Docs & Writing
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
-
ipea Skill ProofreadRead-only proofreading pass over lecture `.tex` or `.qmd` files. Checks grammar, typos, overflow, terminology consistency, and academic writing quality; produces a report without editing. Use when user says "proofread", "check for typos", "look for grammar issues", "copy-edit this", "any writing errors?", or before a lecture release.
-
studyzy Skill Stk Report对比优化前后诊断报告
-
code-yeongyu Bundle Bun 1 4MUST READ before your first js eval cell: this session's eval js kernel runs Bun 1.4+ (this skill is present only when it does). Also read before any bun -e, script, server, CLI, test, bundle, or package-management work. Bun 1.4 ships builtins that replace 15+ npm deps — check here BEFORE installing sharp, puppeteer/playwright (scraping), marked, node-cron, node-pty, concurrently, serve-static, tar, json5, fast-xml-parser, string-width. Triggers: eval js, bun, Bun.serve, bun test, bun build, bun install, bun run, image resize, headless browser, markdown render, cron, PTY.
-
hackermanishackerman Bundle Doc NavigatorEfficiently navigate codebase documentation during Research phase. Use instead of Grep/Glob for finding architectural decisions, feature specs, and technical docs. Maps topics to doc locations for fast context retrieval. If codebase lacks documentation structure, provides patterns to establish one.
-
shockrock2004 Bundle WongCompile everything Claude did today across ALL sessions and repos into one dated teaching-guide markdown saved in "~/Daily Log", render it as a phone-readable PDF, and upload to Google Drive. Safe to run multiple times a day — it appends only newly-uncovered work to that day's single file rather than overwriting. Use when the user runs /wong, or says "log today's work", "end of day log", "daily log", "wrap up the day", or any similar end-of-day trigger. Accepts an effort level (light/medium/heavy, default heavy) to control token usage — e.g. "/wong medium" — and optionally a past date (YYYY-MM-DD).
-
supermarioyl Bundle Markdown PrettifyReformats a Markdown file in place. Pure text processing, no network.
-
sven-li-sankyuu Bundle Ppt Polished Deck CollabUse when collaborating with humans to produce polished, editable, high-quality PPT decks across business, technical, research, education, product, and operations themes. Supports deck planning, slide archetype selection, diagram/chart/icon asset strategy, preview export, and validation for reusable PowerPoint deliverables.
-
trystan-sa Skill Postkit SetupBrand intake — interviews the user about their handles, audience, goals, voice, and visual identity, then persists the answers to plain Markdown files in memory/ at the project root so every later post-creation and review uses them. Run this before drafting any post. Also use when the user wants to revise the brand profile.
-
xileades Skill Pennylane Supplier InvoicesCollect supplier invoices from mailboxes, obtain the PDF (attachment, link or portal), identify which legal entity is billed, import them into Pennylane via the API, then file the processed mail. Use when the user says "pull the invoices", "get the invoices from my mail", "import these invoices into Pennylane", or talks about purchase invoices to enter. Load the pennylane-access skill first.
-
zhangyanbo Skill Vibe Research ExploreRun exploratory research loops - branch, run small fast experiments, produce figures, report findings honestly, let the user judge direction. Use when exploring a new idea or hypothesis, testing whether an approach works, running quick experiments in a research project, or whenever the user asks to "try" something experimental.
-
adobe Skill DocumentGenerate and update S3Mock project documentation. Use when asked to document code, update CHANGELOG.md, update README.md, update AGENTS.md files, or fix formatting, wording, or style in any existing documentation file. Also invoked at the end of the implement skill workflow.
142 -
adobe Skill RefactorImprove code readability, enforce idiomatic Kotlin conventions, and enhance documentation quality in S3Mock without changing behavior. Use when asked to clean up code, improve naming, add KDoc, or align with Kotlin/project idioms. Also invoked by the implement and test skills before adding new code to messy areas.
Audited 142 -
adobe Skill ImplementImplement features, fix bugs, and modify production source code in S3Mock. Use when asked to add functionality, change behavior, or modify source files in server/, integration-tests/, or testsupport/. Not for documentation-only or test-only changes. Orchestrates lint, test, and document skills as part of the complete workflow.
