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.
-
shen-an Bundle Paper Reading把学术论文(PDF/摘要/DOI/二手转述)加工成可核查的中文精读笔记:支持 PDF 导入与页码锚点,先一段话总结核心内容,再按"背景→方法→实验→贡献→局限"重建论证链,公式统一用 Markdown 数学语法,并附符号表与来源分层;产出八种互相独立的文件——精读讲解、逐篇填表、思维导图(文本大纲 + 可渲染 Mermaid 两种形态)、难点与解答、中英对照的全量专业术语表、多篇汇总综述,以及把整个笔记库管成 wiki 的合集层索引(主题清单 + 术语速查 + 跨论文对比 + 未解决问题 + 证据强度总览),每篇论文目录里另有一份可机械校验的单篇索引(全量文件登记 + 证据强度提示 + 待核入口)。当用户说"讲一下这篇论文""论文精读""导入这篇 PDF""填这个表格""生成思维导图""这篇论文的难点""可能遇到什么问题""写文献综述""整理我的论文笔记库""更新笔记库索引""这篇论文的专业术语""出个中英对照术语表"或输入 /paper-reading 时使用。
-
roasbeef Bundle Doc GraphSet up and maintain a per-package documentation graph in any repo: one CLAUDE.md per package (Purpose, Key Types, Relationships, Traffic, Invariants, Deep Docs) with a byte-identical AGENTS.md mirror, a no-toolchain gate script that checks coverage, mirror equality, git-time staleness and file:line citation drift in docs/, and a repo-customized doc-gardening skill that regenerates stale docs from source. Use `init` in a repo that has none of this (it detects the language and layout, asks what the repo's traffic vocabulary is, installs scripts/doc_check.sh, a make target, a CI job, and .claude/skills/doc-gardening/), or `check` and `garden` in a repo that already has it. Pairs with `decision-records` and `handoff`.
-
roasbeef Skill Roasbeef ProseWriting style guide for Roasbeef's technical prose. This skill should be used when writing PR descriptions, commit messages, technical documentation, blog posts, or any written content that should match Roasbeef's established voice. Activate when creating PRs, drafting commit messages, writing release notes, or composing technical explanations.
-
roasbeef Bundle Technical WritingTechnical Writing (The Sense of Style)
-
devattom Bundle AI MultimodalProcess and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
-
madappgang Skill Style Format 2Style template format specification. Single markdown files that describe artistic direction.
-
pumblus Skill Okf Harness 5Unified OKF Harness entrypoint for Pi, OpenCode, and OpenClaw. Use when the user asks to create, find, select, repair, check, ingest into, reconcile, answer from, or graph an OKF Harness workspace. Do not use for generic Markdown editing, repository maintenance, repository dependency graphs, or non-OKF knowledge-base work.
-
rebyteai Bundle Financial Charts 2Render stock/price charts in financial reports with TradingView Lightweight Charts (candlestick, OHLCV, volume, indicators, backtest markers, equity curves). Use whenever a report chart is fundamentally about a traded instrument's price over time. Keep ECharts for generic business charts. Fill a declarative JSON spec plus a sibling data JSON; deliver as an artifact.
-
th0rgal Skill Orchestrator Worker 2Worker skill for boss-spawned missions. Stay within scope, verify, and report blockers quickly.
-
lidessen Bundle Technical Article Writing 2Methodology for writing argumentative technical articles — pieces that convince the reader of a specific claim through a chain of reasoning. Use when the user wants a technical article, essay, or book chapter that takes a position — introducing a new idea, challenging an accepted one, or arguing for a particular approach. Triggers on phrases like "write an article/essay/chapter about X," "make the case for X," "argue that Y," or structuring a multi-chapter argument about agents, architectures, systems design, or methodology. Do NOT trigger for tutorials ("how to do X"), reference or API documentation, release notes, changelogs, or pure explainers where no claim is being argued — those need a different framework.
-
tbsten Bundle Exploratory Nightly Verification 2Nightly Checking ワークフロー上で 60 分 budget の単発探索的検証を行う運用規約。 PR 差分ではなく main の最新を対象に、 ライブラリ本体・integrationTest・docs 全体を 多角的に揺さぶり、発見都度 `.local/nightly-exploration/issues/` へ Markdown 起票する。 Kotlin / Compose / Gradle / AGP の最新 release 情報も探索範囲に含める。 Use when requested: "nightly 探索", "夜間探索的検証", "exploratory-nightly".
