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.
-
tommyducx Bundle PDF Image Text Extractor从图片或 PDF 文档中识别并提取文字内容,支持多种图片格式和 PDF 文件,自动判断是否包含文字并保留原始格式输出结构化结果;v2.1 采用零额外依赖方案:扫描版 PDF 自动渲染为图片交由 AI 视觉识别(无需 tesseract/rapidocr)、表格用 pymupdf 内置 find_tables 结构化提取(无需 pdfplumber)、批量处理目录(PDF+图片一次性提取);当用户需要从图片或 PDF 提取文字、进行 OCR 识别、处理含文字的文档、提取 PDF 表格、批量处理文件夹或转换为可编辑文本时使用。该skill能力来自RedFoxHub,官网:https://redfox.hk/skills。
-
yogiraja Skill WatchWatch and analyze any YouTube video by fetching its transcript, then summarizing it, extracting key takeaways, pulling quotes, building timestamped chapter notes, listing action items, or answering a specific question about it. Use this whenever the user shares a YouTube link (youtube.com or youtu.be) and wants to know what's in it, says "watch this", "summarize this video", "give me the key points / notes / takeaways from this talk", "what does this video say about X", "tldr this YouTube video", or wants to skip watching something and get the content fast. Trigger even when the user just pastes a YouTube URL with a brief instruction, and even if they never say the word "watch".
-
yogiraja Bundle QA DeckQA pass on a PowerPoint deck. Renders every slide and checks it for visual defects and fabricated facts. Use when the user asks to QA or check over a .pptx, and proactively before a deck is delivered or after its slides are edited.
-
arozumenko Bundle Reproducing IssuesUse when a bug is unclear or unconfirmed and needs reproduction before RCA or any fix. Turns a vague bug report into precise, repeatable steps with evidence and a CONFIRMED / CANNOT-REPRODUCE / PARTIAL verdict. Reproduction and documentation only — does not fix code.
-
insideto27 Bundle Lark Slides飞书幻灯片:创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面(创建、删除、读取、局部替换)。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时,也应直接使用本 skill,不要因为域名不是飞书而回退到 WebFetch;路由依据是 URL 路径模式和 token,而不是域名。不负责:云文档内容编辑(走 lark-doc)、云文档里的独立画板对象(走 lark-whiteboard)、上传或下载普通文件(走 lark-drive)。
-
arozumenko Bundle Reproducing Issues 2Use when a bug is unclear or unconfirmed and needs reproduction before RCA or any fix. Turns a vague bug report into precise, repeatable steps with evidence and a CONFIRMED / CANNOT-REPRODUCE / PARTIAL verdict. Reproduction and documentation only — does not fix code.
-
insideto27 Bundle Amazon Negative Keyword Batch ReviewReview MT002 Sponsored Products search terms from the prepared Feishu increment workbook, the manual workbook, or a user-provided report folder. Screen existing-negative coverage and stage Chinese-translated candidates for human review; not for ad changes or a full PPC rebuild.
-
swyxio Bundle AI ReadmeCreate or substantially revise repository README files that help a specific reader understand a technical project, reach a verified first result, and progress into realistic use, evaluation, debugging, or contribution. Use for project landing READMEs, CLI and library quickstarts, experimental or research repositories, executable engineering notebooks, and contributor-facing repository guides when Codex should reconstruct behavior from code, tests, commands, examples, and history rather than write generic documentation.
-
swyxio Bundle AI DevblogTurn coding, debugging, research, architecture, migration, deployment, or product work into a clear, evidence-backed technical post in an existing publishing system. Use when Codex should reconstruct primary evidence, decide whether the material deserves a note or article, align on the intended reader, choose among field-report, explainer, reversal, origin-story, hands-on, or evidence-led argument forms, write and edit the piece, inspect its rendered presentation, and publish it at the requested visibility. Pair with blog-system-design for changes to the shared blog system.
