Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Contract review skill that adds comment-based issue annotations without changing original text. Enforces a four-layer review (entity verification, basic, business, legal), writes structured comments (issue type, risk reason, revision suggestion) with risk level encoded via reviewer name, and generates a contract summary, consolidated opinion, and Mermaid business flowchart (with rendered image). Output language must follow the contract’s language
Score a written grant proposal against the donor's published award criteria (SCORE mode), or compare that scoring against the donor's own Evaluation Summary Report (CALIBRATE mode). Use when Ane asks how a donor would score an application, whether it passes the threshold, where points would be lost, or provides a call document and a submitted proposal. Distinct from /proposal (writes proposals to donors), procurement-offer-review and tor-procurement (the buying side, supplier offers against a ToR), accreditation-desk-review (MAs against IPPF standards), and check-deliverable (a QA gate, not a scored assessment).
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill `brutalist-skill` (Tactical Telemetry mode).
Convert legal texts (statutes or legal cases) into properly formatted Markdown and remove redundant promotional content. Use this skill when users need to process statutes (such as civil or criminal codes), organize legal cases (such as Supreme People’s Court model cases or judicial documents), or format pasted text as a legal document. Note: This skill handles formatting and content cleanup only; it cannot retrieve content. Content retrieval should be handled by another skill (such as wechat-article-fetch), and the AI will determine the order of skill collaboration automatically. A built-in archive mechanism stores all results self-contained in the skill directory.
Generate beautiful, on-brand HTML — presentation decks or full responsive websites — in any brand's design language, combining brand DNA extracted via Firecrawl with codified, research-backed design principles (20 rules for slides, 20 for the web).
Sharp-tongued product manager skill pack for gathering requirements, writing product documentation, and iterative updates. Key features: rejects vague answers, points out problems directly, pushes users to think things through, provides AI-enhanced suggestions, and detects conflicts.
Use when the user asks to explain a problem, issue, PR, or feature as an infographic. Create a step-by-step visual explanation starting from user code or actions, with a clear problem/solution boundary, syntax-highlighted snippets, and focused diagrams. Support standalone educational PDFs and Markdown-first PR explanations, with optional images only for complex diagrams. Also apply when explicitly invoked by the repository PR writer.
Create, edit, replicate, and iteratively refine editable research and technical diagrams in diagrams.net/draw.io (.drawio XML) from prompts, papers, repositories, screenshots, or existing diagrams. Use when asked to generate a scientific figure, paper method diagram, ML/system architecture diagram, draw.io file, reference figure reproduction, browser screenshot feedback loop, Windows-safe draw.io preview, or layout fixes for text overlap, arrows, colors, icons, fonts, and component alignment.
Feishu Slides presentations. slides create creates a presentation from an XML template (POST /open-apis/slides_ai/v1/xml_presentations); slides media-upload uploads media (drive upload_all + parent_type=slide_file; files must be ≤20MB, and chunked uploads are not supported). Use when the user asks to create a Feishu PPT, upload slides, or work with a presentation or slides. Not suitable for complex slide editing (complex block insert/replace semantics are not yet implemented); use lark-slides.
Open an HTML file, Markdown file, or localhost page in the browser so the user can edit text directly and leave comments on specific parts, then send all edits and comments back to you. Use after writing or updating something the user will read — specs, plans, reports, newsletter drafts, landing pages, slide decks, and locally running web pages
Generate Mermaid diagrams (.mmd) and export to PNG/SVG/PDF using mmdc CLI or Kroki API. USE THIS SKILL when user mentions diagram, flowchart, sequence diagram, class diagram, ER diagram, state machine, architecture, visualize, git graph, 画图, 架构图, 流程图, 时序图, 类图, ER图, 甘特图, 状态机. PROACTIVELY USE when explaining ANY system with 3+ components, API flows, authentication sequences, class hierarchies, database schemas, or state machines. Supports 17+ diagram types with fully automatic layout.
Use when the user wants to write, structure, or revise academic paper sections, improve notation consistency, or refine figures and tables. Triggers on phrases like "write the abstract", "structure the methods", "improve this section", "notation consistency", "figure refinement", or "paper structure".
Create style-driven slide images strictly with the Image 2.5 model, assemble them into image-only PPTX decks, and manage reusable visual style libraries from documents or visual references. Use when the user asks for a “PPT Skill”, “风格驱动 PPT”, “提炼风格做 PPT”, “调用某个风格做 PPT”, “图片版 PPT”, “保存 PPT 风格”, “列出 PPT 风格”, “文档生成 PPT”, “文章生成 PPT”, “把文档做成演示文稿”, or wants to extract, save, reuse, and apply visual style keywords specifically for visual slide/image deck creation.
Convert Markdown articles into polished HTML for publishing on WeChat Official Accounts. Apply professional CSS styling, syntax highlighting, and improved formatting. Use when the user asks to polish an article, convert it to HTML, optimize the WeChat Official Account format, or generate WeChat Official Account HTML.
