Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Draft a complete civil or criminal judgment based on the Chinese People's Court judgment document drafting standards. Use this skill when the user asks to "draft a judgment", "generate a judgment document", "write a civil judgment", "write a criminal judgment", or "write a document from case files", or provides case materials and asks for a judgment document, autonomously invoking atomic skills (such as issue identification, statutory retrieval, deductive reasoning, evidence admissibility assessment, etc.) while drafting each section.
Use when references in a .bib file (often from /search-lit) should land in Zotero and Obsidian. Syncs them to the Zotero library, writes Obsidian literature notes and extracts cross-cutting concept notes once enough accumulate. A folder of PDFs is /obsidian-paper-vault.
Creates, maintains, and synchronises core project documentation (README, TODO, DESIGN, Architecture, Testing, Deployment). Use when the user needs to write, update, or structure project documentation based on codebase changes, or whenever asked to perform documentation reviews or updates.
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
Turns a product walkthrough recording into an RFP-response video plus a written requirements matrix. Maps each requirement or question from the RFP's actual requirements list to the specific moment(s) in the recording that address it, trims the video down to just that RFP-relevant content with restrained captions naming which requirement each segment demonstrates, and flags any requirement the recording doesn't cover before anything gets built. The matrix is authored on the project's live article and also handed back as text in the response. Use when the user says "turn this demo recording into an RFP response video", "build our RFP video and reference doc from this walkthrough", "map this recording to our RFP requirements", or "we need a video and a requirements matrix for this RFP response".
Automate contract review and monitoring with Box MCP — find new or expiring contracts, compare them against firm templates to flag material variances, write structured contract metadata back to Box for searchability, and produce variance reports with citations. Use this skill when the user mentions contract review or monitoring, NDA or MSA review, contract expiration or renewals, contract metadata, or variance analysis, even if they don't name a specific Box tool.
Automate legal client intake and onboarding with Box MCP — review intake documents for completeness against firm requirements, summarize risk for attorney review, route incomplete or high-risk submissions to the right attorney, extract client and matter metadata to Box, and generate engagement letters from Box DocGen templates. Use this skill when the user mentions client intake, client onboarding, new client review, intake documents, or engagement letters.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Draft or update Elastic Workflows documentation pages in explore-analyze/workflows/ — step references, use cases, how-tos, concepts, and overviews. Use when writing Workflows docs, documenting a step type, turning workflow YAML into documentation, drafting from a doc issue in docs-content or docs-content-internal, or creating a new page under the Workflows docset.
Use when creating, editing, formatting, or extracting LibreOffice Impress (.odp) presentations via UNO, including session-based slide edits, structured targets, lists, tables, charts, media, notes, master pages, patch workflows, and snapshots.
Skill for creating new PPTX, PDF, and PNG files with Presenton. Use this skill whenever a user asks for a PowerPoint, presentation, slide deck, pitch deck, report deck, PDF, presentation PDF, PNG slide, slide image, or exported deck, even when Presenton is not mentioned. Use a concrete design brief from the user when provided; otherwise search Presenton designs, upload user-provided images, search Presenton icons, generate 1280x720 HTML with HTTPS asset URLs, export requested formats—or all three formats when none is specified—and return download URLs plus a shareable presentation-preview link.
Analyze, draft, revise, or audit scientific peer-review response letters and point-by-point rebuttals. Use for reviewer comments, response letters, rebuttals, revision summaries, quoted manuscript changes, replies that must align with a manuscript or Supplementary Information, and submission-ready checks of direct question-answer alignment, evidence, figures, tables, notes, panels, terminology, numbers, and internal citations. Especially useful when replies must reuse the reviewer's terms, map every sub-question to an explicit answer, report new analyses or experiments, identify exact revision locations, or distinguish mandatory fixes from optional polishing.
Adversarial verification of AI-generated legal content with systematic fact-checking, source validation, and quality control. Use when a user asks to verify, fact-check, red-team, validate sources, or quality-control a legal document, briefing, compliance summary, or regulatory analysis before it is distributed to clients, stakeholders, or published. Trigger phrases include "verify", "fact-check", "red team", "red-flag", "check accuracy", "validate sources", "quality control", "is this correct", and "review for errors". Produces a structured verification report with severity-categorized errors, verified sources, unsupported claim list, missing disclaimers, and an explicit distribution-readiness assessment.
