Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Route editable PDF, DOCX, XLSX, and PPTX creation or modification tasks to the appropriate official Hermes document skill. Use when the user asks to create, edit, format, convert, fill, annotate, review, or otherwise produce an editable office document. Do not activate for simple read-only extraction or summarization. For presentation-only output where the user does not need an editable PowerPoint file, use Starchild's official slide-creator skill.
Draft, rewrite, polish, expand, condense, standardize and export Chinese official documents and formal administrative texts. Use when the user asks to write, revise, summarize, standardize, or convert 公文、决议、决定、命令、公告、公报、通告、意见、通知、通报、报告、请示、批复、议案、函、纪要, as well as 总结、简报、新闻简报、信息专报、舆情专报、汇报材料、讲话稿、工作方案、实施方案、回复函 and other formal documents of government agencies or organizations — especially when fixed document-type structures, a formal official tone, unified wording, standardized titles, hierarchical numbering, signature dates, template application, Word docx export are needed, or when current news material must be turned into formal official documents and formal briefing materials.
Update existing OpenWiki documentation (openwiki/ directory) after source changes — surgical, git-diff-driven edits to only the affected pages, with a no-op check when nothing changed. Use when the user wants to refresh, sync, or maintain the repository wiki.
Analyze local Q&A session JSONL files and produce a complete, auditable English Markdown weekly report over consecutive time windows, with all data required for downstream Feishu document and whiteboard rendering. Use for requests such as "analyze the latest week of sessions," "generate a community Q&A weekly report," or "compare with last week." This skill does not ingest other message sources or create/upload online documents.
Use when the user wants to search academic papers, find literature, download PDFs, or export citations. Invoke when user mentions "论文", "文献", "paper", "research", "学术搜索", "BibTeX", "DOI", or asks to find/search/download academic papers from any source.
Run or resume the complete Standard mathematical-modeling workflow from contest files through reproducible evidence, adaptive formal writing, native-equation Word output, and final render QA. Use as the entry point for complete-paper requests.
View, extract, edit, and manipulate PDF files. Supports text extraction, text editing (overlay and replacement), merging, splitting, rotating pages, and getting PDF metadata. Use when working with PDF documents for reading content, adding/editing text, reorganizing pages, combining files, or extracting information.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Use when user requests diagrams, flowcharts, sequence diagrams, class diagrams, component diagrams, ER diagrams, architecture charts, or visualizations — including generating a diagram from existing source code, or rendering/extracting PlantUML embedded in a Markdown file to images (e.g. preparing docs for Confluence/Notion). Also use proactively when explaining systems with 3+ components, APIs, data flows, or class hierarchies. Generates .puml files and exports to PNG/SVG via Kroki API (no local install required).
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); 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,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Use when the user explicitly asks to "update the project guide", "sync the guide", "capture insights into the guide", or requests the skill by its former name guide-updater. Captures reusable writing insights from the conversation into the project guide file in real time, keeping terminology consistent, the structure stable, and the content testable and reproducible. The guide file path must be specified when invoking.
Help users generate a professional Chinese resume (in both HTML and DOCX) in one pass based on any background material (old resume, JD, work log, etc.), with ATS optimization, role-specific skill dimensions, page-count control, and automatic senior job-search advisor suggestions after generation. Trigger scenarios: user requests "帮我生成简历", "写简历", "改简历", "我要投一个岗位", or any request involving creating, editing or optimizing a resume.
Produces executive summaries, 1-page briefs, and board-level documents by extracting the situation, key findings, implications, and recommendation — answer-first, one page maximum. Use when a lengthy document needs a senior-audience brief that enables a decision. Triggers: 'executive summary', 'summarise this for a senior audience', '1-page brief', 'TL;DR for leadership', 'distil this', 'board summary', 'write a brief'.
Reference: SaaS subscription agreement review, focusing on the clauses most critical in subscription deals — automatic renewal mechanics, price adjustments, data portability, uptime SLAs and subprocessor rights. Loaded when /commercial-legal:review detects a SaaS or subscription agreement.
Use when the user has a scientific draft (with its dataset, figures, and optional analysis code) and wants it iteratively revised until it clears a quality bar. Five specialist judges (figures, scientific content, style, formatting, code) critique the draft; a fresh, independent peer_reviewer grades it on those same axes (1-5 each → a percentage) with honesty guardrails; a scientific_writer revises prose, figures, and code — regenerating figures by running the user's plot command — until the peer-review score clears the threshold or the budget is hit. Not for writing a paper from a blank page, and not for a standalone literature survey.
