
Robust URL-to-Markdown extraction for OpenClaw workflows. Use when the user wants to "extract/summarize/convert a webpage to markdown" (especially WeChat mp.weixin.qq.com) and web_fetch/browser is blocked or messy. Uses a cheap probe via web_fetch first, then falls back to the official MinerU API (via the local mineru-extract skill) and returns a traceable result contract with source links.
Retrieve translated patent claims from the 智慧芽 patent database. Trigger this skill when the user asks about patent claims or claim translations, wants to view claims in a specific language (Chinese, English, or Japanese), looks up patent claims by patent ID or publication number, analyzes claim text, or mentions claim translation, patent claim translation, PatSnap, or patent translation. Trigger it even if the user does not explicitly mention “patent claim translation,” as long as they need patent claims in a specific language.
Repair low-quality or awkwardly laid-out ID scan PDFs. Use when a PDF of a personal ID, passport, or driver's license needs page content rotated without changing the page orientation, scaled up to use more of the page without clipping, renamed with stable bronze/silver/gold filenames, self-checked for cut-off content, or opened locally for final review.
Review and analyze academic research papers. Use this skill when the user asks to review a paper, analyze a publication, summarize research, critique methodology, extract key findings, compare papers, check for numerical inconsistencies, or assess novelty and contributions of academic work. Also triggers when the user mentions reading a PDF of a paper, wants a literature review, asks about related work, or wants to improve a paper before submission.
Retrieve translated patent titles and abstracts from the PatSnap patent database. Trigger for requests to translate patent abstracts or titles, obtain patent content in another language, or look up a patent’s abstract or title by patent ID or publication number. Also trigger for patent abstract translation, patent title translation, PatSnap, patent translation, abstract lookup, or mentions of PatSnap or patent abstract lookup, even if translation is not explicitly requested.
Download full-text patent PDF documents from the PatSnap patent database using a patent ID or publication number. Trigger this skill when the user mentions patent PDF downloads, patent full text, obtaining patent files, publication number lookup, patent family PDF alternatives, bulk patent PDF export, patent PDF download, patent full-text document, patent file download, PatSnap, or patent PDF. Even if the user does not explicitly mention “PatSnap,” trigger this skill whenever they need to download or view patent PDF documents.
Use when asked to compress, tighten, shorten, condense, or de-slop a design doc, PRD, RFC, architecture note, or similar prose "without losing information". Removes only provable redundancy — filler, hedging, LLM-slop, restated content — never a fact, number, decision, or caveat, and flags every judgment call for the author. Returns a compressed document, a categorized removal log, and a shareable scorecard.
End-to-end document understanding for `.pdf`, `.docx`, and `.pptx` (auto convert to PDF). Use when users ask to read, summarize, extract, analyze, compare, audit, or fully understand document content with evidence-based chunk citations.
Investor pitch deck structure with a slide-by-slide framework, visual design rules, and data presentation. Covers the 12-slide framework, chart types, team slides, and common investor turn-offs. Use for: fundraising decks, investor presentations, startup pitches, demo days, grant proposals. Triggers: pitch deck, investor deck, startup pitch, fundraising deck, demo day, pitch presentation, investor presentation, seed deck, series a deck, pitch slides, startup presentation, vc pitch, investor meeting
Full-stack PlantUML expert: create PUML from descriptions, convert images to PUML (vision reverse engineering), and render locally (PNG/SVG/PDF) without internet. Supports macOS/Windows/Linux; automatically installs PlantUML, Java, and Python. Covers all 27 chapters of the PlantUML Language Reference Guide v1.2025.0 (607 pages): Sequence, Use Case, Class, Object, Activity (legacy+new), Component, Deployment, State, Timing, JSON, YAML, nwdiag, Salt/Wireframe, Archimate, Gantt, MindMap, WBS, Maths, ER, Common Commands, Creole, Sprites, Skinparam, Preprocessing, Unicode, and StdLib (C4/AWS/Azure/K8s/ArchiMate). Use for drawing diagrams, creating PUML, converting images to PUML, rendering .puml, debugging PUML, explaining PlantUML syntax, or any UML task
Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.
16:9 HTML deck in an editorial minimalist style. Warm cream slides, serif display type with grotesque body text, hairline rules, monospace metadata, generous macro whitespace, and one accent. Distilled from Leonxlnx/taste-skill `minimalist-skill`.
Image generation and presentations. Use when the user asks for images such as logos, icons, app assets, diagrams, flowcharts, architecture diagrams, patterns, textures, photo edits, or restorations, or needs a presentation or slide deck. Covers nanobanana CLI for image generation and Slidev for presentations.
Verify that every reference in a manuscript really exists and matches its metadata, catching hallucinated, corrupted or mismatched citations before submission. Use when checking a .bib file or reference list, after an AI assistant drafted citations, when a DOI may point to the wrong paper, when adding missing DOIs, or before camera-ready. Queries Crossref, OpenAlex and arXiv; zero dependencies.
Create or update a Jinkō document from markdown through the jinko-sdk, including headings, tables, code blocks, links to Jinkō project items, uploaded images, and links to existing Jinkō References. Use this skill whenever the user wants to turn local markdown into a Jinkō document, refresh an existing document from edited markdown, prepare markdown so Jinkō renders cards and images correctly, or cite existing project References.
Retrieve patent specification (description) data from the PatSnap patent database using a patent ID or publication number. Trigger when the user mentions patent specifications, full patent text, patent technical descriptions, embodiment details, PatSnap specification data, patent specification, patent full text, technical description, embodiment details, PatSnap, or patent detailed description. Trigger even if the user does not explicitly mention “PatSnap,” as long as they want to view the full specification or description for one or more patents.
Retrieve translated patent specification (description) text from 智慧芽. Trigger this skill when the user requests a patent specification translation, the full patent text in another language, a translated full patent text, or wants to view the Chinese, English, or Japanese version of a patent specification; patent specification translation, patent description translation, PatSnap, or patent translation. Also trigger when the user provides a patent ID or publication number and requests the specification/description in another language, or mentions similar intents such as “patent specification translation,” “description translation,” or “translate the full text.”
Creates polished single-file HTML/CSS/JS slide deck presentations with animations, keyboard/click/swipe navigation, and progressive bullet reveal. Use when the user wants to create a presentation, slide deck, pitch deck, or wants to present content as slides.
Create clear, comprehensive technical documentation for developers and users. Use when documenting APIs, writing user guides, creating tutorials, or setting up documentation sites. Covers API docs, user guides, architecture documentation, and documentation best practices.
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.