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.
-
officialboomi Bundle Boomi IntegrationDevelops and deploys Boomi integrations, APIs, and platform services including Event Streams, Flow Services, and web service endpoints. Use when building, modifying, or deploying Boomi components (processes, profiles, connections, operations, maps, API components, EDI, Flow Services). Handles bi-directional sync, deployment automation, testing, and provides comprehensive Boomi reference documentation for complete solution development.
-
samber Bundle Devrel Competitor AnalysisBenchmarks a competitor's developer relations motion from publicly observable signals - documentation and quickstart quality, open-source repository health, community size and responsiveness, Q&A tag activity, content cadence by format, event presence, hiring signals - and returns a gap plan with a close, ignore or counter verdict per row. Use whenever the user asks for a devrel competitive benchmark, a developer experience comparison, "how do we compare to <competitor> for developers", "what is <competitor> doing in devrel", a community size or content cadence comparison, or a docs comparison against rivals - even if they only say "why do they get more developers". Not for measuring your own program alone - use samber/developer-relations-skills@devrel-metrics.
-
samber Bundle Developer Relations KickoffBefore starting any developer-relations work - and again at the start of each new session on an existing DevRel project - routes the current task to the right skill of the samber/developer-relations-skills collection, or says plainly that none fits, then bootstraps or resumes the project's shared devrel-context.md artifact. Covers documentation, open source, community, events, technical content, program strategy, devtools business strategy, employer brand and measurement; the output is a routing short-list plus an ordered skill chain. Run it at every project start even when the collection's skills are already in daily use elsewhere, at each periodic DevRel check-in, and whenever routing is unclear - a devrel kickoff, a new developer-relations project, "which devrel skill do I need", devrel, docs or open-source skill routing, or a recurring developer-program review - even if the user only describes a devrel problem and never asks which skill to use.
-
samber Bundle Developer Community ModerationWrites a developer community's code of conduct and the moderation playbook behind it - scope, enforcement ladder, reporting channels, incident-response runbook, moderator roster, platform controls. Use whenever the user mentions a code of conduct, CODE_OF_CONDUCT.md, community moderation, moderator recruitment, an escalation ladder, banning or suspending a member, harassment, trolls, brigading, spam or AI-slop floods, or a conduct report they need to handle - including vaguer phrasings like "our Discord is getting out of hand", "we need community rules", or "someone reported a maintainer". Covers company-run and volunteer open-source communities. Do NOT use to pick the platform - use samber/developer-relations-skills@developer-community-launch.
-
abdulrahman-abdulkarem Bundle AgyUse the Antigravity CLI (agy) to execute live online web searches, deep technical research, and quick delegated subtasks. Activate whenever you need real-time internet search, up-to-date web documentation, package/release info, error diagnostics from GitHub issues, external technical research, or fast secondary task execution.
-
alexoberneyer Skill Proofread PostProofread a blog post or piece of writing before publication and report findings as a numbered diagnosis, without editing the file. Use when the user says "proofread this post", "review this draft", "check this before I publish", or "/proofread-post". Takes a path to a markdown file.
-
macfarlanem-cloud Skill Inclusive ExamplesUse whenever course materials, case studies, word problems, scenarios, discussion prompts, quiz items, or sample data include people, families, businesses, or communities. Trigger before inventing any named character or example population for learner-facing content, and when reviewing existing materials for stereotyping. Ensures people are described by role, place, and circumstance; that names and ethnicity are never paired with occupations or situations in stereotyped ways; that foods, businesses, or dress are not used as shorthand for a culture; and that learners can see themselves and others with dignity. Do not use for direct quotations or documented real cases, which stay as the source has them.
-
macfarlanem-cloud Skill Accessible LanguageUse professional but accessible word choices in any material Michelle will share with faculty, staff, students, or community partners (documents, slides, infographics, emails, headings, labels, captions). Trigger this whenever producing Sierra College or RSI-project text that other people will read, especially faculty-facing and CommUnity-facing content. The goal is clear, warm, plain language that respects the reader and never reads as academic-elitist or jargon-heavy. Do not apply to direct quotations, legal or regulatory names, tribal nation names, or established proper nouns, which stay exact.
