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.
-
openinterpreter Bundle DocCreate, inspect, and edit Word documents (`.docx`) with local code-execution tools. Use for document drafting, structured edits, tables, comments, and layout-sensitive Word deliverables.
Audited -
openinterpreter Bundle PDFRead, create, edit, and verify PDFs with local code-execution tools and rendered-page inspection. Use whenever PDF layout, forms, extraction, merging, or final visual quality matters.
-
openinterpreter Bundle SlidesCreate, inspect, and edit editable PowerPoint (`.pptx`) decks with local code execution. Use for slide decks, presentations, speaker notes, charts, tables, images, and layout-sensitive presentation work.
-
openinterpreter Bundle Wiki LintHealth-check a persistent markdown wiki. Use this when the user wants to find orphan notes, dangling links, missing pages, graph gaps, contradictions to review, or general wiki maintenance opportunities.
-
openinterpreter Bundle Wiki QueryAnswer questions against a persistent markdown wiki and optionally file the answer back into the wiki. Use this when the user asks what their wiki says about a topic, wants a comparison across notes, or wants citations grounded in the wiki.
-
openinterpreter Bundle Wiki IngestIngest one new source into an existing persistent markdown wiki or established vault workflow. Use this when the user asks to add an article, PDF, note, URL, transcript, or other source into their wiki and wants the source filed, linked, indexed, and logged. If the wiki workflow does not exist yet, use $wiki-bootstrap first. This skill is for the ingest operation only.
-
openinterpreter Bundle Wiki BootstrapBootstrap a markdown workspace into a durable wiki structure. Use this when the user wants to initialize a wiki from an empty folder or convert an existing pile of notes into a more structured persistent wiki.
-
openinterpreter Bundle Wiki MaintainerBuild and maintain a persistent, interlinked markdown wiki (second brain / research notebook / personal knowledge base) from raw sources. Use this skill when the user wants to ingest an article / paper / note / URL / PDF into their wiki, ask a question against their wiki, lint/health-check their wiki, or set up a new wiki from a folder. Triggers include phrases like "add this to my wiki", "ingest this", "file this article", "update my notes with this", "what does my wiki say about X", "health-check my wiki", "find stale/orphan pages", or any workflow involving a `raw/` source folder, `wiki/` markdown folder, `index.md`, or `log.md`. Compatible with Obsidian vaults.
-
vfarcic Skill Reproduce FirstReproduce first, then fix — turn a reported defect into a failing test, fix it, and confirm that same test goes green. Use whenever the user describes the software behaving differently from what they expected or intended, however they phrase it: a complaint, a neutral observation, a question about whether something is meant to work that way, or an aside that something works "except for" one detail. It applies to a report that arrives mid-task about unrelated work, and to a symptom mentioned in passing. Trigger on the situation, not on any particular wording. Invoke it BEFORE reading code to diagnose the cause and before proposing any fix.
-
vfarcic Skill Dot AI ManageknowledgeManage the knowledge base: ingest documents, search with natural language, or delete chunks. Use "ingest" to store organizational documentation, "search" to find relevant content semantically, or "deleteByUri" to remove all chunks for a document. TIP: For complex questions, you can call search multiple times with different phrasings to gather comprehensive information before synthesizing your answer.
-
yokeloop Skill GpGit push with checks and report. Used when the user writes "push", "gp", "git push".
-
yokeloop Bundle ReviewFinds problems in code, fixes them and produces a report. Used when the user writes "review", "code review", "find issues", "find bugs", "check code", "code analysis", "prepare a report", "what's wrong with the code".
-
yokeloop Skill Yoke ReleasePublishing the yoke plugin: quality checks, documentation validation, version bump, tag, push, GitHub release. Used when the user writes "release", "publish", "ship version", "make a release", "prepare a release", "new version".
-
crealwork Skill Lead MagnetUse when creating a lead magnet end-to-end — brainstorming the offer with the user through Q&A, building the actual deliverable (checklist, guide PDF, template, swipe file), and wiring captured leads into a Google Sheets database. Triggers: "리드마그넷 만들자", "리드 마그넷 브레인스토밍", "무료 자료 만들어서 리드 모으고 싶어", "lead magnet", "무료 가이드 만들어줘", "이메일 수집하게 자료 하나". 뉴스레터 발송 자체는 e-blast-newsletter로.
Audited -
harperaa Bundle Gamma SlidesGenerate presentation slide decks from markdown content using the Gamma API. Use when user says "create slides", "make a presentation", "build a deck", "generate a slide deck", or asks to turn content into slides. Run with /gamma-slides.
-
yha9806 Bundle ExportConvert thesis chapters and reading notes from Markdown to Word (.docx) and package for submission. Use when preparing materials for supervisors or examiners.
-
yha9806 Skill ProgressShow reading and writing progress dashboard — how many sources read, chapters completed, word counts, and coverage gaps.
-
yha9806 Skill Manuscript ReframeReframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
-
zenithth Bundle Synthesizing KnowledgeUse when generating a comprehensive markdown knowledge document on a specific topic, where verified reference links and multi-source research are required.
-
zenithth Skill Youtube Minutes SynthesisUse when extracting a transcript from a YouTube video to summarize it like meeting minutes or generating a timestamped overview in a Markdown file.
