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.
-
1weiho Bundle Slide AuthoringTechnical reference for writing or editing open-slide pages — file contract, 1920×1080 canvas, type scale, layout, palette/visual direction, assets, speaker notes, stepped reveals, page transitions, and morph transitions. Consult this whenever you are about to write or modify any file under `slides/<id>/`, including from inside the `create-slide` or `apply-comments` workflows, or for any ad-hoc slide edit. Triggers on phrases like "edit slide", "tweak this page", "fix the layout", "change the palette", "reveal one by one", "add a transition", "morph transition", "write the speaker notes", "generate the script / talk track", "investigate the slide framework", "how do slides work here".
-
jpfrancoia Bundle Simple EnglishWrite or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop. Use for documentation, READMEs, runbooks, procedures, error messages, release notes, incident reports, and API guides. Also use when the user says "STE", "Simplified Technical English", "ASD-STE100", "de-slop", "make this readable", "write for non-native readers", or asks for docs that translate well. Enforces the standard's 53 rules: 20/25-word sentence limits, one word one meaning, simple tenses, active voice, condition before command.
-
jpfrancoia Skill Clarifying QuestionsAsk one structured implementation decision at a time, with a recommendation and result-focused options. Use when code and documentation cannot resolve a decision that materially changes behavior, risk, cost, or scope.
-
machow Bundle Code StandardsCode standards and patterns for great-tables development. Use when writing new code, reviewing PRs, or refactoring. Covers testing patterns, architecture, documentation, and API design.
-
nangohq-nango Skill Creating Integration DocsUse when adding or editing Nango integration documentation - creates and maintains integration pages, setup guides, connect guides, navigation, and provider metadata following established patterns
-
deepread-tech Skill Deepread Form FillAI-powered PDF form filling via DeepRead. Upload any PDF form + your data as JSON — AI detects fields, maps data semantically, fills the form with quality checks, returns a completed PDF. Works with scanned, non-editable forms — no AcroForm required.
-
deepread-tech Skill Deepread Resume ParserParse resumes and CVs into structured JSON — contact info, work history, education, skills, and total years of experience. Works on PDF, Word-exported PDF, and scanned resumes in any layout. Per-field confidence flags. PII redaction for bias-free screening. Free 2,000 pages/month.
-
deepread-tech Skill Deepread Bank StatementsExtract structured data from bank statements — account holder, period, opening/closing balances, and every transaction as typed JSON. Works on PDF and scanned statements from any bank. Per-field confidence flags. PII redaction for compliant sharing. Free 2,000 pages/month.
-
glassbead-tc Bundle Effect TSEffect-TS expert — write, debug, refactor, and explain code using the Effect ecosystem (effect, @effect/platform, @effect/rpc, @effect/cli, @effect/schema, @effect/cluster). Use this skill whenever the user works with Effect-TS code, mentions Effect services/layers/fibers/streams/schedules, asks about Effect error handling or dependency injection, wants to migrate code to Effect, or asks questions like 'how do I do X in Effect'. Also trigger when you see Effect imports in code being discussed, or when the user mentions Effect patterns like generators, pipe, Context.Tag, Layer.provide, or Schema.Class. This skill has a semantic search index over the full Effect documentation — use it to ground answers in official docs rather than guessing.
-
vernonoy Skill Alpha ReportFactor reports. Generate panoramic, deep-dive, or comparison reports. 因子报告。生成全景、深度、对比报告。 Triggers: "generate report", "factor report", "生成报告", "因子报告"
-
leefowlercu Bundle Go StandardsStdlib-grounded Go engineering standards for implementing, reviewing, refactoring, or testing Go code. Use when Codex works on Go packages, CLIs, libraries, concurrency primitives, parsers, formatters, config loading, errors, documentation, examples, table-driven tests, fuzz tests, compatibility-sensitive APIs, or repository standards for high-quality Go code.
-
leefowlercu Bundle Subsystem MdInitialize or update subsystem documentation.
-
cosmonic-labs Bundle Rust DevelopmentExpert Rust development guidance covering naming conventions, type safety, error handling, documentation, and best practices based on official Rust guidelines. Use this skill when writing new Rust code, reviewing or modifying existing Rust code, designing Rust APIs or libraries, refactoring Rust codebases, or whenever the user mentions Rust, Cargo, clippy, rustfmt, traits, lifetimes, or `.rs` files.
-
egermano Bundle Doc ManagerCreates and updates markdown documentation with clear explanations and code examples for complex concepts. Use when the user needs to generate technical documentation, update existing docs, or explain concepts with practical examples.
-
egermano Bundle Text ProcessorPerforms text manipulation operations including case conversion (uppercase, lowercase, capitalize), text reversal, and word counting. Use when the user needs to transform, analyze, or manipulate text strings.
-
sjungling Bundle PDF GenerationThis skill should be used when the user asks to "generate a PDF from markdown", "create a printable book", "convert documentation to PDF", or "export chapters as a PDF". Automatically activates when producing a PDF from a directory of ordered markdown chapters using pandoc and weasyprint. Not for single-file markdown-to-PDF conversion or non-documentation use cases.
-
sjungling Bundle Obsidian Vault ManagerThis skill should be used when the user asks to "manage Obsidian vault", "create a daily note", "move notes without breaking links", "search vault content", or "organize Obsidian notes". Automatically activates when working with Obsidian vaults, markdown notes with [[wiki-links]], daily notes, templates, or tags. Not for general markdown editing outside Obsidian vaults.
