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.
-
masriyan Bundle MultilingualMultilingual communication, translation, localization, and language quality skill for translating, rewriting, localizing, summarizing, tone-matching, and reviewing content across languages. Use for multi-language prompts, UI strings, documentation, cultural adaptation, terminology consistency, bilingual output, language detection, and Indonesian/English or other cross-language workflows.
-
masriyan Bundle Bug Bounty WorkflowBug bounty workflow skill for program scope mapping, recon-to-report automation, deduplication against prior submissions, and high-signal reporting on HackerOne, Bugcrowd, Intigriti, YesWeHack, and self-hosted programs. Use to organize bounty work end to end while staying inside program rules.
-
ousiass Bundle Doc Drift EnCheck documentation vs implementation code consistency and generate drift report.
-
ousiass Bundle Bug Report EnInteractively gather bug details, investigate code, and create a structured GitHub Issue.
-
ousiass Bundle Code Review EnFull codebase quality check and refactoring review with report generation.
-
ousiass Bundle Doc Drift Git EnCheck doc-code consistency on git diff against remote and generate drift report.
-
futurewithvibe Skill ObsidianObsidian vault integration for markdown notes
-
boltaai Skill Brand Voice ValidateScore a piece of content against the brand's voice guideline and return a compliance report with specific fixes. Use this skill when the user asks "is this on-brand", "score this against our voice", "check brand compliance", "validate this post", "does this sound like us", "rate this copy", or pastes content and wants a voice check. Returns a 0-100 score plus a deviation report and concrete edits. For writing new on-brand content use brand-voice-enforce; for building the guideline itself use brand-voice-generate.
-
rooseveltadvisors-claude-agent-stack Bundle ParserExtract structured JSON from URLs, files, videos, PDFs with entity extraction and batch support. USE WHEN parse, extract, URL, transcript, entities, JSON, batch, content, YouTube, PDF, article, newsletter, Twitter, browser extension, collision detection, detect content type, extract article, extract newsletter, extract YouTube, extract PDF, parse content.
-
pedrohcgs Skill ProofreadRead-only proofreading pass over lecture `.tex` or `.qmd` files. Checks grammar, typos, overflow, terminology consistency, and academic writing quality; produces a report without editing. Use when user says "proofread", "check for typos", "look for grammar issues", "copy-edit this", "any writing errors?", or before a lecture release.
-
pedrohcgs Skill Extract TikzExtract TikZ diagrams from Beamer `.tex` source, compile each to a standalone PDF, and convert to SVG with 0-based indexing. Use when user says "extract the tikz", "regenerate the diagrams", "rebuild the SVGs", "sync tikz to quarto", or after editing TikZ blocks in a Beamer deck that also has a Quarto mirror.
-
pedrohcgs Skill Coauthor BriefGenerate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact (manuscript, analysis, slides), open questions, how to reproduce locally, and any restricted-data access steps. Use when user says "coauthor brief", "handoff brief", "bring my coauthor up to speed", "what changed since last week", "onboard a collaborator", "write a handoff for [name]", or before sending a co-author the repo. NOT a commit or a checkpoint — it is the cross-machine, cross-person summary `meta-governance.md` only partially covers.
-
pedrohcgs Skill Devils AdvocateAdversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation. Use when user says "devil's advocate", "poke holes in this deck", "push back on my slides", "stress-test the design", "what would a skeptical student ask?". Read-only; surfaces questions to force rethinking. Lighter than `/pedagogy-review`.
-
pedrohcgs Skill Pedagogy ReviewHolistic pedagogical review of a lecture deck (`.qmd` or `.tex`). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before teaching a deck for the first time. Read-only; produces a report.
-
pedrohcgs Skill R Package CheckRun the full R package release gate — regenerate docs, run the test suite, run R CMD check --as-cran, and triage every ERROR / WARNING / NOTE against CRAN policy before a release or submission. Use when the user says "check my R package", "R CMD check", "is this package CRAN-ready", "run devtools::check", "prepare for CRAN submission", or points at a directory containing a DESCRIPTION file. Produces a check report + CRAN-submission checklist in `quality_reports/`.
-
pedrohcgs Skill Respond To EvalTurn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the syllabus and slide decks. Use when user says "respond to my evals", "what do these course evaluations tell me", "turn my teaching feedback into a plan", or after a semester's evals arrive.
-
pedrohcgs Skill Respond To RefereesGenerate a structured response-to-referees document from a referee report and the revised manuscript. Maps each referee comment to the specific revision, classifies coverage (addressed / partially / deferred / disagreement), and drafts polite but firm responses. Use during the R&R (revise-and-resubmit) stage of paper revision.
