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.
-
perhapsspy Bundle Tighten DocsUse by default whenever creating, revising, reviewing, or finalizing human-authored documentation whose source meaning is settled, including documentation changed within another task. Apply from first draft through final review to keep one direct current state, clear reader routes and ownership, and remove rejected decisions that survive as negation or defensive prose. Skip prose-free mechanical edits, unresolved meaning, append-only history, generated artifacts, pure translation or localization, and always-read instruction design.
-
phodal Bundle Slide SkillUse this skill as reference material when creating or editing presentation slide decks.
-
pengelbrecht Skill AgentviewerDisplay rich content (markdown, code, diffs, mermaid diagrams) to users in a browser viewer. Use when you need to show complex content that benefits from rich rendering - reports, documentation, code with syntax highlighting, git diffs, or diagrams.
-
phuryn Skill Bug FinderReview a Python solution against a markdown spec, run it, and report bugs.
22.6k -
phuryn Bundle Pm BrainInitialize a PM Brain — a markdown-native second brain for a product operator (PM, product lead, founder, or anyone accountable for one product or initiative) doing judgment-heavy work with scattered inputs. Detects greenfield vs. migration mode, runs a focused interview, copies the deterministic scaffold into the working directory, populates placeholders from interview answers, runs a self-test, and commits. Use when invoked via `/pm-brain` or when the user asks to set up a PM Brain.
22.6k -
phy041 Bundle Academic PptGenerate publication-quality academic presentations (.pptx) from paper PDFs, LaTeX sources, or text descriptions. Dual-engine figures: Matplotlib for data charts (precise), Gemini image generation for concept diagrams (visually rich). Scene-adaptive templates: defense, conference, seminar. Use when asked to "make slides", "create a presentation", "defense PPT", "academic-ppt", or "generate slides from paper".
-
phy041 Bundle PDF To MdConvert PDF to Markdown so Claude can read it natively in conversations. Three-tier engine: pymupdf4llm (fast, default), marker-pdf (--quality, Apple MPS-accelerated for scanned/equations), docling (--best, IBM, top accuracy on academic/enterprise PDFs). Auto-extracts images. Use when the user pastes a PDF path, asks "read this paper", "convert this PDF", "summarize this report", or whenever a .pdf needs to enter context.
-
pi0 Skill MdzillaBrowse, search, and export documentation from any source using the mdzilla CLI. Use when Claude needs to: (1) Read or browse documentation for a library, framework, or project, (2) Fetch docs from GitHub repos, npm packages, or websites, (3) Export documentation to flat markdown files, (4) Look up API references, guides, or usage examples from doc sites. Triggers: user asks to "read the docs", "check the documentation", "browse docs for X", "fetch docs from", "export docs", or references a docs site URL, npm package docs, or GitHub repo docs.
-
piekill Bundle Xiaohongshu Search SummarizerSearches Xiaohongshu(小红书) for a given keyword, extracts the top N posts (including texts, images, and user comments), and then synthesizes a comprehensive final analytical report. Use this skill whenever the user wants to search Xiaohongshu for a specific topic, compile research seamlessly combining text and images, or needs an aggregated thematic summary of social media posts, comments, and visual data on a given subject.
-
plannotator Skill Plannotator TuiOpen a Markdown plan or document for the human to review and annotate in a Herdr pane; their feedback arrives as your next message. Use when you have written a plan, spec, or design document that needs human review before you act on it.
