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.
-
given-dream Bundle Search Wos Cnki LiteratureScript Microsoft Edge with Playwright/CDP to execute and iteratively refine arbitrary literature-search strategies from Markdown or query files in Web of Science and CNKI; collect WOS field-tagged exports and CNKI GB/T citations; screen every strategy-defined group and database independently by topical relevance, rolling publication years, journal-quality evidence, citations, and downloads; and export validated UTF-8 BOM TXT files containing Title, Year, Authors, and DOI. Use for reproducible WOS/CNKI retrieval, zero-result query repair, title-led query adjustment, journal-aware selection, CNKI GB/T export, or per-group TXT delivery without GUI computer-use.
-
go-pay Skill Add Payment InterfaceAdd new payment interfaces to GoPay project following standard workflow - analyze docs, implement code, update documentation and version records. Use when adding WeChat Pay, Alipay or other payment platform APIs.
-
go-vikunja Skill Vikunja Help DocsResearch a Vikunja feature area in the codebase and update or create end-user help documentation. Use when asked to document a feature, expand help pages, or when a review identifies under-documented areas.
-
gobelinor Bundle Bugbounty TriageStrict bug bounty triager that reviews web2 vulnerability reports like a human who's read 50 reports today. Replays the PoC end-to-end (not just reads it), challenges scope, impact, and fix-worthiness before rendering a verdict. Built for HackerOne, YesWeHack, Bugcrowd, Intigriti, and self-hosted programs. Outputs a triage-<vuln>.md file with a captured replay log, weaknesses panel, verdict, and (for valid findings) an acceptance/duplicate-risk read with a SUBMIT/HOLD/REVISE call. Use this skill when the user says "triage this", "review this report", "is this valid", "should I submit this", "validate this finding", or wants a second opinion on a vulnerability report before submission. ALSO use proactively, without being asked, whenever a bug bounty report draft has just been written or completed in this session — run the gates against the draft before the user submits it.
-
gongyu0918-debug Bundle Chinese Official Writing用于中文公文、事务性材料和新闻稿件的起草、改写、压缩、润色、审校、文种核对、去口语化、降 AI 味及 Word 格式处理,适用于机关、企事业单位、学校和新闻机构。涵盖申请、请示、报告、通知、通告、意见、决定、决议、议案、公报、命令、函、复函、批复、说明、方案、纪要、公告、公示、通报、制度、规定、办法、细则、操作规程、工作要点、总结、调研、讲话、致辞、主持词、述职、可研、审查材料、技术需求、新闻消息、编者按、新闻评论,以及采购、整改、反馈和 AI 算力等场景。
-
googlarz Bundle Solve Math RigorouslyWorld-class solver-first math skill for reading, mapping, solving, and checking nontrivial math tasks. Use when the user asks to solve an equation or system, find all solutions, prove a claim, optimize a function, work through a derivation step by step, check whether an answer is correct, explain what a worksheet or whiteboard problem says, or read math from an uploaded photo, screenshot, PDF, textbook page, handwritten note, or diagram before solving it carefully and verifying the result.
-
gordensun Bundle Gorden Ppt Skill用 21 套内置中文 PPT 模板(或用户自带的 .pptx 模板)生成与编辑 PowerPoint 演示文稿:只替换文字、不破坏原排版/配色/字号,内置按文本框尺寸的出框检测与同级标题字号一致校验;也支持完全原创的简洁版式。当用户要"做 / 生成 / 制作 / 编辑一份 PPT / 演示文稿 / 幻灯片 / .pptx",或需要工作汇报、年终与季度总结、述职竞聘、项目复盘、开题答辩、商务提案、教学课件、数据可视化等成品 PPTX 时使用。Use when the user wants to create or edit a PowerPoint / PPT / slides / .pptx deck, pick from built-in templates, or apply their own template without breaking the layout.