-
armanzeroeight Bundle Readme GeneratorCreates comprehensive README files with templates for different project types. Use when creating README, project documentation, or getting started guides.
-
armanzeroeight Skill API Documentation GeneratorGenerate OpenAPI/Swagger specifications and API documentation from code or design. Use when creating API docs, generating OpenAPI specs, or documenting REST APIs.
-
armanzeroeight Skill Changelog ManagerMaintains changelogs following Keep a Changelog format, categorizes changes by type. Use when updating CHANGELOG, preparing releases, or documenting version changes.
-
ninthspace Bundle NoteplanSearch and query NotePlan content across markdown files and Spaces (team/shared) SQLite database. Use when user wants to search NotePlan notes, find content, list notes, or fetch specific notes. Triggers on "/noteplan", "search NotePlan", "find in my notes", "search spaces", "list NotePlan notes".
-
ninthspace Skill StatusProject status reconnaissance. Scans CPM artifacts, git history, and codebase changes to produce an ephemeral status report with recommended next steps, plus an optional full-picture dashboard published as a shareable artifact on request. Triggers on "/cpm:status".
-
rooseveltadvisors-claude-agent-stack Bundle CreatecliGenerate production-ready TypeScript CLIs with 3-tier template system (simple argv, yargs, oclif), type safety, error handling, and documentation. USE WHEN create CLI, build CLI, command-line tool, wrap API, add command, upgrade tier, TypeScript CLI.
-
ninthspace Skill PublishRegenerate the markdown projection and the committed dump from the database, so what is on disk matches what the planning database holds. Names every file that would be removed and asks before removing it. Triggers on "/dpm:publish".
-
rooseveltadvisors-claude-agent-stack Bundle PDFCreate, merge, split, extract text/tables from PDFs, fill forms, add watermarks, and convert to/from other formats. USE WHEN pdf, PDF file, merge PDF, extract tables, fill form, split PDF.
-
rooseveltadvisors-claude-agent-stack Bundle DOCXCreate, edit, and analyze Word documents — tracked changes, tables, images, complex formatting, and format conversion. USE WHEN docx, Word document, create document, tracked changes, redlining.
-
rooseveltadvisors-claude-agent-stack Bundle PPTXCreate, edit, and analyze PowerPoint presentations — slide layouts, speaker notes, design elements, and format conversion. USE WHEN pptx, PowerPoint, slides, presentation, create slides, speaker notes.
-
snqb Bundle MdCreate and edit Markdown with all format possibilities. Covers CommonMark, GitHub Flavored Markdown, LaTeX math, Mermaid diagrams, and Obsidian extensions (wikilinks, callouts, embeds, properties). Use when working with .md files or needing markdown syntax reference.
-
snqb Bundle PDFComprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
-
gate Bundle Gate News BriefingNews briefing. Use this skill ONLY when the user's query is exclusively about recent news or headlines with no other analysis dimensions. Trigger phrases: what happened recently, today's highlights, crypto news, any new updates. If the query ALSO mentions coin analysis, risk check, technicals, or any other analysis dimension, use gate-info-research instead — it handles multi-dimension queries in a single unified report.
-
snqb Bundle TicketFast, git-native task tracking using Markdown files. Replaces Beads.
-
snqb Skill FuckoffGenerate a short handoff report from the current session. Collects git changes, screenshots, context automatically. Use when task is done and user says 'отчёт', 'report', 'скинь клиенту', 'fuckoff', or needs to hand off work.
-
snqb Bundle Share MdShare Markdown files as public web pages via rentry.co. Paste MD → get URL. Use when asked to 'share', 'publish', 'send link' for any .md file or report.
-
snqb Bundle BackreasonMine pi session history to discover what the user actually cares about. Use empirical evidence (session starters, concept frequency) to improve AGENTS.md, navigation maps, skill gaps, or any documentation. "What do I keep asking about?" → make it findable.
-
dmccreary Bundle Book PublisherPublishes and promotes a finished intelligent textbook - GitHub README with badges and site statistics, LinkedIn announcement posts, LinkedIn carousel document posts (PPTX/PDF slideshows), and AP-style press releases. Use when announcing a book milestone or updating repository documentation. Routes to the appropriate guide.
-
snqb Bundle NotebooklmProgrammatic control of Google NotebookLM — create notebooks, add sources (URLs, PDFs, YouTube, text), query with Gemini, generate artifacts (podcasts, videos, quizzes, slides, mind maps), download everything. Uses notebooklm-py (unofficial RPC API).
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 respond-to-eval, doc-drift-en, multilingual. 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.