Use when writing a literature review article (narrative, scoping PRISMA-ScR or systematic). Scaffolds a 7-part skeleton with a scope and non-overlap statement, summary-table stubs and reporting-guideline wiring, without inventing citations. Original research is /write-paper.
Turn a Roblox game concept or the current conversation into a short, buildable PRD (game design brief) and publish it to the project tracker. Use when the user wants to lock a chosen concept into a spec before building, write a design brief, or create a PRD for a Roblox game or feature. Pairs with roblox-to-issues, which slices the PRD into vertical slices so the game is built one playable piece at a time instead of all at once.
[user/auto] Use when requesting visual materials or self-contained HTML explanations that explain the background knowledge and actual structure and behavior of a concept. Do not use for explaining a specific change, multi-chapter learning courses, plain-text questions, editing existing writing, or product comparison prototypes.
Exam cram coach. A student gives a course-materials folder (lecture PDF/PPTX/DOCX, notes, homework, answers, past papers), and it teaches chapter by chapter with source citations, crops and displays figures from the slides and questions, quizzes and grades only from the materials, keeps a mistake log and notes, plans the remaining days, builds a cheat sheet, and labels whether each statement comes from the materials. Triggers: final, midterm, exam, exam prep, revise, cram, practice questions, past papers, homework walkthrough, mistake log, key points, cheat sheet, study plan, postgraduate entrance exam, certification exam, lecture walkthrough, slides. Use when a student wants to prepare for a final, midterm or any exam from their own course files: teach chapter by chapter with page citations and the figures cropped from the materials, quiz only from the homework and past papers, keep progress, mistakes and notes across chats, plan the remaining days, build a cheat sheet, and label what comes from the materials. Triggers: exam prep, cram, revise, study for the test, lecture slides, homework solutions, past papers, practice questions, quiz me, mistake log, cheat sheet, study plan, study guide, flashcards.
Remove AI writing tells from text. Use when a text artifact is the deliverable or a major part of one, such as documentation, PR or commit text, release notes, reports, marketing copy, code comments, or when asked to de-slop, humanize, or clean up text. Not for chat replies, status updates, or completion summaries around a non-text task.
Use when the user needs to turn a real software engineering / computer science project and an existing thesis draft into a submission-ready undergraduate thesis manuscript. Trigger for requests such as "根据项目把论文改成定稿", "按学校模板排版成最终版", "复制初稿后生成定稿 Word", "为定稿降查重", "根据PaperPass报告降AIGC", "继续在手改初稿上改", "恢复原来的图表和数据库说明", or when academic-paper-strategist has already produced an evidence-backed rewrite plan. Outputs a cleaned manuscript, final DOCX workflow, and a separate rework report.
Use when authoring or amending developer-tool documentation — the adoption + integration narrative for an SDK, library, CLI, framework, or API platform: the guide a developer reads to install, integrate, and operate the tool. Guides the METHOD, not the outline: developer GOALS not endpoints; a signposted start-here + a fast verifiable first success; concepts before recipes; goal-named runnable recipes; an end-to-end tutorial; grounded best-practices; a troubleshooting path; archetype-aware emphasis (API/SDK/CLI/framework); POINTERS into — never a copy of — the api-reference; and amending a guide as a versioned delta that sweeps the tool's changes for stale samples. Full Diataxis correctly typed, every sample runnable + accurate to the tool, nothing fabricated. Composes with a template tool + deep-research. Consumes the handed-in feature-spec + api-reference + PRD — never a blank page. Not the api-reference catalog, the end-user user-guide, engineering docs, or reviewing one.
Use when authoring or amending a release/deployment runbook: the go-to-production procedure for shipping a system to production safely. Guides the METHOD, not the outline: grounding it in SRE/operational practice, deriving deploy steps from the architecture-doc + technical-design rollout and verification from the test-plan exit criteria, writing idempotent copy-paste-safe steps each with an expected result, defaulting the deploy strategy to blue-green, sequencing a stateful change as a backward-compatible expand-contract migration (roll-forward if irreversible), giving every forward change a documented revert with measurable triggers, naming the comms window for a user-impacting deploy, and amending the living runbook as a versioned re-validated delta — to a bar where an unfamiliar engineer can deploy, confirm, and roll back from it alone, no secret inlined and nothing fabricated. Composes with a template tool + deep-research. Not the CI/CD pipeline config (cicd-plan), not a post-mortem, not reviewing one.