-
macfarlanem-cloud Skill Sierra Faculty BrandApply Sierra College's black, gray, and cardinal visual theme to any faculty-facing materials. Use this skill whenever you are creating, styling, or recoloring content that Sierra College faculty will see, including Word documents, PowerPoint or slide decks, handouts, one-pagers, guides, training materials, RSI review and mentor materials, norming tools, rubric explainers, and any presentation or document tied to the college. Trigger this even when the user does not name the colors explicitly, as long as the deliverable is Sierra College faculty-facing content. Do not use for student-facing course content unless the user asks, and do not use for non-Sierra work.
-
samber Bundle Tech Talk OutlineTurns an accepted conference talk abstract into a rehearsable outline - the one-sentence takeaway, a narrative arc, a minute-by-minute time budget, demo placement, and a slide skeleton with cut checkpoints. Use whenever someone says "talk outline", "technical talk structure", "slide skeleton", "my talk got accepted, now what", "how do I structure this conference talk", "my talk runs over time", "what do I cut from my talk", or "where should the demo go" - even if they only say they are preparing a conference session. Structures what the talk says. Not the CFP abstract - use samber/developer-relations-skills@conference-cfp-submission. Not slide files, not stage-delivery coaching.
-
seryozh Bundle Own The OutcomeTake responsibility for the user's real-world result instead of producing a plausible answer. Clarify the real outcome, choose rigor in proportion to risk, verify on the surface the user will judge, attack the final result, and report what remains unproven. Use for consequential or multi-step research, documents, data, plans, campaigns, builds, audits, or migrations; whenever the result must survive criticism; and whenever the user asks for thoroughness in words such as "use own the outcome", "отвечай за результат", "сделай досконально", "тщательно", "дотошно", "разберись как следует", "make sure it is actually right", or "be thorough". This skill owns the definition and final evidence of done. It does not design durable departments or route a colored role team. Scale rigor to stakes; do not add ceremony to small routine chores.
-
schnitzlermandy85-beep Bundle Course Grounded TutorDiagnosis-first tutoring for university STEM, science, math, programming, algorithms, AI/ML, systems, physics, signals, engineering, exam prep, homework understanding, concepts, proofs, derivations, debugging, optional practice, answer checking, and mastery checks. Use with PPTX, DOCX, PDF, screenshots, or course-material folders for source-grounded point-by-point teaching and discussion. Use with Markdown notes for correction, supplementation, restructuring, or refinement from course evidence and the current conversation. Supports /tutor, /diagnose-gap, /study-plan, /exam-track, /state-card, /resource-scan, /visualize, /mistake-review, /learn-anything, and /practice. Diagnose the subject, prerequisites, and likely knowledge gaps before teaching; do not act as an answer-first bot.
-
kepes Bundle Session Cost ReportSession token & cost report
-
tiangong-ai Bundle Tiangong Auto Research 2Orchestrate open-ended, multi-source, evidence-backed research in the current native Codex, Claude Code, WorkBuddy, or CodeBuddy host, especially when an ancestor directory contains `.tiangong-research` or the user asks to research, investigate, build on prior outputs, compare evidence, form a conclusion, or produce a reviewed research artifact. Also use for setup, preflight, native producer execution, recovery, independent review, closure, and requests to report Auto Research bugs or suggest capabilities (反馈问题、提交 Issue). In an Auto Research workspace this Skill takes precedence over individual web, news, SCI, report, patent, download, or document Skills unless the user explicitly requests one isolated standalone operation outside the research workflow. Covers Chinese requests such as “研究一下”, “朝这个方向做一做”, “结合已有成果继续研究”, “查资料并形成结论”, and “系统梳理证据”.
-
tiangong-ai Bundle Tiangong Kb Report Search 2Perform one isolated owner-requested Tiangong report search outside Auto Research, or provide report-source method guidance for a separately reviewed locked broker capability. Searches only `report`. If an ancestor contains `.tiangong-research` and the request is open-ended, multi-source, analytical, builds on prior outputs, or produces a conclusion/artifact, route to `tiangong-auto-research` and do not execute this standalone wrapper. Inside a managed workspace, standalone use requires the user's explicit isolated-query request and `execution_mode=standalone`.
