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.
-
okwinds Skill Resume Reporter汇总:写 report.md 记录 src/dst run、fork 点与 evidence 指针(workflow 示例:Reporter 角色)。
-
okwinds Skill View Image Offline Runner离线演示:在 workspace 内生成小 PNG,并通过 view_image 读取返回 base64/mime/bytes,最后落盘 image_meta.json 与 report.md。
-
okwinds Skill Aggregator汇总器:读取 outputs/* 并生成 report.md(包含证据路径指针)。
-
okwinds Skill Chatops Incident Triage Assistant读取 incident.log,澄清关键问题(request_user_input),更新计划(update_plan),输出 runbook.md/report.md。
-
cyberuni Bundle Init QuillUse this skill to register quill as the SDD documentation plugin for this project — writes a quill role-map entry to .agents/universal-plugin.json so the SDD conductor resolves the quill production-chain roles for documentation domain types.
-
cyberuni Bundle Verify ScenariosPartial Skill: invoke by name only — the Gherkin-scenario-to-test-report bridge verifier — invoked by the impl-judge at the impl gate, not triggered by users directly.
-
cyberuni Bundle Quill Builder SpecPartial Skill: invoke by name only — the Quill Builder bar at the spec gate — what a documentation spec must contain. Loaded by the Quill spec-producer to self-align and by the spec gate to grade. Not triggered by users directly.
-
cyberuni Bundle Check Spec ReferencesPartial Skill: invoke by name only — project-spec/check-spec-references' engine that resolves every relative reference in one project spec's markdown and fails on the ones pointing at nothing — run from the per-project CI entrypoint, not triggered by users directly.
-
ferroxlabs Skill Ferrox Docs UpdateYou want project documentation written or refreshed, checked against the actual code
37 -
synkraai Bundle Architect FirstGuide for implementing the Architect-First development philosophy - perfect architecture, pragmatic execution, quality guaranteed by tests. Use this skill when starting new features, refactoring systems, or when architectural decisions are needed. Enforces non-negotiables like complete design/documentation before code, zero coupling, and validation by multiple perspectives before structural decisions.
-
jtprogru Bundle SrekitСкаффолдит SRE-артефакты через CLI `srekit` — investigation log, RFC/ADR, SLO, error budget policy, capacity plan, retro, on-call report, changelog, LICENSE — и наполняет их из контекста сессии без галлюцинаций, с GAP-маркерами. Срабатывай на «сделать/оформить/завести» такой документ, даже без слова srekit. Постмортем — `srekit-postmortem`, runbook — `srekit-runbook`; команды `incident` больше нет.
-
jtprogru Bundle Obsidian IngestПревращает markdown-источник (статья, вебклип, транскрипт, конспект) в знания базы: литературная заметка, атомарки, связи. Срабатывай на «добавить в базу знаний», «переработать статью», «обработать конспект», «ингестировать», «положить в SecondBrain».
-
polar-bear-org Skill One On One CompanionBriefs a manager before every conversation with a direct report, weekly 1:1s and the annual review conversation alike, part of the Annual Review Cycle Pack by Polar Bear. Use this whenever the user says "run one-on-one-companion", "prep my 1:1 with [name]", "I'm meeting Maria in an hour", "help me prepare the review conversation", or pastes a meeting transcript into a direct report's pinned chat. Use it even for a quick "what should I ask Tomas today".
-
polar-bear-org Skill Role Play DesignerDesigns role-play walkthroughs for service concepts, part of the Design Thinking Pack by Polar Bear. Use this whenever the user says "run role-play-designer", "set up a service walkthrough", "help us act out this concept", "design a role play for the team", or a service idea exists only as boxes on a slide and nobody has lived it yet. Use it even for "how do we know this service actually works".