Build and manage M&A virtual data rooms with Box MCP — create secure due-diligence folder structures, scope role-based access for internal teams and external parties, validate permissions before sharing, and answer cross-document due-diligence questions with Box AI. Use this skill when the user mentions M&A, deal rooms, data rooms, VDRs, due diligence, or mergers and acquisitions.
CRITICAL: EXCELLENT at parsing BOTH PDF documents and IMAGES (including LONG SCREENSHOTS, scanned documents, and standard images). Extract structured Markdown content (text, tables, images). MUST use this skill WHENEVER a user wants to parse, read, OCR, or extract content from ANY PDF file, image file, or long screenshot. Also trigger this automatically when users share a local file path, URL, or TOS path pointing to a PDF or image, even if they don't explicitly say 'parse'.
Generate, audit, or update GitHub READMEs with project-type-aware structure, voice calibration, and SEO/AEO discoverability guidance. Three modes: generate (new), audit (check existing), update (patch). Detects repo type and adapts sections, tone, and badges accordingly.
Explore any Hexagone Web space via Playwright headless browser, capture screenshots, and produce a PO-oriented Markdown document. Use when the user wants to explore, document, or extract the features/screens of a Hexagone Web space, capture UI screenshots of a running Hexagone Web app, or generate PO-oriented feature documentation from it.
Based on the case fact description, coordinates 8 atomic capabilities to generate a complete criminal judgment with standard formatting and rigorous argumentation. Covers the full process of fact finding, legal application, sentencing reasoning, and document output.
Turns a screen recording into a searchable help-center article, built as a real, live article inside a Clueso project: a clear title, a one-line summary of what the reader will accomplish, numbered steps naming the real control and the resulting outcome, and supporting screenshots pulled from the recording (or a generated image standing in wherever a captured frame doesn't actually convey the point). The article is the primary deliverable; a polished companion video built from the same recording is optional and secondary here. Use when the user says "generate a help article from this recording", "turn this screen capture into a searchable doc", "make a knowledge-base article from this screen recording", or "write me a help-center article from this walkthrough".
From one screen recording, always produces both a polished video and a full step-by-step help article: two equal, always-built deliverables rather than one primary format with the other optional, with the article built as a real, live article inside a Clueso project. Use this instead of recording-to-help-article specifically when the team needs both formats by default. If the user already has an existing Clueso article, the finished video and written steps can be attached to and merged into that one instead of a new project. Use when the user says "turn this recording into a video and a help doc", "I need both a video and written steps from this capture, no matter what", "make a guide and a video from this recording, I want both every time", or "give me a polished video plus documentation from this screen recording".
Replace a help article's outdated screenshots with current captures at the same steps, keeping the article's text and structure untouched. Use when the user says "the screenshots in this article are outdated", "refresh the screenshots", "update the images in our help doc", "the UI changed and the article still shows the old design", or "swap in current screenshots".
Use this skill to write package release notes, changelog entries, and hosted release descriptions from supplied drafts or verified changes, or to review release copy for completeness, consistency, and wording. The work can cover a commit, commit range, pull request, branch, tag, diff, or every change since the latest release. Don’t use it for ordinary commit summaries unless they’re intended for use in release notes or a changelog
Use when reviewing/judging a published, consumer-facing API reference an integrating developer calls an API from — deciding if they can integrate from it. A gate, not authoring. Judges against a single-sourced 11-condition usability + contract-consistency bar: getting-started + auth reach a first call; every api-spec operation (incl. events/webhooks) is documented with purpose + typed params + a worked example + errors; errors first-class; rate-limits + pagination documented where applicable; versioning + deprecation/sunset stated; the reference is CONSISTENT WITH THE HANDED-IN api-spec (no drift, no fabricated endpoint — the load-bearing check); samples runnable; an amendment re-syncs to the changed contract. Emits exactly `VERDICT: approve|revise` plus actionable findings; approves a proportionally-sized reference, revises on a named gap. Not authoring it, not the end-user user-guide, not the developer-adoption guide, not the engineering api-spec (reviewing-api-spec).
