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.
-
rarango10 Bundle Verify E2eVerifica una feature ya implementada de punta a punta, en dos fases: escribe e2e-tests-plan.md con 3 casos (1 happy path y 2 de fallo) a partir del spec aprobado, y después orquesta la generación de los tests de Playwright y su corrida, hasta un e2e-test-report.md que rutea cada fallo. Usalo cuando la persona diga 'verifiquemos e2e', 'probemos de punta a punta', 'armemos los tests end to end', 'corramos el e2e', o cuando todas las tareas de un tasks.md ya estén en hecho y falte comprobar que la feature completa funciona. Es el paso siguiente a la verificación por tarea de dod-checker: dod-checker verifica una tarea contra sus criterios, este skill verifica la feature entera contra el spec. No escribe los tests ni el reporte por su cuenta — eso lo hacen los subagentes e2e-test-writer y e2e-triager.
-
librefang Skill Technical WriterTechnical writing expert for API docs, READMEs, ADRs, and developer documentation
-
librefang Bundle Word CounterCount words, sentences, and characters in text.
-
dhinc1 Bundle Drawings AnalyserTurn a construction drawing set (PDF or folder of PDFs) into a queryable structured database plus per-sheet markdowns, a symbol library, a cross-reference graph, and a concept wiki of the notes/specs. Builds the building's components as instances with coordinates (IFC-style), tags every fact with a reliability score, validates its own sources, and flags conflicts/RFIs. Then answers questions by querying the database (counts, locations, relationships) and the source PDFs on demand (areas, schedules, dimensions) — far cheaper than re-reading the PDF each time. Trigger when drawings are shared and the user says "analyse/review these drawings", "break down this drawing set", "build a database from these drawings", "extract the symbols", "find coordination issues", "how many X", "where are the X", or asks Claude to understand, query, or get across a drawing set. Not for full-set takeoffs (use construction-takeoff) or project onboarding (use project-indexer).
-
dhinc1 Bundle Land Plan EstimatorRead, index, measure, and estimate from land-development / civil site plan sets delivered as PDFs (subdivision layouts, grading & drainage, utility plans, road plan-and-profile, erosion control, landscape/buffer plans, construction details, boundary/survey). Use this ANY time the user uploads or points to a plan set, drawing set, "the civils", a sheet index, or a large multi-sheet PDF and wants to query it, summarize sheets, pull quantities (lot counts, disturbed acreage, cut/fill, pipe sizes, pavement areas, curb LF, buffer LF, setbacks), prepare a land-development budget takeoff, or find which sheet a given detail lives on. Trigger even if the user just says "read these plans" or "what does sheet C-3 say" — do NOT try to stuff the raw PDF into context, use this preprocessing-and-index workflow instead.
-
mike22890 Bundle PPTXPowerPoint 演示文稿的创建与编辑。当需要制作 PPT、幻灯片、演示文稿、Pitch deck、汇报材料、培训课件、keynote、演讲辅助、动态演示、PPT 模板设计、图表可视化、演示动画、导出 PDF/图片时使用。
-
prompthon-io Bundle Garbage CollectorScan local cleanup targets, apply readable cleanup rules, produce a preview report, and execute approved cleanup actions with logs. Use when a user asks Codex to clean up their computer, empty old Trash items, find duplicated Downloads files, review local storage clutter, or propose safe file cleanup actions before making changes.
-
prompthon-io Bundle Daily News WatcherPersistent daily news monitoring backed by local SQLite and Markdown reports. Use when a user asks Codex to track named publications, fetch the last N hours of news, summarize recent articles by topic, deduplicate articles across runs, or maintain a personal newsroom that survives across sessions.
-
prompthon-io Bundle Personal Knowledge CaptureCapture and synthesize local or explicitly provided web sources into cited Markdown notes. Use to register a research folder, summarize new or modified Markdown/TXT/PDF/DOCX files, deduplicate sources, surface conflicting claims, capture a provided URL or persist course knowledge notes with provenance. Do not use to move or organize files or schedule workflows.