-
alexeyshishin Bundle Code PlanDesign a feature before writing code. Spawns planner + skeptic subagents that read the Memory Bank, argue, and write a plan to swarm-report/. Use BEFORE /code-build, for any feature touching 2+ files or with unclear scope. Skip for typos and one-line fixes.
-
alexeyshishin Bundle Content FactoryA content factory — turns a single source into a full content package in one pass. Takes as input a finished article, a video transcript, OR (if there's only a topic) offers to run deep research and assemble a source itself. Output: a 1500–2500 word article, 10 threads, 5 Reels/Shorts scripts, 5 posts (Telegram/VK/MAX), 3 carousels, and a content plan — in 6 separate files. Preserves the author's voice, avoids repetition between units (angle matrix), doesn't invent facts, and runs every text through an anti-AI filter. Trigger: /content-zavod, "content factory," "turn this video/article into content," "cut this script into posts, reels, and carousels," "make content from a transcript."
-
alexeyshishin Bundle Obsidian IngestProcesses an arbitrary markdown file (article, web clip, transcript, notes, draft note) and turns it into structured knowledge for an Obsidian base using the PARA methodology. The skill extracts atomic entities (concepts, insights, facts), invents logical names for notes, creates a source literature note, and builds wikilinks and frontmatter. Use this skill whenever the user wants to "add this to the knowledge base", "rework this article", "process these notes", "extract the knowledge from this text", "ingest this", "put this in the vault", "put this in the base", or brings a markdown file to save into Obsidian.
-
alexeyshishin Bundle Content DocumentationStructures a technical tutorial — prerequisites, a "after reading this you'll be able to do X" goal, numbered steps with commands and checks, troubleshooting, cleanup. Doesn't write the full text: it produces a correct skeleton for the author to fill in with details. Use when "write a tutorial," "put together step-by-step instructions," "how-to," "tutorial," "deployment guide," "instructions for how to do X."
-
browseros-ai Skill Save PageSave web pages as PDF files for offline reading, archiving, or sharing. Use when the user asks to save, download, export, or archive a page as PDF.
Audited -
browseros-ai Skill Read LaterBookmark the current page to a "📚 Read Later" folder and save a PDF copy for offline reading. Use when the user wants to save a page for later, bookmark it for reading, or keep an offline copy.
Audited -
browseros-ai Skill Summarize PageExtract and summarize the main content of the current web page into structured markdown. Use when the user asks to summarize, digest, or get the gist of a page.
Audited -
browseros-ai Skill Screenshot WalkthroughCapture step-by-step screenshots of a workflow or process for documentation, bug reports, or tutorials. Use when the user asks to document steps, create a walkthrough, or capture a process.
Audited -
onescience-ai Bundle Onescience Paper ReproOneScience 论文复现信息提取技能。作为 onescience-orchestrator 的执行技能,接收论文输入,提取结构化信息,生成编码任务提示词。输入:论文来源(PDF/URL/arXiv/DOI)或论文信息;输出:reproduction_spec.md(结构化规格)、coder_task_description.md(编码任务提示词)。不执行编码,不调用其他技能。
-
platonai Bundle Task Token UsageAnalyzes Claude Code session traces (JSONL) and draft task files to report token usage per task. Use when asked about token usage, session costs, or task efficiency metrics.
-
platonai Bundle PDFExtracts text and tables from PDF files, fills PDF forms, and creates/merges/splits PDF documents. Use when users mention PDFs, forms, document extraction, or PDF generation.
Audited -
receptron Skill E2e Live Wiki実 mulmoclaude を叩く wiki カテゴリ (markdown image coverage) の総合テストを実行する。`yarn dev` が起動済みであることが前提。
-
receptron Skill E2e Live Media実 Claude API を叩く media カテゴリ(画像 / PDF / 動画)の総合テストを実行する。`yarn dev` が起動済みであることが前提。
-
receptron Skill Mc ZennTurn MulmoClaude work into a Zenn tech article (markdown) inside the workspace. On first use it sets up a Zenn project at `github/zenn/` — clone an existing GitHub repo or `zenn init` a fresh one, idempotent and skipped when already initialized — then writes articles to `github/zenn/articles/<slug>.md` tagged with the `MulmoClaude` topic. Use when the user says "Zenn にまとめて", "この作業を記事にして", "share this on Zenn", "Zenn 始めたい", or "Zenn のリポを用意して".
-
receptron Skill Mc Cooking CoachPersonal recipe book — save / read / update / delete cooking recipes as markdown files under `data/cooking/recipes/`, with a `README.md` index that lists every recipe. Use when the user asks to remember a recipe, look one up, or refine one.
-
receptron Skill Mc Manage SkillsSave, edit, list, or delete a Claude Code skill in this workspace. Use when the user wants to turn a workflow into a reusable skill ("skill 化して", "save this as a skill"), modify or remove one, or list what's registered. Writes one markdown file per skill at `data/skills/<slug>/SKILL.md`; a workspace-side hook mirrors it into `.claude/skills/<slug>/SKILL.md` so Claude Code picks it up.
Audited
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 doc, pdf, slides. 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.