-
zjunlp Bundle ArxivSearch, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
-
tommylower Bundle Muller Brockmann Grid SystemsOpt-in Muller-Brockmann grid system for editorial, magazine, report, and longform web pages: modular columns, baseline rhythm, grotesque type, restrained color, inspectable grid overlays, subgrid bands, and optical display-type alignment. Use when explicitly asked for Muller-Brockmann, Swiss/International Typographic Style grids, magazine spreads, editorial layout, grid systems, baseline grids, visible grid overlays, or rigorous grid alignment.
-
skills-agents-co Bundle Ceo TodoMaintains one canonical markdown file as a CEO's single source of truth for everything they're on the hook for, and runs the Getting Things Done loop over it — capture, clarify, organize, reflect, engage. Turns pasted emails, meeting notes, and asks into clarified next-actions with an owner and a priority, tracks status with a fixed vocabulary ([OPEN]/[DONE]/[STALE]/[WAITING]), ages open items to [STALE] after 7 days, flags [WAITING] items past their reply-by date, archives done work without ever deleting it, and never auto-closes an item the CEO added by hand. Every mutating run is snapshot-backed and gated by a bundled deterministic validator so a commitment is never lost, corrupted, or silently changed. Use this skill whenever the user says "run my to-do", "update my todo doc", "what am I on the hook for", "GTD", "getting things done", "capture this", "triage my inbox into my todos", "weekly review", "single source of truth", "CEO to-do", "/ceo-todo", or points at a markdown to-do file and asks to keep it
-
skills-agents-co Skill Board DeckTurns a period's financials into the finance section of a board deck. It takes a P&L export, plus optional prior-period and plan figures, and drafts structured text: headline metrics, period-over-period movement, the narrative behind each move, and an always-present list of what it could not figure out from the input. Hand it a past board deck and it matches that deck's format, swapping in this period's numbers and commentary. It never invents a figure and never guesses at a cause it cannot trace back to the input. Text only, no slides, charts, or images.
Audited -
skills-agents-co Skill Gl To ReportTurn a raw accounting/GL export into a clean reporting template (flash report) and draft variance commentary against prior actuals and budget. Use for the monthly close and the recurring flash report.
-
skills-agents-co Bundle Resume TailorTailors your resume and cover letter to a specific job description with ATS keyword scoring, parser-safe formatting, and submission-ready PDF output.
-
skills-agents-co Bundle Data Set AnalysisReads an attached data file and a stated data type, then writes a four-part report, summary of key content, patterns and trends, insights grouped by priority, and recommendations, with the metrics it focuses on shifting to match the data type. Every insight names why it's high, medium, or low priority, and every recommendation names the insight it follows from. Use whenever the user attaches a data file and asks for analysis, insights, or a summary, or says "analyze this data", "analyze the attached file", "what patterns are in this", "give me insights on this data set", or "/data-set-analysis".
Audited -
skills-agents-co Skill Expense Policy CheckReview expense reports against policy, flag violations and missing receipts, and draft the monthly missing-receipt chase. Use on an expense report or export, or at month-end. Every flag cites the policy rule it breaks; ambiguous items are flagged to confirm, never auto-approved or auto-rejected. The chase is a draft a person sends.
-
kaiohenricunha Skill Create ExperimentRun a scoped, local-only experiment and save the report to docs/experiments/. Triggers on: "let's try", "compare A vs B", "prototype", "explore".
-
kaiohenricunha Skill Release ConductorGate the open release-please PR before merging: verify CI green, feature PRs landed, no release blockers, changelog reflects intent. One-word approval, then merge. Reports the resulting release.yml run URL. release-please owns the changelog/bump/tag; release.yml owns OIDC npm publish — this skill only gates the merge in between. Triggers on: "ship a release", "cut a release", "merge the release PR", "is the release ready", "verify the release".
-
socketdev Skill Decomposing TicketsBreak a plan, spec, or findings report into independently-grabbable vertical-slice tracker tickets.