-
privatenumber Skill Mac OcrRun the `mac-ocr` macOS CLI (or its Node.js API) to recognize text in images and PDFs, extract structured document content on macOS 26+, or create a searchable PDF from a scanned PDF or an image with an invisible selectable text layer. Use when asked to OCR, extract or read text from an image or PDF, stream text from a large PDF page by page, extract paragraphs/tables/lists from a document, make a scanned PDF searchable/selectable, or convert an image (PNG, JPEG, HEIC, ...) into a searchable PDF - on-device via Apple's Vision framework. Covers the default OCR action (text/JSON/JSONL output, batching, stdin, URLs, languages, regions, encrypted-PDF passwords), the macOS 26 `document`, `searchable-pdf`, and `languages` subcommands, and the Node API (`ocr`, `ocr.pages`, `ocrDocument`, `ocrDocument.pages`, `createSearchablePdf`, `supportedLanguages`). macOS only; not for editing or replacing a PDF's existing text.
-
privatenumber Skill Md PenUsage patterns and API reference for md-pen. Use when formatting markdown strings programmatically.
-
pm-shawn Bundle Tikz Scientific FiguresCreate publication-grade scientific figures and schematic diagrams with TikZ/PGFPlots, output as vector PDF (and SVG for visual editing). Use when the user wants a figure for a paper/thesis/report, a data plot (line, scatter, bar, error-bar, heatmap, log axis), a circuit diagram, a flowchart or block diagram, a free-body/force or geometry schematic, a biology figure (immunofluorescence/tissue, cell, signaling pathway, gene or plasmid map), a CS/ML figure (neural network, system architecture, finite-state machine, tree, graph), or a molecular structure — especially when they mention TikZ, PGFPlots, circuitikz, LaTeX figures, reproducible/vector/publication-quality plots, or editing an existing .tex figure. Produces reproducible .tex + data sources the user can re-edit.
-
pontjs Bundle Pontx HubDiscover, compare, inspect, preview, call, and integrate curated public APIs with Pontx Hub. Use whenever a user asks to find a public API for a task, identify which Endpoint or Schema returns a field, inspect PontxSpec or OpenAPI documentation, install provider-specific Skills, preview a request safely, confirm a mutation, or generate code with a published Pontx SDK.
-
ponylang Skill Write PatternGuide for writing new pattern pages in the pony-patterns documentation. Load when adding a new pattern or a new pattern category.
-
psylch Bundle Karpathy Rss Daily BriefingFetches Andrej Karpathy's curated RSS feed, reads ALL original articles, and generates a themed daily briefing document with citation links. This skill should be used when the user asks to generate a Karpathy RSS daily report, fetch Karpathy's curated RSS updates, or create an AI/tech daily briefing based on Karpathy's sources. Trigger phrases include "Karpathy 日报", "Karpathy RSS", "生成日报", "RSS briefing", "Karpathy daily".
-
qiao Bundle Rust API GuidelinesEnforces the official Rust API Guidelines (https://rust-lang.github.io/api-guidelines/) when writing, reviewing, or refactoring Rust library code. Use this skill whenever you are writing new Rust structs, enums, traits, functions, or modules that form a public API — including when designing error types, implementing conversions, naming methods, adding documentation, creating macros, or structuring crate features. Also use it when reviewing existing Rust code for API quality, idiomatic patterns, or crate publishing readiness. Trigger on any Rust library design task, even if the user doesn't explicitly mention "API guidelines."
-
psylch Skill Skill IssueReport skill bugs, design flaws, or suggestions to the centralized issue tracker. Use when a skill doesn't work as expected, has a design problem, or could be improved. Triggers: 'report skill issue', 'skill bug', 'skill problem', 'skill-issue', '上报skill问题', 'skill设计问题'
-
psylch Bundle Tech ResearchComprehensive technical research by combining multiple intelligence sources — Grok (X/Twitter developer discussions via browser automation), DeepWiki (AI-powered GitHub repository analysis), and WebSearch. Dispatches parallel subagents for each source and synthesizes findings into a unified report. This skill should be used when evaluating technologies, comparing libraries/frameworks, researching GitHub repos, gauging developer sentiment, or investigating technical architecture decisions. Trigger phrases include "tech research", "research this technology", "技术调研", "调研一下", "compare libraries", "evaluate framework", "investigate repo".