Use when reviewing/judging a test plan / QA verification plan — deciding whether a tester can execute it and every behavior is covered. A gate, not authoring. Judges it against a single-sourced 10-condition bar: every handed-in upstream behavior (feature-spec/api-spec ops+errors, else PRD) has >=1 TRACEABLE case; functional levels fit; entry/exit testable (coverage floor + open-defect threshold); environments + test data specified; each case has preconditions + steps + observable result (a metric-threshold-on-a-dataset for ML) + traces-to; the catalog is RISK-WEIGHTED (coverage gap, padded/thin, OR combinatorial blow-up = a finding); each warranted non-functional type (perf/security/WCAG 2.2 AA/compat/i18n) carries a target; an amend is reviewed delta-scoped; nothing fabricated. Emits exactly `VERDICT: approve|revise` + actionable findings; approves a proportionally-sized plan, revises only on a named gap. Not for authoring it, the release runbook, design-review, or the test scripts.
Use this skill whenever a user wants to create a presentation outline, slide deck structure, storyboard slides, or plan a deck for any context (talk, boardroom, email report). Also use when the user mentions "help me structure my presentation", "slide outline", "storyboard my deck", "presentation flow", "plan my slides", "key message for my deck", "pyramid principle for slides", "what slides should I include", or "help me tell a story with slides". This skill walks through a complete, interactive process in two phases: Phase 1 (setup → key message → storyboard) saves a slide-outline.md; Phase 2 (interactive per-slide copy drafting → polish) saves a slide-copy.md that is linked from slide-outline.md. Trigger even when the user only mentions a vague intent like "I need to present X to my team" or "help me put together a board deck".
Turn an uploaded slide deck (PPT) into a narrated video that doesn't feel like a deck: slide text rewritten into spoken narration instead of read aloud, slides that don't earn screen time cut or merged, motion added to the slides that matter, and clean transitions at section boundaries. Use when the user says "turn this deck into a video", "convert my PowerPoint to video", "narrate these slides", "make a video from this presentation", or uploads a deck and wants a video version.
Use when building, auditing or freezing a journal submission package from the canonical manuscript. Detects drift between the source and the per-journal submission copy, builds byte-preserving packages with manifests, and records current, stale or frozen status.
Shared building blocks for Box-based legal workflows — Box collaboration role definitions, Box AI usage boundaries (what AI must not decide), and reusable human-in-the-loop confirmation phrasings. Referenced by box-legal-workflows-ma, box-legal-workflows-intake, and box-legal-workflows-contract skills.
Turn git commits and diffs into a non-technical client report grouped by feature. Use for client updates, weekly progress, stakeholder recaps, or high-level git-history summaries; resolve the date range from reliable context or ask when ambiguous.
Answer a question across a corpus of contract documents with verified citations. Use when the user asks what a contract says, which contracts have a clause, what changed between amendments, or any question that needs reading and citing across a set of contract files. The corpus must be on the local filesystem (see README).
Guide for drafting cookie policies compliant with GDPR and the ePrivacy Directive. Includes CNIL 2020 recommendations, a reference template, and best practices. Use when drafting or revising a cookie policy for a website or application.
Transform audit data, performance reports, and structured analyses into polished visual deliverables. Generates presentation decks (PPTX), interactive HTML dashboards, or styled markdown reports with charts. Includes a customizable design system with forest green accent and warm cream backgrounds. Use when the user has analysis data and needs a visual deliverable.
Publishes HTML or Markdown as display.dev URLs with public, company, or private access. Supports signup, claiming, sharing, browsing, bounded reads, exact edits, and comment iteration. Use when the user asks to "publish this", "share this", "share with the org", "post this online", "make a private link", "share with [email]", "publish a report", "list my artifacts", "find an artifact", "publish a large file", "publish this generated HTML file", "read this artifact", "search inside this artifact", "change this passage", "make a copy of this artifact", "duplicate version", "create a display.dev account", "claim this publish", "add a company email domain", "transfer an email domain", "change the email domains add-on", "watch comments on this artifact", "respond to comments", or "resolve this comment thread". Use whenever a request contains a display.dev artifact URL (`*.dsp.so/*`). Anonymous publishing returns a 30-day preview and browser claim URL.
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.