-
swyxio Bundle Youtube Studio Batch UploadBatch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files. Use when Codex needs to download many submitted videos, stage filenames, build YouTube titles/descriptions from table fields, upload through Chrome/Computer Use, set videos Unlisted, add a playlist, save each upload before moving on, track links, and report incomplete or blocked source rows.
-
swyxio Bundle Swyx WritingApply swyx's reusable nonfiction writing preferences when drafting or materially revising prose, including technical posts, essays, research memos, reports, documentation, profiles, scripts, announcements, and publishing copy. Use as the shared style and editing layer alongside the skill that owns the subject or format. Do not use for verbatim transcription, code-only work, or fiction unless the user explicitly asks for swyx's nonfiction voice.
-
00200200 Skill Mkl Write ReadmeCreate or improve a repository README from actual project evidence, with a clear purpose, usable quickstart, and honest limitations. Use for project landing documentation and onboarding, rather than long tutorials or release notes.
-
00200200 Skill Mkl Reproduce BugReduce a reported software bug to a runnable, minimal reproduction with the exact command, environment, and observed failure. Use when verifying a bug report; do not infer success from a failing setup command.
-
00200200 Skill Mkl Localize Pl EnTranslate and localize Polish and English technical documentation, UI text, and project updates. Use for natural PL/EN phrasing while preserving commands, placeholders, factual precision, and a project glossary.
-
swyxio Bundle Visual PlaytestVisually inspect a local or deployed site/app in a real browser and report concrete layout, responsive, or design regressions. Use when asked to visually check UI changes, reproduce a screenshot issue, compare a page with a reference, or playtest representative visual states. Do not use for code-only review or open-ended design ideation.
-
swyxio Bundle Transcribe AnythingTranscribes audio and video files to text using pluggable ASR backends. Default backend is local whisper/MLX Whisper for ASR. Supports pyannote.audio direct diarization, whisperX, insanely-fast-whisper, faster-whisper, whisper.cpp, OpenAI Whisper API, Groq Whisper API, Deepgram, AssemblyAI, Gemini, and Hugging Face models. Handles very long files (1-8+ hours) by preprocessing with ffmpeg: extracts audio from video, converts to optimal ASR format, detects and skips silence, and chunks for API size limits. Supports speaker diarization, word-level timestamps, custom vocabulary, and multiple output formats. Use this skill when someone says "transcribe this", "convert to text", "speech to text", "get the transcript", "transcribe this video/audio/podcast/recording", or provides a media file and wants text output.
-
ivy00johns Bundle Repo Deep DivePerform a comprehensive technical deep dive on an open-source repository, combining a deep-research markdown document with hands-on codebase analysis to produce a structured 12-14 document reference series. Use this skill whenever the user wants to deeply analyze a repo, do a deep dive on a project, reverse-engineer a codebase, create a technical reference for an open-source tool, understand how a project works inside and out, or compare another project's architecture against a reference project. Also trigger when the user mentions "deep dive", "deep research", "analyze this repo", "break down this codebase", "technical reference", "how does this project work", or has a deep-research markdown alongside a cloned repo ready for analysis.
-
ivy00johns Bundle Coverage LoopGrow a test suite until a coverage target is met: run coverage, find the lowest-covered meaningful unit, add REAL behavior-checking tests for it, then re-measure the whole report — looping until total (and per-target) coverage is at or above the configured target AND the full suite is green. Reads the target from .claude/profile.yaml (no hard-coded 80 or 100). Forbids gaming the number with assertion-free tests or excluding files from the coverage config — both are findings. Use when coverage is below target, when a build wave needs more tests, or as the QE coverage inner loop under an orchestrated build. Trigger on: "raise coverage", "hit the coverage target", "add tests until coverage", "get to N percent coverage", "coverage is too low", "loop until coverage passes", "grow the test suite", "cover the untested code", "/coverage-loop". A configuration of loop-controller.