Create or update a RevealJS HTML presentation using the repository's bundled slide template. Use for creating RevealJS talks, making HTML slide decks, building presentation slides, starting a new conference talk deck, or converting a talk outline into RevealJS slides.
Sinh MỘT file .md bàn giao đủ dày để một phiên KHÁC (người hoặc agent, không có context nào của phiên này) mở ra là bắt đầu làm được ngay — việc còn dở, thứ tự ưu tiên có lý do, số đo làm bằng chứng, cạm bẫy đã trả giá, và nợ mở không chặn. Gọi khi user nói "bàn giao", "handover", "handoff", "viết lại để phiên sau làm tiếp", "context cho session khác", "tôi sắp hết phiên", "ghi lại để mai làm", "/orca-handover". KHÁC record-episode (ghi cho MÁY truy hồi ngữ nghĩa) và KHÁC plan (brief thi hành cho task ĐÃ duyệt, đã hiểu rõ) — orca-handover dành cho việc CÒN DỞ và CÒN MƠ HỒ, nơi thứ tự và lý do quan trọng hơn từng bước code.
Reorganizes and creates long Markdown documents—such as reports, research notes, industry analyses, strategy memos, technical white papers, retrospectives, and weekly reports—as self-contained HTML feature pages with editorial judgment, web aesthetics, and evidence structure. Use when the user asks to “convert to HTML,” “turn a report into a webpage,” “beautify a report,” “create a feature page,” “make it easy to share,” “improve readability/design,” or “turn the report into a webpage.” Must write plan.md before writing HTML, preserve the original factual claims and strength of conclusions, avoid templates, and do not mechanically convert Markdown.
Generates Draw.io diagrams based on the current project or code. Supports four types: technology stack, system architecture, data structure, and E-R diagrams. Outputs a .drawio file in Draw.io syntax (mxGraph XML) that can be imported directly into Draw.io for editing. Use when the user mentions a technology stack, system architecture, data structure, or E-R diagram
Use when turning a requirement, spec, or feature brief into a single self-contained HTML design document in a fixed house style — one styled HTML page with a table-of-contents, architecture/sequence SVG diagrams, code/SQL/YAML blocks, callout boxes, an aligned-decisions (已对齐结论) panel, test cases, and a code index. Reuse for any new 需求/设计文档 that should look identical every time.
Research and discovery workflow for document deliverables — competitive analyses, architecture comparisons, ADR scaffolding, literature reviews, vendor evaluations. No TDD requirement. Phases: gathering → synthesizing → completed. Triggers: 'discover', 'research', 'explore topic', or discover.
Use when users explicitly request a systematic review, literature review, related work, or literature research, or want to check close prior work and novelty for a research idea. Compatible with the old name systematic-literature-review. Standard mode performs querying, retrieval, scoring, relevance-based paper selection, writing, citation verification, and PDF/Word export; novelty-check mode delivers only close prior work, counterevidence, and unconfirmed items. Stops by default if queries are missing or invalid; does not silently fall back to a single query. Supports en/zh/ja/de/fr/es.
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".
Routes any Feishu/Lark/Doubao operation, including recording lookup by date (按日期找会议录音), through the version-matched lark-cli domain guide embedded in the installed CLI, then executes and verifies the task. Use for 飞书/Lark/Doubao docs, drive, sheets, Base, wiki, minutes, meetings, calendar, IM, mail, tasks, approval, apps, auth/scope, resource URLs or tokens, and lark-cli troubleshooting. This is the single Lark entry point; use ima-copilot instead for Tencent IMA.
Use when the user asks to "create a PowerPoint", "generate PPTX slides", "make a PowerPoint presentation", "build a .pptx deck", "create editable slides", "PptxGenJS", "editable presentation", "corporate deck", "slide deck for sharing", or when the output format is PPTX for any presentation task. Also triggers on "export to PowerPoint", "pitch deck PPTX", "offline presentation", or when the context implies an editable/corporate format. Generates OOXML-compliant .pptx files with PptxGenJS, precise layout, text measurement, and overlap validation.
Transform Markdown or text specifications into human-readable HTML documents with summaries, reordered structure, visual explanations, diagrams, charts, and traceability to the source. Use when asked to convert a spec, requirements document, API spec, product spec, design doc, or technical document into readable HTML, especially when the user wants summarization, restructuring, diagrams, graphs, images, or visual aids rather than a literal Markdown-to-HTML conversion.
Rebuild or restyle editable Microsoft Visio diagrams from reference images and existing .vsdx files, then export deliverables as .vsdx, PNG, SVG, PDF, or PPTX. Use when the user asks Codex to open Visio, recreate a diagram from a PNG/JPG/screenshot/reference image, match a scientific model figure, update colors/typography/layout in a .vsdx, calibrate panel coordinates to avoid shifted or overlapping submodules, or create publication/presentation outputs while preserving Visio native editable shapes rather than embedding the reference image as a flat picture.