-
prompthon-io Bundle Presentation Template DesignerPlan reusable presentation templates from a creative brief, optional brand assets, or an existing deck. Use when Codex needs to define a slide inventory, choose an editable presentation toolchain, author or validate a template manifest, adapt a visual system for PowerPoint or Google Slides, or prepare a reviewed template plan before generating a deck.
-
hideki5123 Bundle Gdrive CLIOperate Google Drive from the terminal via `rclone` — list, upload, download, search, sync, mount, check quota, export Google Docs/Sheets/Slides, browse Shared Drives, and manage trash. Use whenever the user mentions Google Drive, Drive folders, or anything stored in Google Workspace files from the command line. Trigger phrases include "google drive", "g drive", "gdrive", "drive cli", "upload to drive", "download from drive", "list drive", "search drive", "sync to drive", "backup to drive", "mount google drive", "mount drive", "check drive quota", "drive storage", "drive space", "google docs export", "shared drive", "shared with me", "drive trash", "empty drive trash", "google workspace files", "drive folder", "rclone drive", "rclone gdrive".
-
chendeninghan-pixel Bundle Illustrator Jsx用 ExtendScript (.jsx) 脚本自动化 Adobe Illustrator:新建画板、绘制图形/文字/虚线、打组、批量排版、批量替换文字、导出 PNG/PDF/SVG。This skill should be used when 用户需要在 Illustrator(设计行业黑话"AI",注意与人工智能区分)里自动排版、批量绘制或修改元素、写/改/运行 .jsx 或 ExtendScript 脚本、批量改字换字体,或要求"操控/驱动/自动化 Illustrator"、把画板导出为图片或 PDF,以及批量生成展板、导览图、桌游卡牌、展览物料等 Illustrator 原生排版任务。
-
hideki5123 Bundle PostmortemGenerate a blameless postmortem (incident report) from a Slack incident thread and publish it to Confluence. Fans out to subagents that collect evidence from Slack, GitHub, and Jira, merges their compact evidence cards into a sourced timeline with TTD/TTM/TTR, drafts the report (Overview, Impact, Root Cause & Contributing Factors, Timeline, Lessons, Action Items), independently fact-checks every factual claim against the original sources, then publishes to Confluence and optionally files action-item Jira tickets. Raw Slack messages, diffs, and logs never enter the main session — only the cards. Use when the user asks to write a postmortem, an incident report, a retrospective for an outage, or to turn an incident thread into a document. Trigger phrases include "postmortem", "ポストモーテム", "incident report", "障害報告", "障害レポート", "インシデントレポート", "障害の振り返り", "write a postmortem", "postmortem from slack", "incident writeup", "outage report", "RCA", "root cause analysis", "/postmortem".
-
hideki5123 Bundle Review LocalReview local git changes from 8 expert perspectives by spawning the matching reviewer subagents in parallel. Produces a consolidated report with Critical/Important/Nice-to-have severity. Lightweight pre-commit or pre-push quality gate — no PR or branch push required. Use when the user asks to review local changes, check changes before committing, get a team review of working tree changes, or run a pre-commit review. Trigger phrases include "review local", "review my changes", "review local changes", "pre-commit review", "review before commit", "review before push", "team review my changes", "check my changes", "review working tree", "local code review", "review diff", "review my diff".
