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.
-
benjaminstelzer Bundle Scoville PlanRepository-native planning guardrail for creating, maintaining, resuming, auditing, and handing off durable project Plans, Work Items, and Decision records through direct Markdown and YAML edits only. Owns their concise writing and wording audits without requiring Scribe. Use when a task invokes Scoville Plan, requests repository-owned implementation planning or decision records, must survive interruption or compaction, or works in a format-version-1 project with PROJECT_INDEX.md, docs/plans, and docs/decisions. Do not use for a small contained task that needs no durable plan, or when the user explicitly opts out of Scoville Plan.
-
benjsmith Bundle Plan AssistSet up and maintain a three-tier project-documentation system (charter.md + work-plan.md + log.md) that keeps a project's intent from drifting across sessions. The journal is a write-ahead log for project intent; a cheap periodic "heartbeat" catches drift early. Use when the user says "set up project docs", "plan docs", "start a new project", "plan-assist", "session handoff", "wrap up this session", "before I move/reset the repo", or "project heartbeat". Invoke explicitly or when these phrases surface.
-
berkaybuharali Bundle Cv BuilderUse this skill to build a tailored, ATS-friendly CV as a 1-page or 2-page PDF using Pandoc and WeasyPrint. Trigger whenever someone wants to: create or update a CV/resume targeting a specific job or company, convert their work history into a polished PDF, customize their CV for a specific role, or generate a 1-pager or 2-pager from existing source materials. Also trigger when the user says 'apply for a job', 'tailor my resume', 'create my CV for [company]', or 'update my CV' — even if they don't mention PDF format explicitly.
-
bevibing Bundle SocratesSocratic method teaching skill that guides users to discover answers themselves through questioning, never giving direct answers. TRIGGER when: user's message contains 'socratic', 'Socrates', or '소크라테스'. Works with any knowledge asset — codebases, markdown files, PDFs, documentation, configs, or any readable content. Respond in the user's language.
-
bholmesdev Bundle Write DocsCreate or revise documentation for the simple-stack repository, especially MDX guides and API reference content under www/src/content/docs/. Use when asked to write docs, restructure guides, add examples, or enforce documentation tone, structure, and code highlighting conventions.
-
billliao Bundle Ppt Design SkillUse 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; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Includes 9 built-in design themes (5 magazine + 4 Swiss) and 32 layout templates. Trigger whenever the user mentions 'deck,' 'slides,' 'presentation,' or references a .pptx filename.
-
binli Skill Driver DebugDebug Linux kernel drivers with token-efficient dynamic documentation loading. Use this skill when debugging driver issues, analyzing kernel crashes, dmesg logs, oops messages, lockdep warnings, or investigating hardware/device driver problems. Automatically discovers and loads relevant kernel documentation from Documentation/ based on the specific subsystem.
-
bjg4 Bundle Decision LogCapture already-made decisions as individual markdown files with YAML frontmatter in a decisions/ directory, indexed by an append-only decisions/_index.jsonl. Works for any domain — engineering, research, health, creative, financial, personal, scientific, legal, or anything else. Use ONLY when the user explicitly asks to log, record, or capture a decision, update the decision log, review logged decisions ('what decisions have we made'), look up a specific DEC-XXXX, or invokes /DL, /DecisionLog, or /decision-log. Handles decision extraction from conversations, options-considered tables, auto-generated index, status tracking, and supersession chains. Do NOT use for general note-taking, meeting minutes, journaling, brainstorming, or helping the user make a decision that has not been settled yet.
Audited -
jamesshi96 Bundle Lark Tasklist Export从飞书任务清单(tasklist)中提取所有未完成任务及其自定义字段,生成结构化的 Markdown 文档。当用户要求导出/提取/读取飞书任务清单、把飞书任务做成文档、导出任务列表为 markdown 时使用。也适用于用户说"帮我看看任务清单里有什么"、"把清单里的任务整理成文档"等场景。即使用户没有明确说"导出"或"markdown",只要涉及从飞书任务清单中批量提取任务信息并生成文档,就应触发此 skill。
-
jameswei Bundle Plan Build ReviewPlan and execute explicitly requested scoped work, from a feature to a milestone, through independent plan review, user approval, task-level build and review checkpoints, integration review, and controlled publication. Use only when the user explicitly invokes this skill by name (for example, $plan-build-review in Codex or /plan-build-review:plan-build-review in Claude Code) or clearly asks for this workflow in other words; do not invoke it for ordinary coding, review, or documentation tasks.
