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.
-
frog1205 Skill Legal Report PDFProfessional PDF Report Generator
-
spacholski1225 Bundle Writing SkillsTDD for process documentation - test with subagents before writing, iterate until bulletproof
-
spacholski1225 Bundle Testing Skills With SubagentsRED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes
-
hugorcd Skill Create Evlog Framework IntegrationCreate a new evlog framework integration to add automatic wide-event logging to an HTTP framework. Use when adding middleware/plugin support for a framework (e.g., Koa, H3 standalone, Deno Fresh, etc.) to the evlog package. Covers source code, build config, package exports, tests, example app, and all documentation.
-
intelligent-internet Bundle Research To WebsiteBuild informative websites from research reports. Transforms research output (markdown or typst/pdf) into polished, domain-appropriate websites with professional design, data visualization, and scroll-based animations. Triggers on research-to-website tasks, report visualization, or when converting research into web presentations.
-
himself65 Bundle Earnings PreviewGenerate a pre-earnings briefing for any stock using Yahoo Finance data. Use this skill whenever the user wants to prepare for an upcoming earnings report, understand what analysts expect, review a company's beat/miss track record, or get a quick overview before an earnings call. Triggers include: "earnings preview for AAPL", "what to expect from TSLA earnings", "MSFT reports next week", "earnings preview", "pre-earnings analysis", "what are analysts expecting for NVDA", "earnings estimates for", "will GOOGL beat earnings", "earnings beat/miss history", "upcoming earnings", "before earnings", "earnings setup", "consensus estimates", "earnings whisper", "EPS expectations", "what's the street expecting", "earnings season preview", any mention of preparing for or previewing an earnings report, or any request to understand expectations ahead of a company's earnings date. Always use this skill when the user mentions a ticker in context of upcoming earnings, even if they don't say "preview" explicitly.
-
binhmuc Bundle Markdown Novel Viewermarkdown-novel-viewer
-
qiuy-collab Bundle AutoflowRoute artifact work through either a lightweight direct module or a managed multi-step workflow. Use direct mode for small single-module deliverables without dependencies or consequential choices; use managed task/image/Word/PowerPoint/video/package DAGs with durable state and human STOP reviews for connected or high-consequence work. Explicit autoflow invocation selects this Skill but does not force full workflow overhead.
-
qiuy-collab Bundle Presentation SkillAutoFlow's audited local presentation capability for creating, editing, and verifying editable PowerPoint PPTX files from structured source.
-
memorysaver Skill Version BumpBump version across all looplia-core package.json files, changelog, and documentation. Use when: releasing a new version, preparing a version bump PR, updating version numbers across the monorepo. Handles all 5 package.json files, CHANGELOG.md, docs/README.md, and the landing page version badge.
-
piaoxuemoli Skill Qoobee T F SkillTest & Fix skill for ImmerseAI. Supports automated testing (AT-01~AT-14), manual test report fixing (HT-01~HT-10), and CR(Code Review) report output. Trigger with: 自动化测试, 自动测试, auto test, 人工测试, manual test, 测试报告, test report, 运行测试, run tests, CR, code review, 代码审查.
Audited -
seldonframe Skill ReelierReplay recurring deterministic jobs at 0 tokens instead of re-reasoning them every run. For cron/heartbeat tool-call workflows (status checks, data pulls, report generation, CRUD sequences) — record the job once with reelier, then run "npx -y reelier run <skill>" on every heartbeat and gate drift with "reelier diff". Never for open-ended coding or file-edit work, which Reelier cannot replay.
-
azure-samples Skill Docs StandardsKeeps scenario README files and session docs aligned with the repo's documentation conventions.
Audited -
nathan5674312 Skill JanitorSweep the vault clean — delete tasks marked done + deletable after verifying their info lives in a wiki page, flag orphan pages, spot duplicate topics, and report every action. Use when the user says "clean", "janitor", "sweep", "tidy", "clean up the vault", or after a large ingest batch. Never deletes wiki pages without explicit approval.
