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.
-
rwilson504 Skill Dataverse Classic CompareStructurally diff two Dataverse Classic Workflow XAML files and report what actually changed. Use when user says "what changed between these two workflows", "diff these workflows", "compare version A and B", "compare DEV and PROD copies of this workflow", "why does this behave differently in the other environment", "did anything change other than formatting", or supplies two `.xaml` files. Compares triggers, scope, steps, and conditions at the activity level rather than by text diff, so reordered attributes, regenerated GUIDs, and `UserData` designer blobs do not drown the real differences. Do NOT use for summarizing a single workflow (use dataverse-classic-read), applying changes (use dataverse-classic-write), or cloning one workflow into another (use dataverse-classic-copy).
-
kesslerio Skill Openclaw DocsWrite or review high-quality OpenClaw developer documentation.
-
allanninal Skill Doc GenerateGenerate documentation from code including API docs, README sections, and CLAUDE.md files. Use when documenting APIs, creating setup guides, or updating project documentation.
-
sitaggart Skill Docs ResearcherResearch official documentation and version-specific constraints for a framework, library, or API when current external behavior materially shapes a plan or implementation. Returns official-docs findings, version caveats, and community patterns.
-
sitaggart Skill Document ReviewReview requirements, PRDs, kickoff docs, and implementation plans with taste. Use after ce-plan for markdown plans, before ce-plan for requirements docs that need a quality pass, or whenever a written project artifact needs sharper scope, coherence, and reader utility.
-
sitaggart Bundle Principle Prove It WorksApply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
-
sitaggart Skill Repo Research AnalystPerform scoped repository reconnaissance — technology, architecture, patterns, conventions, issues, templates — and return a compact evidence-backed markdown summary inline. Use when onboarding to a codebase, grounding a plan, or when a loop skill dispatches scoped repo research.
-
allanninal Skill Changelog GeneratorTransform git commits into customer-friendly release notes and changelogs. Use when preparing releases, generating CHANGELOG.md, or creating release documentation.
-
willoscar Bundle Rubric WriterUse when `paper-review` has claims plus evidence gaps and needs the final referee-style report.
-
willoscar Bundle Latex ScaffoldScaffold a LaTeX project (`latex/main.tex`, optional bibliography wiring, structure) from an existing Markdown draft.
-
willoscar Bundle Beamer ScaffoldGenerate a Beamer slide deck from the final tutorial and approved module structure.
-
mattwoodco Skill SlidesTransform markdown to beautiful Apple-like presentation slides using Marp. Use this skill when the user says "create slides", "make presentation", "markdown to slides", "generate deck", or "create powerpoint".
-
willoscar Bundle Outline RefinerPlanner-pass coverage + redundancy report for an outline+mapping, producing `outline/coverage_report.md` and `outline/outline_state.jsonl`.
-
willoscar Bundle Writer SelfloopWriting self-loop for surveys: run the strict section-quality gate, then rewrite only the failing `sections/*.md` files until the report is PASS.
-
willoscar Bundle Evidence AuditorUse when `paper-review` needs a claim-by-claim evidence gap report grounded in an extracted claim ledger.
-
willoscar Bundle Idea Memo WriterSynthesize the shortlist into a discussion-ready research idea brainstorm memo, writing `output/REPORT.md`, `output/APPENDIX.md`, and `output/REPORT.json`.
-
willoscar Bundle Latex Compile QACompile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report.
-
zhizhunbao-ai-dev-config Bundle DOCX To MdWord 文档转 Markdown。Use when (1) 将 .docx 转换为 .md, (2) 提取 Word 文档内容, (3) 批量转换文档, (4) 保留格式和图片, (5) 自动化文档处理
-
zhizhunbao-ai-dev-config Skill Dev TranslationIT technical document translation assistant. Use when (1) translating technical articles, documentation, or papers, (2) creating bilingual (Chinese-English) content, (3) ensuring technical term consistency, (4) translating code comments or API docs.
-
willoscar Bundle Beamer Compile QACompile the Beamer tutorial deck and write a build report.