-
jane-xiaoer Bundle Wechat To ObsidianExport any WeChat 4.x (macOS) conversation — favorites, filehelper (文件传输助手), friends, or chatrooms — into an Obsidian vault as structured markdown + attachments. Triggers: /wechat-to-obsidian, 微信→Obsidian, 微信备份, 文件传输助手导出 Prerequisites: macOS, WeChat 4.x logged in, frida, pycryptodome, zstandard
-
jasonchanjj123 Bundle Study TutorUse this skill whenever a user uploads lecture notes, course slides, textbook pages, screenshots, code files, spreadsheets, or any academic material and wants help studying, reviewing, or understanding them. Triggers include: requests to summarize lecture content, create flashcards, build study guides, explain concepts from class, generate practice problems, review for exams, reorganize notes, or any mention of 'study', 'review', 'flashcards', 'exam prep', 'quiz me', 'help me understand this lecture', 'chapter review', or 'what do I need to know'. Also triggers when a user uploads academic files (even without explicit study requests) and asks 'what's in here' or 'help me with this'. This skill transforms passive notes into active-recall study assets — flashcards, Feynman explanations, knowledge graphs, concept maps, and practice exercises. Use this skill even if the user just says 'I have some lecture notes' or uploads a .pptx/.pdf and mentions school, class, or studying.
-
jasontsaicc Bundle Notebooklm StudioImport sources (URLs, YouTube, files, text) into Google NotebookLM and generate user-selected artifacts: podcast, video, report, quiz, flashcards, mind map, slides, infographic, data table. Use when the user sends content and asks to generate learning materials, podcasts, videos, or study packages.
-
jasonviipers Bundle Revolut TradingComprehensive trading skills for the Revolut X Crypto Exchange API. Use this skill to authenticate, fetch market data, manage orders, and execute trades on Revolut X. Includes API documentation and a Python client wrapper.
-
jaysonmulwa Skill Flanner PlanSave or update a plan, design, architecture, migration, or RFC document through flanner so it is placed in the managed plan directory, given the standard YAML header, and versioned. Use when the user asks to write or revise any planning markdown that should be tracked, or when you are about to create such a document yourself.
-
jeasonstudio Bundle CcusageToken usage statistics for Claude Code CLI. Use when users ask about token consumption, API costs, usage reports, or billing data. Triggers include 'token usage', 'how many tokens', 'API costs', 'usage report', 'spending', 'claude code usage', 'token consumption', 'cost breakdown', 'usage statistics', 'daily/weekly/monthly usage'.
-
jeffreydeng-spec Bundle Deeptutor Academic LiteLightweight tutoring skill for concept explanation, slide walkthroughs, derivation steps, and example-led teaching.
-
jerryjliu Bundle Llama ExtractExtract structured JSON from PDFs, DOCX, images, and other documents using a schema. Faster and more accurate than reading pages directly for tables, multi-page schedules, financial filings, invoices, contracts, and any document where a defined schema describes the expected output.
-
jfernandez Skill MdservePreview markdown with mdserve when content is long or likely to be iterated with the user (tables, diagrams, multi-section docs). Skip preview for short markdown that is easy to read directly in the terminal.
-
jftuga Bundle TranscribeTranscribe and critically analyze audio/video content. Accepts a .vtt file, an audio file (.m4a, .mp3, .wav, etc.), or a URL (YouTube or other yt-dlp-supported sites). Generates a structured markdown analysis.
-
hst368 Bundle PDF ToolkitOperate on PDF files: compress PDFs, render pages to images, extract text, extract embedded images, OCR scanned PDFs, and merge/split/extract/delete pages. Use when the user asks for PDF compression, PDF to image, text extraction, image extraction, OCR, or PDF page operations.
-
htlin222 Bundle Drug DrugEvidence-based Drug-Drug Interaction (DDI) assessment skill modeled after the Micromedex Drug-Reax methodology. Trigger this skill whenever the user types /drug-drug, mentions "drug interaction", "DDI", "drug-drug", "can I take X with Y", "interaction between", "交互作用", "併用", or asks whether two medications can be used together. This skill performs systematic literature retrieval via PubMed, CrossRef, and WebSearch, then produces a structured assessment report with Severity, Documentation, Onset, Mechanism, Clinical Effects, and Management — mirroring the Micromedex Drug-Reax classification framework. Even casual questions like "is it safe to combine A and B" should trigger this skill.
-
htlin222 Bundle Irb Form GeneratorAutomate KFSYSCC IRB document preparation — generates Word docs for all IRB submission phases (new case, amendment, continuing review, closure, SAE, etc.). Use when user mentions IRB, ethics review, human subjects research, form generation, or KFSYSCC. Triggers on study proposals, IRB submissions, or form filling tasks.
-
htlin222 Bundle PDF To Tts ZhTurn a PDF (slides, case reports, handouts) into a single narrated Traditional Chinese audiobook MP3. Rasterize each page to an image, read it, write a natural spoken 繁體中文逐字稿 per page, synthesize each with edge-tts, then concatenate into one mp3. Use when asked to make a Chinese voiceover/audio/podcast/audiobook from a PDF or slide deck, "把 PDF 轉成語音/逐字稿/有聲書", or "用 edge-tts 唸投影片".
-
htlin222 Bundle Thsr TimetableLook up live Taiwan High Speed Rail (THSR) train timetables — given two stations and a Taipei-local datetime, returns the next ~16 trains with departure / arrival / duration / intermediate stops. Use whenever planning HSR travel (medical talks, meetings, day trips), comparing train options, or filling 高鐵 times into a form. Wraps Superior APIs proxy. No PDF parsing, no scraping.