Creates and edits Excel spreadsheets with formulas, formatting, and financial modeling standards. Use when working with .xlsx files, financial models, data analysis, or formula-heavy spreadsheets. Covers formula recalculation, color-coding standards, and common pitfalls.
Extracts key specifications from component datasheet PDFs for maker projects. Use when user shares a datasheet PDF URL, asks about component specs, needs pin assignments, I2C addresses, timing requirements, or register maps. Downloads and parses PDF to extract essentials. Complements datasheet-parser for quick lookups.
Validate and assess the quality of Elastic changelog YAML files against current Elastic standards. Reports schema errors, content quality issues, systematic pattern violations, type-title alignment mismatches, missing product/surface context in titles, description verb-tense issues, and overly technical content that needs user-focused rewrites. Features repository-aware area validation. Fetches canonical guidance to stay in sync. Use when checking or reviewing changelog files before merging — pairs with docs-fix-changelog to get suggested fixes
Professional consulting-style data visualization and infographic creation skill for strategic analysis and executive presentations. Create high-density, boardroom-ready visualizations in McKinsey/BCG style with institutional authority and editorial financial-report aesthetics. Covers 11 visualization types (including cover slides), detailed color palettes with hex codes, aspect ratio standards, prompt engineering templates, and strategic framing guidance for insight-driven deliverables.
A skill that clarifies Japanese text into a state where its meaning is grasped at a single reading. Triggered by phrases such as "わかりやすく直して", "読みやすくして", "読みにくいので整えて", "AIっぽさを消して", "ドキュメントを推敲して", "冗長な日本語を削って", "文章を明晰化して". The target is explanatory Japanese body text such as technical articles, READMEs, design documents, internal documents, and blog explanations. Out of scope are code itself, short social media posts, creative works such as novels and poetry, and the strict prose of legal, medical, or academic writing. The goal is to strip away double negatives, long adnominal modifiers, chains of "の", excessive nominalization, redundant expressions, buried enumerations, and constructions that are hard to parse even for native Japanese speakers, such as LLM boilerplate like "重要なのは〜" and "掘り下げる", and paragraph-level paraphrase repetition. It adds no voice, stance, or personality, and aims only at clarity (clarity = being clear and understandable).
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Universal document conversion using Pandoc with a focus on DOCX. Use when converting documents to or from DOCX, including Markdown, HTML, PDF, and other formats. Supports: (1) converting other formats to DOCX (Markdown, HTML, reStructuredText, etc.), (2) converting DOCX to other formats, (3) custom DOCX templates and styling, and (4) batch document processing
Alibaba Cloud PDS (intelligent cloud drive/network drive) file operation skill. Supports file search, upload, download, rename, move, copy, folder creation, tags/notes, share links, document/audio-video analysis, batch download, image editing, reverse image search, and installation and mounting of the PDS mount app (mountapp, which mounts the cloud drive as a local disk). Use this skill when users want to operate on files or spaces in their PDS, network drive, or cloud drive (including only describing safe ways to handle operations such as renaming, moving, or copying, without actually performing them), or want to mount the cloud drive locally to access it like local files. Trigger even for simple requests such as “help me download from PDS,” “upload to the network drive,” “rename report.pdf,” “what files are in PDS,” “batch-download the files,” “analyze this document,” “mount the cloud drive locally,” or “install the mount app.” Triggers: “PDS,” “network drive,” “cloud drive,” “personal space,” “enterprise space,” “team space,” “drive_id,” “domain_id,” “upload file to PDS,” “download from PDS,” “PDS rename,” “PDS move file,” “PDS copy file,” “PDS create folder,” “PDS document analysis,” “PDS video analysis,” “PDS image editing,” “PDS file search,” “PDS reverse image search,” “PDS batch download,” “bulk download,” “aliyun pds,” “PDS Drive,” “mount app,” “PDS mount app,” “enterprise cloud drive mount app,” “mountapp,” “mount cloud drive,” “mount the cloud drive locally,” “PDSDrive.” Do not trigger merely because PDS is mentioned in informational content: general product concepts, product comparisons, pricing, deployment methods, or documentation questions are outside this skill; neither are local file system operations or operations on other cloud drives. Use this skill for operations on the user's PDS files or spaces, and for installing/mounting the PDS mount app (mountapp) to access the cloud drive as a local disk. Do not trigger for generic PDS product concepts, comparisons, pricing, deployment, or documentation questions.
Check documentation for compliance with the Elastic style guide using Vale linter output and style rules. Use when the user asks to check, lint, or review docs for voice, tone, grammar, formatting, accessibility, or word choice, or when a docs review runs. Do not use for ordinary drafting or editing.
Generate accessible alt text for data visualizations in Quarto documents. Use when the user wants to add, improve, or review alt text for figures in .qmd files. Triggers for requests about accessibility, figure descriptions, fig-alt, screen reader support, or making Quarto documents more accessible.
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.