-
nebu1eto Bundle PDF TranslatorTranslates PDF documents to any target language with layout preservation. Supports academic papers, books, manuals, and general documents. Extracts text, tables, and metadata, translates with parallel processing, and outputs both Markdown and PDF formats. Handles vertical writing (Japanese), RTL languages (Arabic, Hebrew), and academic terminology with original language annotations. Use when translating PDF files, research papers, or technical documents.
-
nebu1eto Bundle Effective WritingApply layered writing-quality guides to user-facing prose and persisted documents. Loads universal rules plus language-specific and domain-specific references as needed. Use for drafting or revising reports, documentation, tickets, messages, review comments, and presentation copy in any language.
-
notryag Skill WriterMarkdown report writing workflow for thread output artifacts.
-
notryag Skill ResearchWeb research workflow for traceable Markdown reports with artifacts.
-
notryag Skill File AnalysisAnalyze uploaded or thread-local files and produce Markdown reports.
-
ou-gc Skill Report WriterUse when writing, rewriting, translating, or polishing academic reports — English/Chinese Word (.docx) documents or presentation decks (.pptx). Encodes a working *pattern*: draft content in Markdown first for review, write English first then translate to Chinese, keep everything aligned to a single source of truth, and treat the user as a co-author whose manual edits are sacred. Trigger on tasks like "重寫 Evaluation"、"做中文版"、"整理表格"、"對齊用詞"、"找參考文獻"、 "做 PPT"、"畫架構圖"、"畫流程圖"、"畫 framework 圖".
-
paodingai Bundle Chatdoc Studio KnowledgemateCreate and operate ChatDOC Studio knowledge bases through pd_router using a Bearer API key and JavaScript helpers. Use when Codex needs to upload one or more PDF/DOC/DOCX files, skip failed files without aborting the whole job, create a knowledge base from successful uploads, or call the ChatDOC Studio knowledge-base skill endpoints through `https://platform.paodingai.com/openapi/chatdoc-studio/...`.
-
piotrlason Skill Show Help Video To Code SkillDisplays the full README.md for this plugin. Use when the user wants help, documentation, installation steps, usage examples, parameters, outputs, or troubleshooting for video-to-code-skill.
Audited -
roger-luo Bundle New RfcDraft and revise RFC markdown files for agx using project template, metadata conventions, and review gates.
-
salzaki Skill Score AI SlopUse when the user wants a slop quality-pass rather than a rewrite or a located list. Triggers include "score this for slop", "how sloppy is this", "give me a slop breakdown", "rate this writing for AI tells", "is this ready to publish", or "slop report by category". Returns a per-category breakdown (deterministic counts plus judged notes) and a publish-readiness read, deliberately without a single 0-10 headline number, because one number invites gaming. For located findings use detect-ai-slop; to rewrite the text use remove-ai-slop.
-
salzaki Skill Detect AI SlopUse when the user wants to SEE which AI tells are in a piece of text without rewriting it. Triggers include "flag the AI slop", "where are the tells", "show me what to fix", "detect AI-generated writing", "check this for slop but don't change it", "what would you flag here", or any editorial / pre-publish review that lists issues by location. This is the report lens; it returns located findings (category, severity, the offending text), never a rewrite and never a single 0-10 score. To rewrite instead, use remove-ai-slop.
-
scrollport Bundle AI Visibility ReviewProduce a defensible client report from repeated ChatGPT answers, brand mentions and cited pages, then recommend source-backed improvements. Use for AI search visibility baselines, unreliable AI reporting or understanding which sources appear for real buyer questions.
-
sepantajoshani Bundle Address Pr CommentsSafely address GitHub pull request feedback with the gh CLI. Use when asked to process review comments, especially mixed human, AI-reviewer, and automation feedback: verify the exact PR worktree and branch, collect complete paginated comments, validate each claim, apply focused fixes, run targeted checks, create one local commit per resolved comment, and report evidence without pushing or posting replies.