-
rezkam Skill VerifyEstablish that a change actually works before reporting it done, and report what was run in a fixed shape. Use before any completion claim, when the user asks "did you run it" or "is it done", and after any fix that has not been executed.
-
yugasun Bundle Baidu SearchSearch the web using Baidu AI Search Engine. Use for live information, documentation, or research topics.
-
shareai-lab Bundle Understanding First ReportReconstruct and report long-running or multi-turn research, architecture questions, reviews, decisions, completion results, and status as a clear, self-contained brief. Use when a reader must re-enter earlier context, understand the real question and its relationships, distinguish verified facts from judgment and open evidence, or make a decision without reconstructing the work log. Quote the relevant original user wording before substantive analysis, keep one coherent main line, use spatial diagrams when relationships matter, and finish with an explicit decision boundary and practical next step.
-
canvas-medical Bundle Canvas SdkCanvas SDK reference and documentation. Use whenever a question, claim, or piece of code touches Canvas SDK capabilities, API usage, implementation patterns, or testing — including quick conversational questions ("how do I ingest ADTs?", "what's the import for X?", "does Canvas support Y?"). The bundled docs are the source of truth; do not answer Canvas SDK questions from memory.
-
canvas-medical Bundle Fhir API Client DevelopmentFHIR API reference and documentation for Canvas plugins that need to read or write data via FHIR endpoints
-
kiraneswaran Bundle Documentation StandardsDocumentation best practices including Markdown formatting, Mermaid diagrams, technical writing, ADRs, and open source standards. Use when writing documentation, README files, markdown content, creating diagrams, or when asking about documentation structure, technical writing, or open source project setup.
-
bazelbuild Bundle Analyze CI FailureDownload and analyze a CI failure log to construct an actionable suggested fix plan and report back
-
brucehart Bundle Fill PDFFill interactive PDF forms with pdftk using structured context values. Use when the user provides a fillable PDF plus field data (or natural-language context) and wants a completed output PDF, flattened final copy, or help mapping context keys to PDF form field names.
-
soju06 Skill Openspec Context DocsOpenSpec context documentation policy: keep requirements in spec.md and capture narrative context in context/overview/rationale docs under openspec/specs. Use when creating or updating OpenSpec docs, spec context, or onboarding/guide documentation.
-
huangjia2019 Skill Code Health CheckPerform a comprehensive code health check on a directory. Use when the user asks to analyze code quality, find issues, or get a health report.
-
schovi Skill ReleaseCut a CI-gated GitHub release for projects distributed through Homebrew, GoReleaser, GitHub Releases, casks, formulae, or SemVer tags. Handles version selection, CI gating, release notes, optional GoReleaser automation, tag publishing, release verification, and a follow-up documentation-sync pull request. Explicit invocation only (/homebrew:release in Claude Code, `use $release` in Codex).
-
schovi Bundle Batch WorkRun multiple Ready tasks from the repo's workflow/ status folders sequentially in isolated subagents, with a consolidated report. Use when the user asks to batch-run tasks, run work overnight, run the first N Ready tasks, or invokes /workflow:batch-work, /batch-work, or /batch.
-
schovi Bundle Framework InitExplicit invocation only. Initialize the workflow framework in a repo that does not have one: create the workflow/ status folders, install the board-view script, write the repo contract, scaffold the docs skeleton, and route AGENTS.md to the plugin. Use only when the user explicitly invokes "/workflow:framework-init", says "init the workflow" or "set up the board here", or invokes "use $framework-init". Never invoke this skill because a different workflow skill found no workflow/AGENTS.md. A repo with an existing legacy markdown board must be migrated to status folders by hand first.
-
grafana Bundle Docs ReviewReview documentation changes for style, accuracy, and completeness. Use when docs have been written or updated and need a quality check before submission, when the user asks to review docs, proofread, check style compliance, or verify technical accuracy of documentation.
-
grafana Bundle Docs Pr WriteWrite or update product documentation for user-facing PR changes. Use when the user asks to write docs for a PR, document a PR, update existing docs based on a code change, process PRs flagged by docs-pr-check, or provides PR numbers or links and wants the corresponding documentation created or updated — even if they say "document these changes" without mentioning PRs explicitly. This skill writes and updates docs only; it does not triage PRs (use docs-pr-check), review existing docs (use docs-review), or generate release notes.
-
grafana Bundle Persona CheckUse this skill to assess whether documentation content fits its intended audience. Identifies the target persona (Learner, Practitioner, Expert, Operator), use case, and entry state, then flags mismatches between the content and what that audience needs. Use when the user asks to check persona fit, review audience alignment, asks "who is this page for?", questions whether content is at the right level of detail, or mentions /persona-check. Also use when reviewing a PR where content seems too advanced, too basic, or aimed at the wrong reader. This is not for style guide, grammar, or link checking — use docs-review for those.
-
grafana Bundle Sembr ReformatReformat prose using Semantic Line Breaks (SemBr) from https://sembr.org while preserving rendered output and meaning. Use when asked to reflow plain text or compatible markup (Markdown, AsciiDoc, reStructuredText, LaTeX, Org, MediaWiki) into semantic one-thought-per-line formatting, or when improving prose diffs and editorial readability.
-
fusionet24 Skill Documentation WriterActivates when creating or improving technical documentation, READMEs, and API docs
-
cloudflare Skill Pr Review GuideGuidelines for posting pull request review comments via GitHub CLI, including suggested edits format, handling unresolved comments, etiquette, and report/issue tracking. Load this skill when reviewing a PR via GitHub and posting inline comments.
2.1k
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 slide-authoring, simple-english, clarifying-questions. 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.