-
devolutions Skill Code Review 2Review Devolutions Gateway pull requests and diffs using focused contract, compression, documentation, prose, and skeptical passes. Use whenever Copilot code review is requested or a proposed change needs review.
-
devolutions Skill Commit Scope 2Select commit and PR scopes in the Devolutions Gateway repository. Use whenever composing or reviewing a Conventional Commit subject, especially for shared libraries, packaging, tests, documentation, CI, or changes spanning products.
-
ai-lcs Bundle Paper FormattingUse when formatting Kevin's paper docx, OMML, tables, swaps.
-
alizeisnotalice Bundle Paper Maker把题目图片或文档(PDF/Word/Markdown/文本)整理成带 LaTeX 公式和配图的试卷 PDF,并交付可编辑的 .tex 源文件。当用户说"把图片转成文档"、"提取图片中的题目"、"整理题目"、"把文档转成试卷"、"提取文档里的题目",或提到图片转文字、题目提取等关键词时使用。
-
alizeisnotalice Bundle Answer Maker制作题目的答案与解析文档,交付与 paper-maker 同风格的 .tex 与 PDF。输入可以是纯文字、纯图片、文字+图片的混合文档,也可以是 paper-maker 生成的试卷 .tex/PDF;若输入格式与 paper-maker 生成格式不一致,先调用 paper-maker 把题目整理成标准试卷格式,并在输出时附上新整理的题目文档。当用户说"做答案"、"制作答案"、"生成答案解析"、"题目答案"、"整理答案解析"或要求给题目配答案/解析时使用。
-
axelvm Bundle Feature Par IaDéveloppe une feature de bout en bout en TDD avec documentation Obsidian, gates de validation humaine, tests fonctionnels E2E, tests unitaires, puis boucle de build jusqu'au vert. Use when the user asks to create, implement, or develop a feature with AI, TDD, functional tests, or the feature-par-ia protocol; when they say "nouvelle feature", "crée une feature", "feature par IA", "implémente cette fonctionnalité", or invoke /feature-par-ia.
-
charliechiou Bundle DeeppapernoteGenerate a high-quality deep-reading note for a single paper from a local PDF and write Markdown plus extracted images into the current workspace. Use when the user gives a local PDF path and wants a polished Markdown note with strong structure, evidence-based analysis, grounded figures, and reproducible local outputs.
-
charliechiou Bundle Hackmd Manage NotesManage HackMD notes and folders with Microsoft Edge through Playwright. Use when Codex needs to read, create, update, move, organize, or verify notes in HackMD while preserving Markdown and writing style; create or verify Book Mode; manage custom share links; resolve editor conflicts; or verify server persistence.
-
cj-lazy Bundle Paper Deep Read对学术论文进行科研式精读、讲解和批判性评估;适用于用户提供论文 PDF、链接或文本,并希望理解研究问题、方法、证据、图表、创新与局限时。
-
consensys-incorporated Skill Author Page 2Scaffold or draft new Zesu documentation to editorial standards. Use when creating a new page, writing a first draft, or helping a non-writer meet the documentation team's expectations.
-
finos Bundle Technical Writer 2Assists with writing and maintaining Morphir Rust technical documentation. Use when creating, reviewing, or updating documentation including API docs, user guides, tutorials, and content for the Jekyll-based GitHub Pages site. Also helps ensure documentation quality through link checking, structure validation, and code review for documentation coverage.
-
slawekradzyminski Bundle API Exploratory TestingExplore APIs through focused source-code analysis and live HTTP experiments, identify risky behavior, and report reproducible bugs and contract gaps. Use for exploratory API testing and code-informed bug hunting; regression-suite implementation is a separate task.
-
talmolab Skill Pr 2Create a well-structured GitHub PR with proper branching, testing, formatting, and documentation. Use when the user says "create a PR", "make a PR", "open a pull request", or wants to submit changes for review. Handles the full workflow: branch creation, implementation, testing, formatting, committing, and PR creation with comprehensive descriptions.
-
talmolab Skill Investigation 2Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what touches X", "follow the wiring"), document system architecture comprehensively ("document how the system works", "archeology"), investigate bugs ("figure out why X happens"), explore technical feasibility ("can we do X?"), or explore design options ("explore the API", "gather context", "design alternatives"). Creates dated folder with README. NOT for simple code questions or single-file searches.