-
goreleaser Skill Authoring DocsUse when writing or editing GoReleaser documentation under www/content (Hugo site) — customization reference pages, YAML config examples, "Since vX.Y" / Pro badges, callouts, or documenting a feature that is merged but not yet released.
-
gostyan Bundle DOCX Editor CnUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
-
grafana Skill GoBest practices for working with Go codebases. Use when writing, debugging, or exploring Go code, including reading dependency sources and documentation.
Audited -
muxxik Bundle App Store AsoМетодология ASO для App Store — метаданные, ключевые слова, локали, замеры. Использовать всякий раз, когда работа касается видимости приложения в App Store, даже если слово «ASO» не прозвучало — подбор ключей, сборка или правка Name/Subtitle/Keywords, решение открывать ли локаль, разбор выгрузок App Store Connect или ASO-сервисов (ASO Mobile, AppTweak, AppFollow), диагностика «почему нет показов/загрузок в стране X». Use whenever the user works on App Store search visibility, even without the word "ASO" — keyword research, Name/Subtitle/Keywords fields, App Store Connect impressions/downloads analysis, store locale decisions, autosuggest research, or "why does my app get no impressions in country X". App Store only; Google Play works differently / Только App Store.
-
neofirst0715 Bundle French Sentence BreakdownTurn any French audio transcript, article, or written text into a full deep-dive study package using English (not the learner's native language) as the bilingual bridge — clean transcript, sentence-by-sentence grammatical breakdown (English translation, IPA, word-by-word gloss, sentence structure, grammar notes flagging English/French convergence and divergence, extension examples), a running grammar-review table, a running faux-amis (false friend) log, and a Three-Listen-Rule listening plan. Use this whenever the user uploads or pastes French content (podcast transcript, subtitles, song, article, journal entry) and wants it broken down, explained, corrected, or turned into study material — even if they just say "break this down" or "整理一下" or "帮我看看这段法语". Also use when the user asks for a French listening/study plan, wants their own French writing corrected, or wants to track French grammar progress toward a level goal (A1–B2). Handle long transcripts (40–80+ sentences) in a single pass rather than defaulting
-
neonsalamander Skill R Package Update CheckАгент для автоматического сбора и описания новых пакетов CRAN за последнюю неделю. Используй этот навык когда пользователь просит: найти новые пакеты CRAN, сделать дайджест/обзор новинок CRAN, описать пакеты R за неделю, подготовить еженедельную сводку CRAN, или упоминает "hermes", "CRAN digest", "новые R-пакеты". Также триггерится при задачах мониторинга CRAN, составления бюллетеня или рассылки по новым пакетам R. Результат всегда оформляется и сохраняется как .md файл — используй этот навык всякий раз, когда нужен структурированный Markdown-дайджест пакетов CRAN.
-
nisus74 Bundle HumaniseWrite, rewrite, edit and review human-facing prose in a specific person's voice. Use for emails, posts, reports, proposals, PRDs, board papers, documentation, applications, messages and any text the user will send, publish, present or sign off. Also use when the user asks for Australian English, natural writing, less corporate language, fewer AI tells, stronger voice, or prose that sounds like them. Do not apply the prose sweep to code, config, fixed legal text, quoted material or private scratch notes unless the user asks.
-
noahmustafa Bundle Ats Latex CvBuild ATS-optimised, human-sounding CVs in LaTeX (Overleaf-ready code). Trigger this skill whenever a user asks to create, rewrite, reconstruct, or improve a CV, resume, or job application document — including when they upload an existing CV, paste raw experience, or describe a target role. Also trigger when the user says things like "make my CV better", "tailor my resume for X", "help me apply for a job", or "write my CV from scratch". Always use this skill for any CV/resume task, even if the user doesn't use the word "LaTeX" or "ATS".