-
dss-time Bundle PDF ReviewDefault to this Skill for an unqualified PDF review and for checks involving searchable text, structure, tables, page-located claims, numeric consistency, citations, scanned pages, OCR, rendering, completeness, or visual layout. Detect available capabilities and degrade within this Skill when tools are unavailable; do not modify the source PDF or claim unsupported verification. Do not use when the user explicitly requests pdf-review-basic or a lightweight, text-only check without OCR, rendering, or complex layout review. 未限定范围的通用 PDF 审查,以及涉及可搜索文字、结构、表格、页码定位、数字一致性、引用、扫描页、OCR、渲染、完整性或视觉版式的检查,默认使用本 Skill。检测可用能力,工具不可用时仍在本 Skill 内降级;不得修改原 PDF 或声称完成不受支持的验证。用户明确指定 pdf-review-basic,或明确要求不做 OCR、渲染和复杂版式检查的轻量纯文本任务时不使用本 Skill。
-
dss-time Bundle Report WriterDraft or revise a structured report from user-provided goals, audience, evidence, and format, separating facts, quotations, inferences, recommendations, and unknowns. Use when the deliverable is a report; use research-brief when the main task is gathering and synthesizing evidence, and do not invent missing facts or claim DOCX/PDF generation without available tools and explicit authorization. 根据用户提供的目标、读者、证据和格式撰写或修订结构化报告,并区分事实、引用、推断、建议和未知项。交付物是报告时使用;主要任务是搜集和综合证据时使用 research-brief;不得补造事实,也不得在缺少工具或未获明确授权时声称生成 DOCX/PDF。
-
dss-time Bundle Research BriefDefine and answer a bounded research question with a source plan, evidence ledger, cross-checking, conclusions, unknowns, and next steps. Use when gathering or synthesizing evidence is the primary task; use report-writer when supplied material only needs a polished report, and never claim current research without accessible sources or network capability. 围绕有边界的研究问题制定来源计划、建立证据台账、交叉验证并输出结论、未知项和下一步。主要任务是搜集或综合证据时使用;已有材料只需形成正式报告时使用 report-writer;无法访问资料或网络时不得声称完成实时研究。
-
dss-time Bundle Document ReviewDefault to this Skill for an unqualified document or Word review and for holistic checks of structure, logic, completeness, terminology, factual support, figures, citations, grammar, formatting, tables, links, comments, tracked changes, or authorized revisions. When DOCX or rendering tools are unavailable, degrade within this Skill and state the limitation. Use content-consistency-check for cross-document reconciliation, and do not use when the user explicitly requests word-document-review-basic or a lightweight, read-only, text-and-headings-only Word check without complex formatting or revisions. 未限定范围的通用文档或 Word 审查,以及结构、逻辑、完整性、术语、事实依据、数字、引用、语法、格式、表格、链接、批注、修订痕迹或获授权修订等整体检查,默认使用本 Skill。DOCX 或渲染工具不可用时仍在本 Skill 内降级并说明限制。跨文档核对应使用 content-consistency-check;用户明确指定 word-document-review-basic,或明确要求轻量、只读、只检查文字和标题且不处理复杂格式或修订时不使用本 Skill。
-
dss-time Skill PDF Review BasicPerform a lightweight, read-only, text-only PDF check only when the user explicitly limits the task to extractable text, headings, obvious textual issues, and a short issue list without OCR, rendering, scanned-content recognition, tables, images, complex layout, or source-file changes. Do not use for an unqualified PDF review; use pdf-review for generic requests, page or visual verification, OCR, scanned pages, tables, images, layout, or completeness. PDF modification or regeneration is outside both review Skills and requires a separately authorized editing workflow. 仅在用户明确把任务限定为基础、轻量、只读、纯文本检查时,检查 PDF 的可提取文字、标题和明显文本问题并给出简短清单,不做 OCR、页面渲染、扫描内容识别、表格、图片、复杂版式或源文件修改。不得用于未限定范围的通用 PDF 审查;通用请求、页码或视觉核验、OCR、扫描页、表格、图片、版式或完整性应使用 pdf-review。PDF 修改或重新生成不属于这两个审查 Skill,需要另行授权的编辑流程。
-