142 -
agentscope-ai Bundle Dingtalk Message钉钉消息发送技能。支持企业内部机器人(批量单聊/群聊)和 Webhook 自定义机器人两种接入方式,支持多机器人管理,支持文本、Markdown、链接、ActionCard、FeedCard等多种消息类型。
-
agw-sales-ops Bundle Ali Weekly ReportAli Weekly Report
Audited -
agw-sales-ops Skill Weekly Report OciOCI周报全功能:大盘多维汇总与月度Top10排行 + 客户周用量折线图 + 客户月度用量柱状图。按销售汇总CSPA/Runrate客户的多维用量,列出本月前十客户排行,生成周用量折线图(标记最高/最低点),以及按客户×月份分组的柱状图。触发词:OCI周报 / Oracle周报 / 周报 / 大盘汇总 / 客户排行 / 周用量 / 折线图 / 波动图 / 月度柱状图
Audited -
haibaraaiaptx Skill Download OpenapiDownload remote OpenAPI/Swagger JSON specification from a URL to local file using aptx-ft CLI. TRIGGER when user mentions: (1) fetch/pull/download swagger or openapi from URL, (2) save API spec to openapi.json locally, (3) get API documentation from server, or (4) prepare local input for code generation. DO NOT TRIGGER when: generating code/types from local file, reading existing openapi.json, downloading non-OpenAPI files, or authentication is required.
-
joaomonteiro100 Bundle UX Usability StudyPlans and produces the complete set of materials for a moderated usability test — research questions and success metrics, a recruiting screener, a consent form, a facilitator script with think-aloud protocol, realistic task scenarios, a note-taking and issue-tracking structure, and a findings report. Use this whenever the user wants to run, plan, prepare, or moderate usability testing, user testing, or a usability study; wants to recruit or screen test participants; needs a test script, tasks, or scenarios; needs to take structured notes during sessions; or wants to synthesize observations from real user/participant sessions into prioritized findings (that synthesis belongs here, not to heuristic evaluation). Trigger even when the user only describes the situation ("we're about to watch five people use our checkout flow") without naming "usability testing" explicitly.
-
kkenny0 Bundle Deep Read深度阅读非技术素材,输出完整研究文章。四阶段流水线:捕获→精读→综合→撰写。素材类型:论文(arxiv、期刊)、书籍章节、新闻报道、长文、访谈记录、行业报告、政策文件。一个 skill 从头到尾完成,不依赖外部 skill。当用户想要:深度阅读论文、研究非技术主题、把多份素材综合成文章、对论文做深度解析、把报告整理成研究文章、综合分析多份素材、理解一篇论文的核心思想并写成文章、深度研究某个话题(社会现象、商业模式、理论框架等非代码主题)时,都应该触发。即使用户只说"分析这篇论文"或"帮我读一下这个"——只要素材不是代码或技术项目,就应该用 deep-read 而不是其他 skill。用户分享论文 PDF/URL、arxiv 链接、报告文件并要求分析时,一律触发。不触发:GitHub URL / 源码分析 / 技术框架深度解析 → source-dive;纯 URL 抓取不分析 → read skill;vault 维护 → loom-maintain。
-
kerliula Skill Build MeImplement a solution write-up (typically the markdown file produced by /solve-me) in this Laravel project, following existing project patterns and Laravel best practices. Cuts the work into commits itself, writes the commit plan to docs/build/<slug>.md, and gets the developer's approval before writing any code. Then builds one commit at a time, saying up front and afterwards why that commit is needed and which numbered requirement it serves, and stopping after each one for the developer to review and edit. Every piece of new logic gets a short plain-language comment explaining what it does and why that approach was picked — meant to be deleted once reviewed. Suggests a commit message after each commit. Always implements the option the developer already picked in the /solve-me file — never a different one. Use after /solve-me, when it's time to actually write code.
-
kerliula Skill Grill MeRuthlessly eliminate comprehension debt before design or implementation. Use when the developer wants to stress-test a plan, decision, requirement, bug, feature, architecture, or implementation idea. The developer must demonstrate that they understand the problem, constraints, behavior, and consequences in their own words before the session can advance. Closes the two answers developers always get wrong — what's out of scope, and how we'd know it works — by drafting both lists itself and having the developer confirm or correct them. Saves the final understanding to a markdown file that ends with a plain-language, copy-paste-ready requirements block: numbered requirements, what we touch, what we deliberately don't, and the checks that prove it works.
-
kerliula Skill Solve MeTurn an understood problem into a solution, using divide-and-conquer. Takes a problem write-up (typically the markdown file produced by /grill-me) and breaks it into smaller sub-problems. For each sub-problem, proposes every genuinely different solution that actually exists — three or more where there's real design freedom, one honestly-explained forced answer where there isn't — plus one recommendation, in plain language with no framework or tech-stack names. Saves the result to a markdown file. Use after /grill-me, before writing any code.
-
leon-sg Bundle Orbid Read DatasheetUse when the user attaches a product datasheet, brochure, IFU, 说明书, user manual, or certificate PDF and wants a read-only spec extract. Triggers: 读说明书, 读这个 datasheet, what's on this brochure, listed CE/ISO on this file. No Orbid account. Not for org catalog lookup, query_knowledge, query_gaps, or filling a tender.