One-time setup that maps the codebase and gathers user-provided product context to write a root PROJECT.md overview of what the project is, who it serves, how it is structured, and how it runs. Use when the user invokes $setup-project-md, says "setup project md", "create PROJECT.md", or asks for a complete project overview document at the repo root.
Turn a contract review into a summary that business stakeholders will actually read. Not a legal memo — a two-minute answer to "can we sign? what do we need to know?" Use when the user says "summarize it for the business," "write it for [stakeholder]," "explain it to procurement," "non-legal summary," or needs to send something to non-lawyers after a review is complete.
Use when writing, structuring, drafting, or reviewing a thesis, dissertation, undergraduate thesis/TFG, master's thesis/TFM, or empirical research write-up — scoping the topic, outlining chapters, drafting sections from evidence and data, editing drafts, or planning the work. Covers undergraduate through master's/doctoral level.
Review AI vendor terms — focusing on training data provenance compliance, allocation of liability, model change notification, and flow-down of compliance obligations. Applies to reviewing AI SaaS agreements, AI model licensing, AI API terms of service, or when a procurement team asks "is there a problem with this AI vendor contract?"
Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
Build CoinFund-branded web presentations as self-contained HTML files. Supports static (print/PDF) and dynamic (keyboard nav, transitions) modes. Outputs a single versionable HTML file with optional PDF export via Puppeteer. Trigger on: 'web deck', 'web slides', 'html presentation', 'web presentation', or any request for a browser-based slide deck.
Write a GxP-compliant Standard Operating Procedure (SOP). Covers regulatory SOP template structure (purpose, scope, definitions, responsibilities, procedure, references, revision history), approval workflow design, periodic review scheduling, and operational procedures for system use. Use when a new validated system requires operational procedures, when existing informal procedures need formalisation, when an audit finding cites missing procedures, when a change control triggers SOP updates, or when periodic review identifies outdated procedural content.
Draft unanimous written consents for a board or committee in internal format, retrieving precedent from the resolution repository. Handles multi-resolution consents, director conflict flags, notice requirements under applicable law and signatory tracking, with a built-in scope caution for significant single actions. Use when the user says "written consent," "unanimous consent," "board resolution," "resolution in lieu of a meeting," "written approval," or describes an action needing board approval without a meeting.
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.
Detects whether AI-assisted review tools (such as Luminance, Kira, etc.) are in use, hands off large-batch clause extraction to the tool, and QA's its output according to the trust levels in `~/.claude/plugins/config/claude-for-legal-zh/corporate-legal/CLAUDE.md`. Use when the user says "hand off to an AI tool", "batch review", "AI extraction", or when diligence-issue-extraction encounters large-batch categories.
Use this skill any time the user wants to create, draft, or generate a written document or report. This includes: competitive analysis, market research reports, technical design docs, PRDs, project proposals, meeting summaries, white papers, business plans, literature reviews, due diligence reports, industry analysis, executive summaries, SOPs, memos, and any request where the output is a structured document. Also trigger when: user says 写个文档, 做个竞品调研, 写份报告, 产品需求文档, 技术方案, 项目提案, 行业分析, 会议纪要整理成文档. If a document or report needs to be created, use this skill.
Automates financial and business data analysis, mines data value in depth, and generates professional reports. Activation scenarios: the user provides financial statements (income statement, balance sheet, cash flow statement) or business data (sales, operations, customer, cost data), or asks for data analysis, data mining, report generation, KPI calculation, trend analysis, variance analysis, year-over-year and period-over-period analysis, multidimensional analysis, or data cleaning. Trigger keywords: 分析数据, 财务分析, 业务分析, 做报表, 数据挖掘, 看看数据, 分析一下, 出报告, KPI, 趋势, 同比, 环比, 差异分析, 数据质量, 收入分析, 成本分析, 客户分析, 运营分析.
Process specification for extracting Axure prototype assets, generating themes/data/documentation, restoring pages and generating business documentation using skills such as extract-axure-data in skills/. Use when the user provides an Axure prototype link or requests asset extraction, prototype restoration, theme/data model/documentation generation, or interaction guidance.
Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", "slide deck", or "PPT".
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis
Use Baidu OCR high-precision with position to convert code screenshots into text files while preserving the original indentation. Use cases: (1) recognize code screenshots as editable text, (2) extract code from screenshots, (3) convert images to code text. Triggers: the user mentions "截图转文字", "OCR", "识别代码", "图片转文本", "code screenshot to text"
Generate a structured B2B PRD document (with initial content) based on the business context provided by the user. Triggers automatically when the user asks to create, write, or generate a PRD, requirements document, product plan, or system design document — even if they only say "help me write a PRD/plan/requirements doc".
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.