-
qingcaizz Bundle Github Trending TrackerUse when user wants to check GitHub trending projects, compare daily/weekly/monthly ranking changes, or generate trending reports. Triggers include "GitHub trending", "hot projects", "trending report", "trending changes", "热门项目", "趋势报告".
-
prairie2cloud Bundle TreelistyHierarchical project decomposition and planning. Use when breaking down complex projects, structuring information, planning multi-step workflows, or organizing any nested hierarchy. Supports 21 specialized patterns (WBS, GTD, Philosophy, Sales, Film, etc.) and exports to JSON, Markdown, and Mermaid diagrams.
-
prakhar1114 Bundle Fetch Weather ReportFetch the current weather forecast for a specified location and return a structured summary.
-
provablehq Skill Provable Sdk Tutorial DocsUse when writing tutorial documentation or create-leo-app examples for the Provable SDK (@provablehq/sdk). Covers how to structure runnable templates, write tutorial-style docs, and handle Node.js vs web runtime differences.
-
proyecto26 Bundle NotebooklmInteract with Google NotebookLM (notebook.google.com) notebooks — chat with the AI, generate artifacts (slides, audio, video, mind maps, quizzes, flashcards, infographics, reports, data tables), manage sources (add URLs, YouTube, files, text), run research (fast/deep web research), and manage notes. Use whenever the user mentions NotebookLM, a notebook.google.com URL, audio overviews, or wants to query, create content from, or manage their notebook sources — even if they don't say "NotebookLM" explicitly.
-
pramoddutta Skill Ttacart Pom CreatorGenerate a Playwright Page Object (POM) class for the TTACart demo app (app.thetestingacademy.com/playwright/ttacart) by driving the live page and reading its real selectors. Use this whenever the user gives a TTACart page URL plus a flow to reach it and asks to "create a page object", "build the POM", "scaffold a page class", "POM this page", "generate the page object for the checkout/inventory/cart page", or pastes a TTACart URL and wants a typed page class — even if they don't say the word "POM". The generated class extends BasePage and matches the existing LoginPage / CartPage / InventoryPage conventions exactly (data-test locators, .js ESM imports, the `el` wrapper, `open()` + `assertLoaded()`), then is wired into the pages barrel and verified with typecheck + lint.
-
pranavred Bundle Docs With MermaidCreate excellent technical documentation with Mermaid diagrams. Use when documenting code architecture, API flows, database schemas, state machines, system design, or any technical concept that benefits from visual diagrams. Also use when asked to explain code, create documentation, write README files, or document how systems work.
-
qkgecn93 Bundle Bys Work Report不一书工作汇报助手。写、改、诊断中文职场汇报——日报、周报、月报、项目汇报、专项汇报、述职报告、晋升答辩、年终总结、工作总结、项目复盘,以及延期/未达标/出事故这类坏消息汇报。 核心不是把三行字扩成八百字,而是反过来:把二十件杂事压成三件说得清的事,每条都带可验证的数字,并明确标出要领导做什么。 交付后可选让 AI 扮演你的直属领导或答辩评委做模拟评审并迭代,还会预测对方可能怎么回、你分别怎么接。 一次性使用和长期使用都支持:每次交付可顺手沉淀一份本地《工作留档》,日报素材自动复用到季度汇报和年终述职。 触发词包括但不限于:写周报、周报怎么写、这周周报、日报、月报、工作总结、年终总结、述职报告、晋升答辩、晋升材料、汇报材料、项目汇报、项目复盘、向领导汇报、跟老板汇报、工作汇报、绩效自评、360互评、这段工作怎么跟领导说、项目要延期了怎么说、目标没完成怎么汇报、初始化 不一书工作汇报助手。 即使用户只是丢来一段流水账、一份 git log、一堆聊天记录、一个空模板表格,说"帮我整成周报""这个怎么跟领导讲",只要上下文是向上级或评委汇报工作,都应该触发。 **不要 undertrigger。** 不加载就写,产出的会是一篇典型 AI 周报:形容词代替数字("显著提升"而非"从800ms降到200ms")、一是二是三是的对仗、结尾"后续将持续跟进"、个人贡献和团队成果混作一团。那种东西领导一眼认得出,而且在晋升答辩里是会被当场拆穿的。 不要用于:抖音口播稿(用 bys-koubo-writer)、公众号长文(用 khazix-writer)、对外的客户/投资人汇报、管理者汇总下属周报、与向上汇报无关的普通文档任务。
-