-
vchaindz Bundle GovcControl, report on, and manage VMware vSphere/ESXi environments using the govc CLI. Use this skill whenever the user mentions vSphere, vCenter, ESXi, VMware, virtual machines on VMware, govc, vMotion, DRS, HA, vSAN, datastores, snapshots, OVA/OVF, or asks for a health check, a morning report, patch-day or maintenance-window preparation, or asks to inventory, report, power on/off, clone, migrate, snapshot, or troubleshoot anything in a VMware environment — even if they don't say "govc" explicitly.
-
vchaindz Skill Govc PrivateManage and report on VMware vSphere/ESXi through the govc-safe wrapper, which returns pseudonymised data only. Use this skill instead of the plain govc skill whenever the environment has govc-safe installed, or when the user says vSphere data must not leave their network, mentions PII, GDPR, confidentiality, or asks to avoid sharing infrastructure details. Covers inventory, capacity and snapshot reporting, health checks, and VM/host lifecycle actions using stable tokens (VM-0001, HOST-01) rather than real names.
-
yangjunshuo-ai Skill Paper Final Check Skill检查论文、课程报告、设计报告、终稿 PDF 或 Word 的逻辑、公式编号、符号统一、图表引用、摘要缩写、实验结论和可提交性。适用于用户要求“终稿检查”“看看还有什么问题”“逻辑性错误”“公式是否配套”“是否可以提交”等场景。
-
yogsoth-ai Skill Context Checkpoint 2Append research process and results to the current Phase's context file. Each append MUST contain >=500 lines of markdown covering both process and results. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase.
-
zhaozr815 Bundle Weekly Report把零散工作记录、会议结论、截图/聊天整理成中文周报(本周完成工作、本周工作总结、下周工作计划)。 Use when the user asks to write, revise, polish, or optimize a 周报 / weekly report / 本周完成 / 下周计划 / 工作总结, or pastes day-by-day notes for a weekly summary.
-
zsby-gn Bundle Research Study MaterialsGenerate Chinese research-oriented LaTeX/PDF study materials, frontier learning notes, and deep research handouts from a topic, paper, notes, DOCX/PDF, or rough research direction, with deep knowledge-point explanation as the main body and a minimalist, readable PDF style. Use when Codex should teach related concepts, formulas, assumptions, applicability, experimental signatures, mechanisms, impact, advantages, and limitations in depth, then use recent research papers and DOI references as supporting frontier examples. Supports independent chapters, one-page-minimum top-level sections, and simplified LaTeX/TikZ diagrams for mechanisms, research routes, experiment workflows, and solution maps; exercises should be research-oriented phenomenon/mechanism/solution-analysis questions rather than textbook drills.
-
zsby-gn Bundle Textbook Study MaterialsGenerate Chinese student-facing study materials from textbook chapters, notes, exercises, TeX files, PDFs, pasted content, or rough topic requests. Use when Codex needs to help students understand books by creating structured lesson handouts, concept explanations, example-driven worksheets, practice books, exam-style papers, answer keys, or LaTeX/Markdown study guides in a Chinese math/science teaching style similar to ctexart handouts, tcolorbox theorem/problem boxes, and sectioned exam papers.
-
zyliufeng123 Skill Bid Word Insert ProofInsert a full-page proof image (如无欠税证明 PDF) into 资格预审/投标 Word docs, center it in the printable area, add a TOC line, and refresh page numbers without breaking body titles or other content. Use when the user asks to 插入证明/无欠税/附件材料进 Word、加一页证明、更新目录页码, or to apply the same method used for 南通康浩资格预审文件.
-
agents-flex Bundle PPTXCreate and validate Microsoft PowerPoint presentations (.pptx), including structured slide decks, tables, workflows, metadata, and reproducible generation scripts. Use for presentation, slides, PowerPoint, PPT, or PPTX creation and verification tasks.
-
aidenwu0209 Bundle Paddleocr Doc Parsing 2Use the native DeepSeek Harness PaddleOCR tool to parse document layout and Markdown.
-
aidenwu0209 Bundle Paddleocr Text Recognition 2Use the native DeepSeek Harness PaddleOCR tool to extract text from an image or PDF.
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 paper-reading, doc-graph, roasbeef-prose. 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.