-
hideki5123 Skill Session RecapRead a Claude Code session's transcript and produce two markdown artifacts plus a meta.json: a scannable Summary (TL;DR, key terms, files, decisions, open threads) and a complementary Detailed Note (full glossary, chronological flow, command-by-command annotations, pitfalls). The output language follows the watched session's dominant language (>= 50% Japanese characters → Japanese, otherwise English; overridable via --language). Standalone — pass a session ID, or omit to pick from recent sessions in the current directory. After generation, dispatches a configurable chain of follow-up skills (default ["recap-to-notion"]) read from ~/.claude/session-recaps/.recap-config.json. Owns the manifest schema and runs cleanup of confirmed-uploaded local recap dirs past retention. Read-only on the transcript itself. Use when the user says "session recap" / "セッションのまとめ" / "セッションサマリ" / "学びをまとめて" / "用語集を作って" / "summarize the session" / "recap session" / "session note" / "セッションのノート" / "/session-recap" / "セッション解説まとめ" / "recap掃
-
hideki5123 Bundle Test ScenarioGenerate test outlines (living documentation) and test code from natural language feature descriptions. Supports .NET (xUnit/NUnit/MSTest), Python (pytest), TypeScript (Vitest/Jest). Strict mode: no internal module mocking, real DB, AAA pattern, Design by Contract (DbC). Use when the user asks to generate tests from a feature description, create test cases from requirements, write test outlines, scaffold test files, generate test code from spec, convert TODO tests to real tests, or create tests for a function. Trigger phrases include "test scenario", "テストシナリオ", "generate tests", "テスト生成", "テストケース作成", "write tests for", "scaffold tests", "tests from requirements", "テストアウトライン", "convert todo tests", "implement test outline", "test outline", "test cases from spec".
-
vadrisai Skill Word CounterCounts words, characters, and sentences in a block of text the user provides.
-
hideki5123 Bundle Playwright CLIRun Playwright CLI commands via Bash for test execution, code generation, browser management, reporting, and debugging. Covers the full `npx playwright` surface: test, codegen, install, show-report, show-trace, screenshot, pdf, open, clear-cache, merge-reports, and more. Use when the user asks to run playwright tests, generate test code, install browsers, view a test report or trace, take a page screenshot or PDF, open a URL in a specific browser, clear the playwright cache, merge shard reports, debug tests, or use playwright UI mode. Also covers the guided workflow for turning a codegen recording into a structured test suite with assertions, resilient selectors, and page objects. Trigger phrases include "playwright test", "run playwright", "npx playwright", "codegen", "install browsers", "show report", "show trace", "playwright screenshot", "playwright pdf", "open in chromium", "open in firefox", "open in webkit", "clear playwright cache", "merge reports", "shard tests", "playwright debug", "playwright ui mo
-
vadrisai Skill Expense FilingFiles an expense report end to end — extract receipt data, validate it, submit it, and confirm the submission.
-
jakeschincariol Skill Ig CarouselBuild an Instagram carousel - the cover that earns the swipe, slide-by-slide copy, and the 1080x1350 files to upload. Use when the user says "carousel", "slides", "swipe post", "turn this into a carousel", or has a list-shaped or step-shaped idea that would die as a single image.
-
archplg Skill Period Close ReportUse when the user asks to assemble a periodic report from several systems and to prove it is complete: закрытие месяца, сводка за неделю, отчёт по подразделению из нескольких выгрузок. Says: собери отчёт за период, проверь полноту данных, сведи выгрузки. Do not use to publish or send the report: the skill assembles and checks it.
-
shzshzshz123 Bundle Make Knowledge CardsThis skill should be used when the user wants to turn a pasted article or a local Markdown/TXT file into a compact set of standalone knowledge cards for learning or review. Trigger it on requests such as "把这篇文章做成知识卡片", "把这段内容整理成知识卡片", "帮我把这个 md 文件切成知识点", "整理成闪卡", "提炼要点做成读书笔记", "make knowledge cards from this article", "turn this article into flashcards", or whenever a .md/.txt document is provided and the user asks to extract key knowledge, build study cards, or generate self-test questions.
-
laabidi-ahmed-ai Bundle Anki CardsTurns a topic, a concept, or an existing study PDF into spaced-repetition flashcards and writes a one-click Anki-importable deck to ./output/<deck-slug>.txt. ONLY trigger on explicit invocation by name — e.g. "anki cards: <topic>", "use anki cards", or "/anki-cards <topic>". Do NOT activate for general questions: if the user hasn't named this skill, do not use it.
-
farzammohammadi Bundle Literary EditorTransform drafts into polished English. Use when refining any written content—notes, messages, articles, documentation.