-
htlin222 Bundle Zh Ebn Report台灣護理人員撰寫實證護理報告(實證讀書報告、實證案例分析)的完整教練技能,專為護理進階制度 N1–N4 升等、台灣護理學會與台灣實證護理學會審查格式而設計。當使用者提到「實證護理報告」、「實證案例分析」、「實證讀書報告」、「N2 報告」、「N3 報告」、「N4 報告」、「護理進階報告」、「護理升等」、「PICO」、「5A 步驟」、「CASP 評讀」、「護理 EBP」、「EBN」、「evidence-based nursing」、「實證照護」、「證據等級」、「文獻評讀」,或任何護理人員詢問升等寫作、臨床問題轉化為實證主題、實證文獻搜尋策略、CASP 評讀表、Oxford 證據等級、APA 第 7 版格式、實證介入應用至個案、護理常規挑戰、去除護理迷思等情境,**務必觸發此技能**。即使使用者只是隨口問「我要寫報告」、「我要升 N3」、「幫我找主題」、「幫我設 PICO」、「這篇文獻要怎麼評讀」,也應主動啟動以提供完整的結構、句型與審查通過率最高的寫作策略。
-
humbleteam Bundle Design BriefExtract a 5-bullet design brief (Problem, Audience, Success metric, Must-haves, Constraints) from messy inputs - transcripts, docs, freetext - with a gap report instead of guessing at missing fields. Trigger phrases - "write a design brief", "turn this transcript into a brief", "what's missing from this brief", "update the brief, now it's B2C". Do not use for visual design tokens (extract-design-tokens) or a dev handoff spec (design-handoff).
-
hw10181913 Bundle Claude CodeClaude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Use Spec-Driven Development with spec-kit - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Use spec-kit workflow for structured development - Manage AI-assisted development workflows - Execute complex programming tasks
-
hwdemtv Bundle Dwg Block Compare对比新旧两版 AutoCAD DWG 图纸中指定图块(摄像机、音箱、插座等设备符号)的位置与数量差异,并在新版图纸副本上分色圈画标记(红=一致/黄=微调/绿=新增/蓝+叉=旧有新无),生成 Word 对比方案。当用户要求"对比 DWG 图块"、"图纸版本差异标记"、"新增/删除设备标记"、"CAD 图块分析标记"时使用。依赖 Windows + AutoCAD + pywin32,基于炸开真值法处理天正图纸的大偏移基点块。
-
hydralgorithm Bundle Pyq AnalyzerDeep PYQ (Previous Year Question) pattern analysis skill. Analyzes uploaded exam papers to extract structural and content patterns, confidence scores, variant trends, and priority rankings. Produces Full Analysis (LaTeX PDF), Priority Analysis (chat), or Quick Brief (chat). Works for any subject — engineering, CSE, humanities, law, medicine, commerce. Use when user uploads PYQ papers and wants exam pattern analysis, topic prioritization, or study strategy based on historical question data.
-
hyfdev Bundle Hyfdev Adversarial ReviewAdversarial review (对抗 review) of a finished deliverable — a change ready for a PR, an investigation report, a recommendation, a batch of record edits — before it is reported to the user. Spawns fresh reviewer subagents briefed to disprove it from three directions (open, over-engineering, residue), verifies and fixes what holds, then reports. Run once per deliverable when it is considered done, and on request at level strong (强力) or max (极致). Not for answers to questions, lookups, or steps inside a task.
-
i-am-anshul Skill De AIRemove signs of AI-generated writing from text. Use when editing, reviewing, or generating text to make it sound natural and human-written. Applies to all content: resumes, cover letters, LinkedIn posts, professional writing, documentation. Detects and fixes: inflated symbolism, promotional language, superficial analyses, vague attributions, em dash overuse, rule of three, AI vocabulary, negative parallelisms, excessive hedging, and sycophantic tone.
-
iamvirul Bundle API DocsGenerate OpenAPI 3.1 specs and documentation from code. Supports Express, FastAPI, Flask, NestJS, Spring Boot, Gin, Rails, and more. Use when documenting APIs, creating OpenAPI specs, or generating API reference docs.
-
iamzifei Bundle Linkedin Article PublisherPublish Markdown articles to LinkedIn Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to LinkedIn Articles, or mentions "publish to LinkedIn", "post article to LinkedIn", "LinkedIn article", or wants help with LinkedIn article publishing. Handles cover image upload and converts Markdown to rich text automatically. 新手引导:输入 `/linkedin 新手`、「这个怎么用」「第一次用」「能干嘛」时,走 SKILL.md 的〈新手上路〉,不要直接开始干活。
-
iamzifei Bundle Wechat Article FormatterFormat markdown and publish to WeChat Official Account via bm.md rendering + WeChat official API 新手引导:输入 `/公众号排版 新手`、「这个怎么用」「第一次用」「能干嘛」时,走 SKILL.md 的〈新手上路〉,不要直接开始干活。
-
iannuttall Skill LibrarianUse Librarian to fetch and search up-to-date developer documentation from GitHub and websites so answers are grounded in real docs.
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 write-docs, ccusage, pyq-analyzer. 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.