-
willoscar Bundle Citation InjectorAPPLIES/consumes a `citation-diversifier` budget report (`output/CITATION_BUDGET_REPORT.md`) to inject *in-scope* citations into an existing draft (NO NEW FACTS), so the run passes the global unique-citation gate without citation dumps.
-
mattwoodco Skill ComplianceGenerate Architecture Decision Records (ADRs), operational runbooks, and project documentation. Use this skill when the user says "create adr", "document decision", "setup compliance", "add runbook", "architecture decision", or "operational docs".
-
zhizhunbao-ai-dev-config Bundle Dev Markdown CheckMarkdown format validation and quality checker. Use when (1) checking markdown syntax errors, (2) validating document structure, (3) fixing formatting issues, (4) ensuring markdown best practices, (5) reviewing generated markdown files.
-
zhizhunbao-ai-dev-config Bundle Dev PDF ProcessingComprehensive PDF processing toolkit. Use when (1) extracting text/tables from PDFs, (2) converting PDF to markdown, (3) creating bilingual documentation, (4) processing academic materials, (5) filling PDF forms, (6) merging/splitting PDFs, (7) creating new PDFs programmatically.
-
zhizhunbao-ai-dev-config Skill Dev Document ReviewSystematically review technical documentation for quality issues. Use when (1) user asks to check/review a document, (2) mentions consistency/accuracy/errors in docs, (3) needs feedback on technical writing quality.
-
zhizhunbao-ai-dev-config Bundle Learning Md To DOCXConvert markdown lab reports to Word documents with proper formatting. Use when (1) user needs to submit .docx, (2) mentions "转docx" or "convert to word", (3) preparing lab submission.
-
zhizhunbao-ai-dev-config Bundle Full DevelopmentComplete software development lifecycle from requirements to deployment. Use when (1) starting a new project from scratch, (2) need structured end-to-end development process, (3) require comprehensive documentation and quality gates at each phase.
-
zhizhunbao-ai-dev-config Skill Learning Note TakingAdd concise study notes to lecture materials. Use when (1) user asks to add notes to extracted PDFs/slides, (2) mentions "笔记" or "notes", (3) organizing course content.
-
zhizhunbao-ai-dev-config Bundle Learning Code ScreenshotGenerate code and output screenshots from Python scripts for assignment documentation. Use when (1) user needs to create screenshots for Lab.docx, (2) mentions "代码截图" or "screenshot", (3) needs to capture code execution and results.
-
zhizhunbao-ai-dev-config Bundle Bilingual ContentGenerate bilingual learning materials from structured content. Use when (1) translating technical articles, (2) creating dual-language study notes, (3) preparing course materials with original and translation, (4) converting scraped content to bilingual markdown.
-
zhizhunbao-ai-dev-config Bundle Learning Assignment DocumentCreate assignment submission documents (Word/PDF) with screenshots, discussions, and analysis. Use when (1) user needs to create Lab.docx or Assignment.docx, (2) mentions "作业文档" or "submission document", (3) needs to organize screenshots and discussions for submission.
-
zhizhunbao-ai-dev-config Bundle Brightspace ScraperScrape course materials from Brightspace LMS. Use when (1) need to download course content (slides, labs, assignments), (2) organize course materials locally, (3) filter specific module types, (4) batch download from multiple courses.
-
willoscar Bundle Tutorial SelfloopRun a tutorial-specific quality gate and write a PASS/FAIL report for the final tutorial deliverable.
-
willoscar Bundle PDF Text ExtractorDownload PDFs (when available) and extract plain text to support full-text evidence, writing `papers/fulltext_index.jsonl` and `papers/fulltext/*.txt`.
-
willoscar Bundle Citation DiversifierPRODUCES a citation-budget plan/report (`output/CITATION_BUDGET_REPORT.md`); does NOT edit the draft. Allocates an in-scope per-H3 budget (NO NEW FACTS) so drafts stop failing the global unique-citation gate; citation-injector applies it.
-
zhizhunbao-ai-dev-config Bundle Textbook VectorizationVectorize PDF textbooks for semantic search. Use when (1) need to quickly find concepts in textbooks, (2) building personal knowledge base, (3) preparing study materials with searchable content, (4) want to query textbook semantically.
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 openclaw-docs, doc-generate, changelog-generator. 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.