-
ivy00johns Bundle Settings ConsolidatorScan every .claude/settings.local.json across the user's home directory, deduplicate permissions, collapse supersets, and merge into the global ~/.claude/settings.local.json with a categorized report. Also bootstraps permissions for autonomous/unattended sessions using a 350+ command baseline (shell operators, Claude tools, safety deny list). Trigger on "consolidate settings", "merge permissions", "stop prompting me", "bootstrap permissions", "autonomous mode", "unattended session", "overnight build setup", "I want to go to sleep and let this run", or upgrading colon-wildcards to space-wildcards across Claude Code permissions.
-
optimuslabs-io Skill API Notes Zh项目 REST API 使用说明(中文)。
-
optimuslabs-io Bundle Report GenGenerates the weekly status report.
-
optimuslabs-io Bundle Context LoaderSynchronizes startup context across Claude instances.
-
jhamidun Skill TapestryTapestry — связывает документы (транскрипты, статьи, PDF, код) в граф знаний + implementation plans. Триггеры: «свяжи документы», «граф знаний».
-
jhamidun Bundle QASystematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.
-
jhamidun Skill DOCXWord .docx на python-docx: собрать документ, править существующий, стили и нумерация, таблицы, картинки, колонтитулы, разбор чужого файла, чтение правок и комментариев через XML. Триггеры: «docx», «word», «документ Word», «сделай ворд», «tracked changes», «правки в документе». НЕ конвертация форматов → file-converter; НЕ вёрстка отчёта под клиента → kp-deck-factory.
-
jhamidun Bundle GammaГенерация презентаций, доков и страниц через Gamma Generate API + экспорт в PDF/PPTX/PNG. Триггеры: «презентация в Gamma», «gamma api».
-
jhamidun Bundle ManusАвтономная облачная задача в Manus (REST API v2, manus_helper.py): research, browsing, код. Триггеры: «запусти в Manus». НЕ слайды→manus-slides. Слэш-запуск→команда /manus.
-
jhamidun Skill Epub ToolsEPUB: чтение, поиск по главам, сборка из Markdown (ebooklib). Триггеры: «прочитай epub», «конвертируй в epub», «электронная книга», kindle.
-
jhamidun Bundle NotebooklmGoogle NotebookLM через библиотеку notebooklm-py: подкасты (2 ведущих), deep research с цитатами, квизы, флешкарты, mind maps из PDF/URL/YouTube. Триггеры: «создай подкаст», «quiz из документов», «mind map из темы», «загрузи в NotebookLM».
-
jhamidun Bundle Canvas DesignОригинальный визуальный арт в PNG/PDF: постеры, обложки, композиции. Триггеры: «сделай постер», «нарисуй обложку». НЕ сравнение макетов → design-canvas.
-
jhamidun Bundle Document ImportИзвлечь текст и картинки из PDF/DOCX/PPTX/скетча для прототипа или дека. Триггеры: «из PDF в слайды», «DOCX в лендинг». НЕ переверстать дек 1-в-1→pptx-import.
-
jhamidun Bundle PDF 2Работа с PDF: извлечение текста и таблиц, создание, merge/split, заполнение форм. Триггеры: «пдф», «вытащи текст из pdf», «заполни форму pdf».
-
jhamidun Skill QA OnlyReport-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead.
-
jhamidun Bundle PPTX 2Создание, правка и разбор .pptx файлов: layouts, спикер-ноты, комментарии. Триггеры: «поправь слайд», «заметки докладчика», «собери колоду».
-
jhamidun Bundle API DocumentationДокументация API из кода: OpenAPI/Swagger, Postman, REST/GraphQL/gRPC. Триггеры: «задокументируй API». НЕ: кодбаза→openwiki; чужие репо→deepwiki.
-
jhamidun Skill Epub Tools 2EPUB: чтение, поиск по главам, сборка из Markdown (ebooklib). Триггеры: «прочитай epub», «конвертируй в epub», «электронная книга», kindle.
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 pdf-image-text-extractor, watch, qa-deck. 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.