Audited -
omerwafaey Bundle ManaraOrchestrate a software task end-to-end in Claude Code. Use this whenever the user describes building, fixing, reviewing, planning, or shipping something in a project — e.g. "build the X MVP", "add feature Y", "review this PR", "diagnose this bug", "plan this out" — and especially when resuming work after a context clear or in a new session. Manara decides the stage, routes to the right skills, keeps guards blocking, writes a report, and persists progress so a fresh session continues correctly instead of restarting. Trigger it even if the user doesn't say "manara" but is clearly starting or continuing a multi-step build/fix/review workflow in a repo.
-
openraiser Bundle Paper Webpage BuilderBuild a polished single-page academic project webpage from a paper directory or paper source, including content extraction, figure selection/conversion, module planning, visual design, tables, assets, and validation. Use when asked to create or update webpages for papers, benchmarks, arXiv-style projects, OpenRaiser project pages, or paths containing paper.tex/PDF/images/assets.
-
othmanadi Bundle Codebase Knowledge BuilderStudy unfamiliar codebases and produce evidence-backed knowledge artifacts. Use for repository orientation, architecture mapping, subsystem tracing, onboarding, or codebase documentation.
-
probot2004 Bundle Design BuildBuild presentation decks, reports and web page layouts to an agency standard, from a source document. Use when asked to make, design or build a deck, presentation, pitch, slides, strategy document, report, whitepaper, one-pager, case study, landing page or web page layout — or to restyle, fix or improve an existing one. Front-loads art direction and structure so the work lands in one or two rounds instead of ten.
-
pektech Bundle Anydocs Skillanydocs - Generic Documentation Indexing & Search
-
phsecl Bundle PDF Courseware To Obsidian将本地 PDF/PPT 课件批量整理为图文并茂的 Obsidian 复习笔记知识库。当用户提供课件目录、想把讲义/课件/slides 转成结构化中文笔记、生成 Obsidian Vault、提取课件文本与配图时使用。触发词:整理课件、课件转笔记、PDF转笔记、Obsidian笔记、复习笔记、讲义整理、course notes。
-
pr1m4lc0d3 Bundle ParaphrasisUse when saying the same thing to a different audience — restating, re-voicing, translating for a new reader, shortening, expanding, or adapting a message for a developer, a buyer, an executive, a beginner, a skeptic, or a hostile reader. Also use when compressing to a word count, writing a summary or TL;DR, turning a spec into an announcement, a changelog into a release note, a paper into a post, or one channel's copy into another's. Carries the drift catalog, the fidelity ledger, and the reversal test. Not for improving prose in place — that is peitho. Not for rendering audio into text — that is metaphrasis.
-
ptlimited Bundle Writing CraftApply the nine writing traits that three blind AI judges independently valued when scoring 50 pieces of writing, and gate the draft against them before returning it. Use when writing or rewriting ANY prose a human will read - a post, a newsletter opening, hooks, a punch-up of flat copy, angles on a topic, an email, an essay, ad copy, a landing page. Trigger on "write a post", "write hooks", "give me angles", "make this less boring", "punch this up", "make this sound human", "does this read as AI", "rewrite this", or any drafting request. Also invoke from inside another writing skill that owns voice, since this skill owns craft and stays voice-neutral. Not for code, commit messages, config, or documentation.
-
pymodel Bundle Defensive DesignUse when explicitly asked for defensive design or robustness, or when designing, implementing, reviewing, or debugging code whose inputs, arithmetic, state, dependencies, timing, resources, or authority can violate a meaningful contract. Adapts to any language or architecture using evidence and proportional controls. Do not auto-trigger for routine low-risk formatting, renaming, documentation, or trusted fixture edits; an explicit request still applies a minimal review.