-
marecgents Bundle Ieee Mg ReviewerIEEE Transactions 风格论文审核技能。基于 ieee-mg-share/writing/polishing 的课题组写作规范, 审核一篇论文是否符合课题组风格。生成详细的 Review Report,逐句标注问题和重构建议。 当用户提到"审核"、"review"、"检查论文"、"审稿"、"是否符合风格"、"写作问题"等时触发。
-
max-levitskiy Bundle FellowRetrieve and work with Fellow (fellow.app) meeting notes, transcripts, AI summaries, and action items — answer questions about past meetings, write recaps into a repo, bulk-export to markdown. Trigger even when Fellow is never named — any request to recall, search, summarize, or file what happened in a meeting, like "what did we decide about X", "my action items this week", "pull Friday's transcript". Also for setting up Fellow API access.
-
mehdisoliman Bundle Quittance LoyerGenerate a French rent receipt (quittance de loyer) PDF.
-
orinvoss Bundle Math Paper数学建模团队「论文」岗技能。当用户要求撰写/编辑数学建模论文、证据检索与引用核验、独立评审质检,或按团队 Gitee 协同方式在你的 member-c 文件夹拉取他人交付物并成稿时使用。覆盖证据大纲、论文撰写(Word/LaTeX)、论文终检与评审门禁。
-
orinvoss Bundle Skill根据题目、建模分析和真实代码结果生成完整 Word 数学建模论文,用户显式要求时同时生成 LaTeX 论文。
-
postttt Skill OptimizeAnalyze a codebase for performance and produce an optimization report — where the program is slow, how to make it faster, and the expected speed impact, effort, and risk of each change. Use when the user asks to "optimize the program", "make it faster", "improve performance", "find bottlenecks", "why is this slow", or "reduce latency/memory". Reads and understands the code first, reasons from profiling and algorithmic complexity (not guesses), and reports recommendations ranked by impact — without rewriting hot code until asked.
-
postttt Skill PDF SummaryAnalyze a PDF in full and produce a structured, chapter-by-chapter, page-aware summary that preserves detail. Use when the user asks to "summarize this PDF", "analyze this document/PDF", "break down this PDF", "give me the key points of this PDF/report/paper/manual", or points to a .pdf file. Reviews every page, cites where each point comes from, explains diagrams/images, and keeps instructions/procedures complete rather than compressed.
-
crossbill-app Skill Ticket In CommitsUse when a ticket is large enough to want breaking into commits, or has a reference/spike implementation to port — plans the work as bite-sized commits with the user, then drives each one through an implementation subagent, a report-only review subagent, revdiff, and a commit.
-
danielsitek Skill Handoff ListList all saved handoff files in .handoffs/ with their summaries so the user can see what tasks they have parked. Use this skill whenever the user wants an overview of their handoffs — phrases like "list handoffs", "what handoffs do I have", "show my parked tasks", "what did I stash", "vypiš handoffy". Trigger whenever the user wants to know what is waiting in the handoff queue, even without the exact word "list".
-
darknessomi Bundle Read Yapi UrlSync full YApi project data to the current project via token, then extract requested API documentation from local files for git-managed updates. Use when the user asks to read, fetch, sync, or get YApi API documentation, or provides YApi URLs like "https://yapi.example.com/project/{id}/interface/api/{api_id}" or "https://yapi.example.com/project/{id}/interface/api/cat_{cat_id}". Supports both single API URLs and category URLs. Supports multiple YApi projects in one repo under yapi/{project_id}/. Host is parsed from the URL automatically.
-
dashaworks Skill Deck PublisherTurn content into a responsive, presenter-friendly slide deck published at a live URL via ReportRoom. Use when the user says "make this a deck", "turn this into slides", "presentation for", or wants something to present rather than read. Not for long-form documents (use report-publisher) or polishing an existing deck (use report-designer).
-
databricks Skill Bullet BriefFormat the final answer as a tight markdown bullet list — one idea per bullet, no preamble. Use when the user asks for a summary, a rundown, or to "keep it brief".
-
babygao Bundle Publishing To CnblogsUse when publishing or cross-posting an article to 博客园 (cnblogs) — from a local Markdown file or scraped from another platform such as 51cto — and images show as broken links, markdown won't render, or the old browser-automation tool's selectors have stopped working.
Frequently asked questions
What are Docs & Writing agent skills?
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
Which Docs & Writing skills are most installed?
Popular Docs & Writing skills on SkillMD right now include proofread, stk-report, bun-1-4. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Docs & Writing skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.