-
farzammohammadi Bundle Repo Docs OverhaulOverhaul a repository's documentation layer for clarity and navigability. Rewrites root README, creates section READMEs, renames vague files, adds contributor guides, and codifies documentation conventions. Use when a repo needs to be made OSS-ready or its docs feel generic/sparse.
-
farzammohammadi Bundle Modularize DocumentTransform monolithic markdown into modular index + detail files. Use when user wants to split large documents or mentions modularizing.
-
framecoreworks Bundle Caption StudioUse this skill to plan, normalize, style, review, or repair captions and subtitles for Reels, TikTok, Shorts, ads, explainers, and other videos using provided transcripts, subtitle files, word timing, or available local tools.
-
laabidi-ahmed-ai Bundle PDF Mlops ExplainingExplains ANY MLOps-engineer-path subject (a tool, concept, stage, or comparison) at calibrated depth — full treatment for core topics, one or two sentences for peripheral ones — and renders it as a downloadable PDF saved to ./output/<subject-slug>.pdf so the user builds a personal reference library. ONLY trigger on explicit invocation by name — e.g. "pdf mlops explaining: X", "use pdf mlops explaining", or "/pdf-mlops-explaining X". Do NOT activate for general questions on these topics: if the user hasn't named this skill, do not use it.
-
viderstar Bundle Experiment ArticleWrite up an ML experiment from the notebook and the run log, in a skeleton that keeps the failures: verdict in the title, protocol as a table, ranking and business metrics side by side, "What was not verified", and a Reproduction section. Use when asked to "write up the experiment", "document the results", "describe what came out of the notebook", "summarise the run", "prepare the report on this experiment". Not for READMEs and not for code documentation.
-
framecoreworks Bundle Delivery DocumentationUse this skill to package final files, QA status, source lists, usage notes, caveats, excluded files, and delivery manifests.
-
xxjrq Bundle Novel To Drama将小说片段、章节或梗概改成可排练的中文短剧剧本,同时输出 Markdown 与 JSON,包含场次、人物动作、对白、冲突升级和结尾钩子。适用于短剧策划、试写和分集拆解;保留原作事实,不承诺爆款、过审或收益。
-
jtaroreh Bundle SwarmFan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
-
xxjrq Bundle Novel Review Score对中文小说、梗概或章节做六维审稿评分,逐项给出原文证据、问题影响和可执行修改建议,并输出 Markdown 与 JSON。适用于编辑初筛、自检、横向比较和改稿复盘;评分是辅助意见,不代表签约、过审或市场结果。
-
chenzhiya77 Bundle Ardot SlidesUse this skill for Ardot canvas design tasks whose deliverable is a slide deck / presentation design (NOT a PowerPoint .pptx file). Covers presentations, decks, pitch decks, keynote-style slides, launch-event slides, roadshow decks, proposal/pitch slides rendered as Ardot design canvases. Trigger phrases: design a presentation, create a deck, generate slides, design slides, create a pitch deck, design a keynote, slide deck mockup, presentation mockup, pitch deck design, 幻灯片设计稿, 演示文稿设计, 发布会幻灯片, 路演 PPT 设计稿, keynote 设计, 提案稿, 宣讲稿, 制作 PPT, 做一份幻灯片. Pairs with ardot-design-core (load it alongside). IMPORTANT boundary: this skill OWNS slide/deck/幻灯片 requests whose output is a DESIGN (Ardot canvas, 设计稿, mockup). Defer to the pptx skill ONLY when the user explicitly requires a PowerPoint .pptx file (导出 pptx / 生成 PPT 文件 / references an existing .pptx). Words like 'slides', '幻灯片', 'PPT' alone do NOT trigger pptx.
-
farzammohammadi Bundle GwsUnified interface for Google Workspace via the gws CLI. Send Gmail, create/read/append Google Docs and Sheets, upload and share Google Drive files, and convert markdown to formatted Docs. Use when the user mentions Gmail, Google Docs, Google Sheets, Google Drive, or Google Workspace tasks.
-
aaryan1524 Skill Image PolishImproves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
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 verify-e2e, technical-writer, word-counter. 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.