dss-time Bundle Safe Change PlanTurn a confirmed specification, root-cause finding, or impact analysis into an atomic, verifiable, reversible implementation plan with explicit scope and risk controls. Use only when material decisions are closed and blast radius is sufficiently known; route open decisions to requirements-clarification, settled requirements needing a specification to requirements-to-spec, unknown impact to change-impact-analysis, architecture rationale or decision documentation to architecture-decision-record, and execution to safe-fix-implementation. 将已确认规格、根因结论或影响分析转为原子化、可验证、可回滚且范围明确的实施计划。仅在重大决策已闭合且影响范围足够明确时使用;未决需求交给 requirements-clarification,已闭合但尚需规格化的需求交给 requirements-to-spec,影响未知交给 change-impact-analysis,架构理由或决策文档交给 architecture-decision-record,执行交给 safe-fix-implementation。
-
dss-time Bundle Documentation SyncSynchronize documentation with a confirmed code, configuration, API, or behavior change by updating only evidence-backed README, API, configuration, example, migration, and changelog content while preserving style and language. Use for documentation-only edits; do not modify production behavior, invent undocumented facts, or use as a general code fix. 根据已确认的代码、配置、API 或行为变更,只更新有证据支持的 README、API、配置、示例、迁移和 CHANGELOG 内容,并保留原有风格与语言。用于仅文档修改;不得改变生产行为、编造未证实内容,也不作为通用代码修复。
-
dss-time Bundle Spec To Work ItemsDecompose a confirmed specification, implementation plan, or settled conversation into independently executable and verifiable vertical work items with dependencies, safe parallelism, conflict areas, tests, risks, and rollback notes. Use for delivery planning of a multi-behavior scope; return copyable Markdown in the current response only and never write files, invoke Shell, or create external tasks even with user authorization. Do not use for unresolved requirements, a single small fix, or a file-by-file technical-layer checklist. 将已确认规格、实施计划或已闭合对话拆成可独立执行和验证的垂直工作项,明确依赖、安全并行、冲突区域、测试、风险和回滚。用于包含多个可交付行为的交付规划;只在当前响应返回可复制 Markdown;即使用户授权也不写文件、不调用 Shell、不创建外部任务。需求未闭合、单个小修复或按文件与技术层罗列清单时不使用。
-
dss-time Bundle API Contract ReviewReview a specific REST, GraphQL, RPC, event, SDK, or internal-module contract across server, client, schema, documentation, and tests, classifying breaking, non-breaking, and behavioral changes. Use for API contract compatibility; do not perform a general code review, generic impact analysis, or modify the interface. 审查具体 REST、GraphQL、RPC、事件、SDK 或内部模块契约在服务端、客户端、Schema、文档和测试间的一致性,并分类破坏性、非破坏性和行为变化。用于 API 契约兼容性;不替代普通代码审查或通用影响分析,也不修改接口。
-
dss-time Bundle Presentation OutlineDesign an audience-specific presentation story and slide-by-slide outline with each slide's purpose, title, key points, evidence, and suggested visual. Use when the default deliverable is an outline; generate PPTX only when the user explicitly requests it and capable presentation tools are available, and do not invent missing data or turn a report into dense slides. 针对受众设计演示故事线和逐页大纲,包含每页目的、标题、要点、证据和建议视觉。默认交付物是大纲时使用;仅在用户明确要求且平台具备演示工具时生成 PPTX;不得编造缺失数据,也不得把报告机械切成高密度幻灯片。
-
dss-time Bundle Safe Fix ImplementationImplement one small, safe, verified production fix after a clear diagnosis or for an exact, low-risk edit with an explicit target and desired result. Use safe-test-implementation for test-only changes and documentation-sync for documentation-only changes. 在明确诊断后,或针对目标与期望结果清楚的精确低风险编辑,实施一个小范围、可验证的生产代码修复。仅测试修改使用 safe-test-implementation,仅文档修改使用 documentation-sync。
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 ferrox-docs-update, resume_reporter, view_image_offline_runner. 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.