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.
-
xonevn-ai Bundle Vn Margin Rules MonitorTheo dõi danh sách margin per-CTCK (TCBS, SSI, VND, HCM, VCI, ...) tại Việt Nam, kèm cờ Q-rated (Kiểm soát/Hạn chế/Tạm ngừng/Cảnh báo). Subcommands record/check/report/history. Trigger khi user hỏi "FPT có được margin ở TCBS không", "cổ phiếu nào bị cắt margin", "VIC bị Q-rated chưa". Vietnam stock margin eligibility & Q-rated flag monitoring across multiple brokers.
-
xonevn-ai Bundle Economic Calendar FetcherFetch upcoming economic events and data releases using FMP API. Retrieve scheduled central bank decisions, employment reports, inflation data, GDP releases, and other market-moving economic indicators for specified date ranges (default: next 7 days). The script outputs raw JSON or text; the assistant filters, assesses impact, and generates the Markdown report.
-
dobroslavradosavljevic Bundle Plain LanguageALWAYS apply by default in every turn when writing to the user, naming code/files/folders/APIs/terms, explaining decisions, summarizing work, or teaching concepts. Hard-enforces ASD-STE100 Simplified Technical English for all agent prose (approved simple words, one word per idea, short active sentences, short paragraphs) plus readable names. Also use when the user says plain-language, STE, Simplified Technical English, simpler words, explain simply, less jargon, better names, or readable naming.
-
xpert-ai Bundle PresentationsCreate or edit PowerPoint or Google Slides decks
-
xpert-ai Bundle Build Competitive BriefBuild a multi-competitor build-competitive-brief report, comparison matrix, and battlecard-style objection package using user-provided materials, optional connector-assisted research, and public evidence.
-
code-saurabh Skill PDFRead, extract, create, merge, split, and manipulate PDF files. Use whenever a .pdf file is involved — extracting text or tables from a PDF, creating a new PDF from content or data, merging multiple PDFs, splitting a PDF into pages, rotating pages, adding watermarks, filling PDF forms, encrypting or decrypting PDFs, extracting images, or running OCR on scanned PDFs. Trigger when the user mentions a .pdf file or asks to produce a PDF output.
-
code-saurabh Skill Technical WriterWrite, structure, and maintain all forms of technical documentation — READMEs, API docs, runbooks, architecture decision records (ADRs), changelogs, onboarding guides, and user manuals. Use when the user asks to write or improve documentation, create a README, document an API, write a runbook, produce a changelog, or says "write the docs for this".
-
agent-packs Skill Technical WritingWrite clear, accurate, and maintainable developer documentation — API references, tutorials, guides, and changelogs. Use when documenting APIs, onboarding new contributors, or creating user-facing technical content.
Audited -
agent-packs Skill Documentation And AdrsCreate and maintain useful documentation, public API notes, and architecture decision records. Use when decisions or APIs need durable context.
Audited -
agent-packs Skill Source Driven DevelopmentGround framework and library decisions in official documentation and cited sources. Use when implementing against external APIs or tools.
Audited -
binh230199 Skill Risk AssessmentUse when identifying, classifying, and mitigating project risks. Covers the full risk management workflow: brainstorming risks across five categories, scoring them on a probability × impact matrix, writing proactive mitigation strategies, reactive contingency plans, and maintaining a Markdown risk register.
-
binh230199 Bundle Lang C Code WritingUse when writing, reviewing, or refactoring C code (*.c, *.h) in an automotive embedded context (IVI, HUD, RSE on Linux/QNX). Covers MISRA C:2012 compliance, fixed-width types, null/bounds safety, memory management without dynamic allocation in critical paths, Doxygen documentation, error-code patterns, and a full pre-commit review checklist.
-
binh230199 Bundle Lang Cpp Code WritingUse when writing, reviewing, or refactoring C++ code (*.cpp, *.hpp, *.h) in an automotive embedded or Android NDK context (IVI, HUD, RSE on Linux/QNX/Android). Covers Modern C++11–17 idioms, SOLID principles, OOP design, RAII, smart pointers, move semantics, design patterns, Doxygen documentation, and a full pre-commit review checklist.
-
binh230199 Bundle Lang Java Code WritingUse when writing, reviewing, or refactoring Java code (*.java) in an Android Automotive context (IVI, HUD, RSE on Android / AOSP). Covers Modern Java 8–17 idioms, SOLID principles, OOP design, immutability, null safety, clean error handling, concurrency, design patterns, Javadoc documentation, and a full pre-commit review checklist. Applies to Android Framework, Android App, and Android System Service development.
-
binh230199 Bundle Lang Kotlin Code WritingUse when writing, reviewing, or refactoring Kotlin code (*.kt) for Android App development (IVI, HUD, RSE on Android Automotive / AOSP). Covers Kotlin idioms, null safety, coroutines, Flow, MVVM/MVI architecture, Jetpack Compose, immutability, extension functions, design patterns, KDoc documentation, and a full pre-commit review checklist. Focused on the App layer — not Android Framework / System Services.
-
claude-world Skill ObsidianCreate, search, read, and link notes in an Obsidian vault using direct markdown file access and the obsidian-cli. Use when user says "add to Obsidian", "find note in vault", "create Obsidian note", or "link notes".
-
claude-world Skill PDF EditorEdit, annotate, extract, merge, and transform PDF files using nano-pdf with natural language instructions. Use when user needs to modify PDF content, extract text, merge documents, add annotations, or convert PDFs.