-
skillmedev Skill Trend EducatorTurns a raw Instagram trend-scout report into a plain-language briefing that teaches WHY each trend is working - the algorithm mechanics, audience psychology, and format dynamics behind it - and surfaces specific opportunity angles as a screenshot-ready trend card. Use when someone asks "explain these trends to me", "why is this format blowing up", "turn this trend report into a briefing", or has instagram-trend-scout output and needs to understand it before creating. Do NOT use to gather the trend data itself - use instagram-trend-scout instead; do NOT use to draft the actual post - use instagram-post-builder instead; do NOT use for statistical trend detection in business or product data - use trend-analysis instead.
-
skillmedev Skill Instagram Trend ScoutResearches what is currently working on Instagram for a niche using web search only - no API or login - and returns a structured scouting report of top content, winning Reel and carousel formats, reusable hook patterns, content gaps, and an engagement benchmark with honest confidence labels. Use when someone asks "what's trending on Instagram for my niche", "scout Reels formats for home baristas", "what hooks are working right now", or is starting a weekly content cycle and wants signals before creating. Do NOT use for explaining why trends work in plain language - use trend-educator instead; for drafting the actual post, use instagram-post-builder.
Audited -
skillmedev Skill Instagram Post BuilderInteractively builds a complete, copy-paste-ready Instagram post package - three hook variants using distinct patterns, a caption body, one clear CTA, a 15-20 hashtag set across reach tiers, alt text, and a visual direction with shot list or slide breakdown - through a one-question-at-a-time interview, optionally grounded in a trend-educator briefing. Use when someone says "write an Instagram post for my launch", "build the full post package for this reel", "put together a carousel with hooks and hashtags", or reaches the build stage after trend-educator. Do NOT use for finding what is trending - use instagram-trend-scout instead; for a single caption without the full package - use social-caption-writer; for planning a month of content - use social-content-calendar.
Audited -
syniox5334 Bundle Apple Xcode WorkflowGuide Apple and Swift development work in or around Xcode. Use when tasks involve Xcode workspace inspection, diagnostics, builds, tests, runs, toolchain checks, or Apple and Swift documentation lookup.
-
tomosia-vietnam Bundle VisionLook at what a recording actually shows, by tiling its frames into timestamped contact sheets you can read as images. Use when you need to know what happened in a video rather than take someone's word for it — checking a take you just recorded, finding where a layout breaks, locating the moment an error appeared, or answering a question about a video you cannot watch.
-
tomosia-vietnam Skill FeedbackReport a problem with webapp-evidence itself, or ask for something it cannot do yet, on its public issue tracker. Use when a recording came out wrong, a command failed, or the user says the tool should work differently. Writes nothing in the user's own repository.
-
tomosia-vietnam Bundle RecordingRecord evidence of a web app — an operation video, screenshots and a runbook — for a pull or merge request, a report, or a hand-off. Use when someone asks for proof that a change works, hands over an MR/PR link, or describes a page and the steps to capture on it.
-
voicenterteam Bundle Gossipper AnalyzeInterpret Gossipper output artifacts (summary JSON, trace CSVs, call records JSONL, OTLP events) and produce a structured findings report. Use whenever the user wants to classify failures from a Gossipper run, evaluate latency or media quality verdicts, decide whether a run passed health thresholds, propose threshold values for the next run, convert RTCP jitter from RTP timestamp units to milliseconds, surface Call-IDs and time windows for HOMER/qryn correlation, interpret exit code 2, or read a "Run report" handed over from gossipper-run.
-
iart-ai Bundle Photo SlideshowThis skill should be used when the user asks to "make a photo slideshow", "turn photos into a video", "create a photo montage video", "make a picture slideshow with music", "build a memories/recap video from photos", "add Ken Burns pan/zoom to photos", "sync slide changes to the music beat", or "render a video from a folder of images". Covers per-photo Ken Burns motion, transitions, beat-synced timing, mixed aspect-ratio handling, captions/dates, intro/outro cards, and templating a photo folder into a finished video.
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 writer, legal-report-pdf, Writing Skills. 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.