14 -
hoshino-wind Bundle Automated QA TestStrict automated QA/backtest workflow for web/app features from a user-written requirement, GitHub issue/PR, bug report, or acceptance criteria. Use when Codex needs to dynamically derive a test plan, run UI/API/WebSocket/SSE/command probes, verify feature logic, interaction behavior, stream completion, persistence/data flow, console/network/runtime errors, screenshots, no-fabrication evidence integrity, completeness checks, and produce an evidence-backed test report. Triggers include 自动化测试, 自动化qa-test, QA test, 回测, 测试需求, issue 测试, PR 测试, 功能逻辑测试, 交互测试, 数据是否通, 接口是否通, WebSocket 流式, SSE 流式, 持久化验证, 错误检查, 严格测试, 不能有遗漏, 禁止编造数据, Playwright 测试报告.
-
hristovcodes Bundle Obsidian KanbanCreate and edit Obsidian Kanban board markdown files correctly. Use when asked to create, modify, or work with Kanban boards, task boards, or feature planning boards in any project.
-
iabhishekjhai Bundle Brain DocsSet up and maintain a "project brain" — a brain/ folder holding three living documents (decisions.md, flow.md, todo.md) that give a project persistent memory across chat sessions. Use this skill whenever the user wants a decision log, architecture/flow notes, project memory, living documentation, or notes that survive between sessions ("set up a project brain", "start a decision log for this repo", "remember why we chose X"). Also use it in any repo that already has a brain/ folder: after completing a meaningful code change, when the user says "update the brain docs" or "log this decision", when a risk/limitation/idea surfaces worth writing down, or when the user asks why a past decision was made (read decisions.md before answering).
-
iamcatobot Bundle RssAn RSS client that executes commands using Markdown-defined state/action rules.
-
intelligent-internet Bundle Ii CommonsUse II-Commons for deterministic search across arXiv, PubMed, and policy corpora. Use for evidence comparison, metadata lookup, corpus freshness checks, or full-document markdown.
-
jiaranbb Bundle Report Helper当用户说「深度研究 X」「深入研究 X」或要求生成某产品、公司、概念、人物、产业链、政策、趋势的深度研究/发展研究报告时触发,自动进行联网搜索和研究,产出排版后的 PDF 文档,总字数通常 1-3 万字。 作者:嘉然 | GitHub: https://github.com/Jiaranbb/report-helper
-
jimmysadek Bundle Youtube FetcherRetrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube link defaults to saving a note.
-
jimmynycu Skill CoachRun the token-efficiency coach on a Claude Code session transcript: find wasted tokens (uncached context, bloat, oversized tool output, redundant reads, wrong-tier spend) and report the fixes with dollar estimates. Use when a session felt expensive/slow or the user wants to cut token spend.
-
jok98 Bundle Kiroku ForgeMaintain curated Markdown project memory in kiroku/, query published SQLite checkpoints, and save durable updates at task or milestone boundaries. Use when project context must persist across sessions, an existing task needs continuation, or the user requests memory maintenance. Keep read-only work non-mutating and avoid creating memory for trivial one-shot tasks unless requested.
-
juneyaooo Bundle Gpt Image2 PptGenerate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<collection>/STYLE_ID.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx. Use when the user asks to make a presentation, slides, deck, pitch deck, investor PPT, magazine-style PPT, or 做一份 PPT / 生成幻灯片 / 用 gpt-image 生成 PPT / 按这个模板生成 PPT.
-
k-pourahmadian Bundle Chunk For RetentionBreaks down long or complex material -- book chapters, articles, lectures, research papers, arguments, study notes -- into a small number of meaningful macro-chunks, grounded in John Sweller's Cognitive Load Theory and the working-memory research it builds on (Miller, Cowan, Baddeley & Hitch, Chase & Simon). Use this skill whenever the user wants help remembering, studying, summarizing, or outlining a book/chapter/article for retention; asks about chunking, cognitive load, working memory limits, study techniques, or note-taking strategies; wants a compact map of an argument's structure; or is writing educational/learning-science content that discusses chunking or cognitive load theory -- even if they never say the word "chunking" themselves.
-
kagurananaga Bundle Document Format SkillsChinese 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.
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 search-wos-cnki-literature, add-payment-interface, vikunja-help-docs. 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.