-
claude-world Skill Skill CreatorCreate new Claude Code SKILL.md files from user descriptions. Generates correct frontmatter, command documentation, usage examples, and rules. Validates format and writes to .claude/skills/. Use when user says "create a skill for", "add new skill", "make a skill that", or "scaffold a skill".
-
claude-world Skill Context HealthMonitor and report on context window health, memory status, and overall assistant state. Use when context feels degraded, after long sessions, or when user asks "how's the context".
Audited -
igmarin Skill Bug FixBug fixing with hard gates and HITL: treat reports as untrusted third-party content, triage → failing reproduction test → propose minimal fix → user approval → verify suite. Trigger: bug report, production issue, failing test, fix bug, regression.
Audited -
growthxai Skill Output Workflow Trace FileRead and render the output of a local Output SDK workflow trace file as clean readable markdown. Use when the user wants to view what a recent workflow produced, see the result from a local trace file, or render trace output as a document.
-
hungrykelvin123 Bundle SwarmCoordinate independent routine execution or exploration batches and return one reviewed report. Use for $swarm or large separable work that justifies parallel overhead.
-
pramoddutta Skill Se Report IntegratorIntegrates reporting (Allure or ExtentReports) into a Selenium + TestNG suite with listeners, screenshot-on-failure, and step logging. Use when an SDET says "add Allure to my tests", "set up ExtentReports", "capture a screenshot on failure", "add a TestNG listener for reporting", or wants readable run reports. Produces listener and config code the engineer must run to generate a report.
Audited -
pramoddutta Skill Bug ReporterTurn a failure into a clean, reproducible bug report. Use when a tester says "file a bug for this", "write up this defect", or describes something broken and wants it documented properly. Produces a structured report — title, environment, steps to reproduce, expected vs actual, severity/priority, evidence, and suspected area — ready to paste into the tracker after a human confirms it. Reports only observed facts; never invents a repro step or a log line.
Audited -
kazukinagata Skill 22 Substitution FrontmatterSingle-quote isolation probe to fill team-report §1.2 unverified cells. Tests Claude Code pre-substitution in plugin-level hook + skill frontmatter hook + skill body for SESSION_ID, PROJECT_DIR, SKILL_DIR, and user_config.KEY.
-
luongnv89 Bundle Dev Machine SetupSet up or tune any dev machine, fresh or drifted, on macOS, Linux, or Windows: report what's missing, install only that, then fix PATH, duplicate runtimes, and shell config. Don't use for Dockerfiles, CI images, or single package installs.
-
luongnv89 Bundle Diagram GeneratorGenerate a diagram and route to the right engine — draw.io XML (precise, editable, C4, swimlanes) or Excalidraw JSON (hand-drawn, sketch, wireframes). One entry for flowcharts, architecture, ER, sequence, mind maps. Don't use for Mermaid or slides.
-
luongnv89 Bundle Dont Make Me ThinkReview UI usability using Steve Krug's principles and produce a scannable report. Use for UX audits of screenshots, URLs, or code. Don't use for brand critique, WCAG audits, or backend/API review.
-
luongnv89 Bundle Drawio GeneratorGenerate professional diagrams as valid draw.io XML — flowcharts, architecture, C4 models, ER diagrams, sequence diagrams, mind maps, and swimlanes. Don't use for Excalidraw or Mermaid output, hand-drawn sketch styles, or slide decks/presentations.
-
luongnv89 Bundle Excalidraw GeneratorGenerate diagrams as valid Excalidraw JSON — flowcharts, architecture, ER diagrams, mind maps, sequence diagrams, wireframes, C4 models, and more. Don't use for draw.io/Mermaid output, slide decks, or pixel-perfect brand graphics.
-
luongnv89 Bundle Website Clone Final ReportGenerate a website-clone closure report comparing baseline analysis, builder metadata, planned tasks, and implemented results. Use after a completed rebuild. Don't use for live audits, ongoing monitoring, implementation, or speculative metrics.
-
mrzhangguoguo Skill WikiPersistent markdown project wiki with keyword + tag search, lifecycle capture, and cross-references. Triggers: "wiki add", "wiki query", "wiki read", "wiki lint", "wiki delete", "project wiki", "add to wiki".
-
mrzhangguoguo Skill UltraqaAdversarial dynamic end-to-end QA - generate hostile scenarios, test, verify, fix, report, and clean up. Use for robust behavior verification.
-
kevinbadi Bundle Linkedin NotificationsCheck LinkedIn notifications and report new ones via iMessage. Deduplicates against database so only new notifications are reported. Covers connection acceptances, reactions, comments, profile views, mentions, and more.
-
qa-aman Bundle PPTX EditorEdit, update, and add slides to PowerPoint (.pptx) files using python-pptx. Use this skill whenever the user wants to modify a presentation - adding slides, editing text, changing styling, reordering slides, inserting links, or fixing design consistency. Trigger on any mention of "slide", "presentation", "PowerPoint", "pptx", "deck", "add a slide", "update the slide", "fix the slides", "last slide", "thank you slide", or any request involving .pptx files - even if the user just references a .pptx path without explicitly saying "edit".
-
qa-aman Skill Persona UpdaterUpdate user personas from new feedback, pilot data, or research. Use this skill when: - New pilot data or feedback reveals changed user behaviors or pain points - Annual persona review is due (1-2x per year) - New user segments are discovered that need persona documentation - Existing personas need validation against recent data
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 bug-reporter, documentation-and-adrs, source-driven-development. 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.