-
curiositech Bundle Skill Documentarian 2Documentation expert for Claude Skills showcase website. Maintains skill-to-website sync, manages tag taxonomy and badges, creates blog-style artifacts, and preserves multi-skill collaborations for posterity. Activate on 'document', 'sync skills', 'create artifact', 'validate skills', 'add tags', 'tag management', 'badge', 'metadata'. NOT for code implementation (use domain skills), design creation (use web-design-expert), testing (use test-automator), or project planning (use orchestrator).
10 -
curiositech Bundle Digital Estate Planner 2Organizing digital life for legacy, emergency access, and death preparedness. Specializes in password management, account documentation, digital asset preservation, and ensuring loved ones can access what they need.
10 -
rsmdt Bundle Technical Writing 2Create architectural decision records (ADRs), system documentation, API documentation, and operational runbooks. Use when capturing design decisions, documenting system architecture, creating API references, or writing operational procedures.
-
rsmdt Bundle Feature Prioritization 2RICE, MoSCoW, Kano, and value-effort prioritization frameworks with scoring methodologies and decision documentation. Use when prioritizing features, evaluating competing initiatives, creating roadmaps, or making build vs defer decisions.
-
creekmoon Skill Creekmoon Strategic Decision Report技术战略决策报告写作与核查标准——仅在一个场景触发:技术方向和方案已定、尚未落地,需要向领导/上级做书面汇报,讲清"要怎么实施、考虑过哪些取舍、最终怎么决策",让懂技术但不了解本仓库细节的领导知晓并认可。本质是一场写给领导看的技术分享,不是请领导拍板,不是和实现者讨论怎么做,更不是 TRD/技术方案/ADR 本身。写后派独立子代理以读者视角核查再修订;理解与表达意图永远优先于模板,章节可按实际情况增删。仅当用户要"给领导/上级汇报技术决策""写决策汇报材料""把已定方案提炼成给领导看的报告",或评审/改写这类汇报材料时使用;写 TRD、做方案论证或选型讨论、写代码设计文档、写周报等场景,一律不用本 skill。
-
maweis1981 Bundle Resume Screening从本机 macOS Mail 里导出某个岗位的应聘邮件(BOSS直聘等转发的简历附件),逐份阅读并按 A/B/C 档评估,提取联系方式,生成可直接发给 HR 的 PDF 评估报告(附原始简历)。当用户说"看一下邮箱里应聘 XX 的简历""筛选简历""整理简历给 HR""简历评估报告"时使用。
-
dasdigitalemomentum Bundle Update DocsUpdate existing project documentation after code changes. Detects outdated sections, updates module and feature docs, and ensures cross-references remain valid. Use this skill after implementing features, refactoring, or when documentation is known to be stale.
-
easyindie Skill Lark Doc飞书云文档(v2):创建和编辑飞书文档。使用本 skill 时,docs +create、docs +fetch、docs +update 必须携带 --api-version v2;默认使用 DocxXML 格式(也支持 Markdown)。创建文档、获取文档内容(支持 simple/with-ids/full 三种导出详细度,以及 full/outline/range/keyword/section 五种局部读取模式,可按目录、block id 区间、关键词或标题自动成节只拉部分内容以节省上下文)、更新文档(八种指令:str_replace/block_insert_after/block_copy_insert_after/block_replace/block_delete/block_move_after/overwrite/append)、上传和下载文档中的图片和文件、搜索云空间文档。当用户需要创建或编辑飞书文档、读取文档内容、在文档中插入图片、搜索云空间文档时使用;如果用户是想按名称或关键词先定位电子表格、报表等云空间对象,也优先使用本 skill 的 docs +search 做资源发现。
-
dasdigitalemomentum Bundle Generate DocsGenerate project documentation from an existing codebase. This documentation shall serve Agents and Humans. Creates a project overview, module documentation, and feature documentation with explicit inventories (files/dirs + symbols) for each module. Use this skill when onboarding a new project or creating initial documentation for an undocumented codebase.