prefecthq Skill Writing DocumentationUse when writing, revising, reorganizing, or reviewing technical documentation — concept guides, feature docs, API references, developer-tool docs, tutorials, or docstrings that compile into user-facing docs. Covers both how to teach a single concept on one page and how to keep an entire documentation set coherent as it grows. Also covers short user-facing product text — UI copy, error messages, empty states, tooltips, and help text — which follows ASD-STE100 Simplified Technical English conventions (see "User-Facing Text"). Trigger whenever a task involves producing or improving end-user or developer-facing documentation, or when writing product strings a user will read. Not for README files (use crafting-effective-readmes), conversational walkthroughs of existing code or changes (use explain), or inline code comments.
-
prime-radiant-inc Bundle Proving It Works With A MovieUse when asked for a demo, screencast, tutorial, walkthrough, or proof video of software actually running, when a reviewer needs to see a feature work rather than take your word for it, or when handing over any video artifact of app behavior
-
qltysh Skill Bc CheckAnalyze a qlty pull request (or the current branch) for backwards-incompatible behavior changes. Use when the user asks to review a PR for backwards compatibility, BC breaks, or regression risk — especially before merging changes to the qlty CLI, qlty.toml schema, output formats, or command behavior. Produces a structured findings report.
-
qq-l-xx Bundle Cad Space PlanningUse when a user wants to extract, inspect, redesign, or deepen a DWG/DXF architectural or interior space plan, especially when room positions, retained elements, circulation, zoning, furniture capacity, or CAD/PDF deliverables must be verified against the real drawing.
-
quanru Bundle LifeosOperate, organize, initialize, migrate, and review a LifeOS Markdown knowledge base through the LifeOS CLI or Aino Mobile native tools.
-
pymodel Bundle Code MaxUse when implementing, debugging, reviewing, refactoring, hardening, or migrating code with evidence-backed acceptance criteria, regression protection, and an honest completion report. Adapt engineering rigor to any language, architecture, repository size, and available toolchain without imposing a framework or hiding incomplete work.
14 -
quantskills Bundle Futures Deepview Analyst基于 Pandadata 期货 DeepView 接口做期货品种、主力合约和跨期结构的综合研判,覆盖席位净持仓保证金、席位建仓、盈亏排行、多空比、资金流、基差、期限结构、仓单库存、虚实盘比、现货利润和跨期套利。Use when the user asks for 期货席位分析、持仓博弈、主力席位动向、基差或期限结构监控、仓单库存跟踪、虚实盘比、跨期套利扫描、期货品种综合分析, or a futures DeepView report for a variety or contract.
-
quran Bundle Quran Usage GuideUse when the user asks to quote an ayah/surah, translate a verse, explain meaning/context/tafsir, find verses about a theme, compare translations/tafsir, analyze Arabic word patterns, or view a mushaf page. Also use for any question the Qur'an might address, any Islamic question that might have an answer from tafsir or scholarly commentary, or anything where canonical scripture or insights from tafsir could ground or add value to the response.
-
reactivemarbles Skill Add DocumentationUse when adding or updating XML documentation for any public API in DynamicData, including new operators, changed behavior, batch documentation passes, or PR reviewer requests for improved docs. Covers extension methods, public classes, interfaces, enums, and any member visible in the published API reference.
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 md-pen, tighten-docs, slide-skill. 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.