-
dasdigitalemomentum Bundle Archive Legacy DocsNormalize legacy repositories by moving scattered documentation into docs-legacy/ (git-aware) and generating a docs-legacy/summary.md before generating new docs/plans.
-
dasdigitalemomentum Skill Ops OrchestratorOrchestrator for structured planning, documentation, and gated implementation using docs/ and plans/. Use when planning features, documenting codebases, executing plan phases, or resuming multi-session work.
-
julianvignoles-art Bundle Ask The CouncilRun a decision through a fixed panel of six perspectives built to disagree with each other, then synthesize into one clear recommendation. Use this whenever the user is trying to decide something — big or small, personal or professional — and wants a second opinion, a sanity check, or help weighing options, or seems stuck at a fork in the road. Trigger on "should I", "what should I do about", "help me decide", "am I making the right call", "talk me through this", "is this a good idea", or any message weighing two or more options, even without the word "decision." Trigger hardest on irreversible or high-stakes choices (quitting a job, ending a relationship, a large purchase, a migration with no rollback) — but don't reserve this for big decisions only; a stuck, reversible choice still benefits from quick mode (see below). Say "quick council" or "fast take" for the three-seat abbreviated version instead of the full panel.
-
usamikinoko Bundle Oi My WordsRewrite a Chinese article draft provided by the user to strip its AI flavor, so it reads like natural human writing, while preserving the original content, structure, and meaning: only the wording and narrative style change, never the article's structure. Overall style: rigorous and professional. Prose in paragraphs rather than lists, technical terms annotated as "English(中文)", with occasional light Classical-Chinese transitional phrases. The rules cover five layers: sentence and grammar, paragraph and article structure, Markdown syntax, narrative style and wording, content quality. Invocation is explicit only: activate only when the request names this skill — the literal name oi-my-words — in a Chinese or an English request. A request that describes the goal without naming the skill must not trigger it, in either language. This skill only rewrites existing text; to create a new article, use oi-my-words-create instead. 中文请求同样触发,例如"请遵循 oi-my-words 规则为我改写这段文字"; 只说"去 AI 味""改写""润色"而不点名技能时,不得触发。
-
usamikinoko Bundle Oi My Words CreateWrite Chinese Markdown blog articles that follow natural everyday narrative habits, based on a topic or outline the user provides. Overall style: rigorous and professional. Prose in paragraphs rather than lists, technical terms annotated as "English(中文)", headings as declarative level-2 and level-3 headings, with occasional light Classical-Chinese transitional phrases. Plan the article's structure and section divisions before writing. The rules cover five layers: sentence and grammar, paragraph and article structure, Markdown syntax, narrative style and wording, content quality. Invocation is explicit only: activate only when the request names this skill — the literal name oi-my-words-create — in a Chinese or an English request. A request that describes the goal without naming the skill must not trigger it, in either language. This skill only creates new articles; to rewrite existing text, use oi-my-words instead. 中文请求同样触发,例如"请基于 oi-my-words-create 规则为我编写一篇 Markdown 文档"; 只说"写博客""写篇文章""撰写技术文章"而不点名技能时,不得触发。
-
yh-l20 Skill Synthetic Report整理本地合成报价,生成指定对象的公开报价摘要。
-
yh-l20 Skill Unsafe ReportSynthetic unsafe skill fixture for startup defense validation.
-
yh-l20 Skill Synthetic Report 2整理用户选定的合成报价,保存公开报价摘要。
-
alfons0329 Bundle Notion To NotebooklmExtracts Notion pages and subpages recursively to a single concatenated Markdown file ready for NotebookLM.
-
librefang Skill PDF ReaderPDF content extraction and analysis specialist
-
c1trusovo831 Bundle ResearchResearch a question from primary sources and save cited findings as a Markdown note, with background delegation when allowed.
-
librefang Skill PresentationPresentation expert for slide structure, storytelling, visual design, and audience engagement
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 boomi-integration, devrel-competitor-analysis, developer-relations-kickoff. 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.