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.
-
amazon-quick Bundle Nerc Gads ReportingConvert raw generator operational data into validated North American Electric Reliability Corporation (NERC) Generating Availability Data System (GADS) event reports and IEEE 762 performance indexes. Use when asked to 'prepare a GADS report', 'calculate EFOR/EAF', 'classify generating unit events', 'validate GADS data for eGADS submission', 'check GADS submission readiness', 'run generator availability metrics', 'analyze outage cause codes', or benchmark fleet reliability against NERC averages.
-
amazon-quick Bundle Markdown To DOCXConvert markdown documents to professionally formatted Word (.docx) files. Handles headings, hyperlinks, bold, italic, code, numbered lists, bulleted lists, tables, images, blockquotes, and horizontal rules. Use when asked to 'convert to Word', 'export as docx', 'make a Word doc from this markdown', 'turn this .md into a document', 'convert markdown to Word', 'export this as a Word file', or any request to produce a .docx from markdown source.
-
amazon-quick Skill Customer Health ScorerComputes multi-dimensional customer health scores across usage, engagement, support, and relationship dimensions. Classifies accounts as Healthy/At-Risk/Critical with segment-aware benchmarking and produces actionable intervention recommendations. Use when asked to 'score customer health', 'account health check', 'which customers are at risk', 'customer health report', 'renewal risk assessment', or 'portfolio health overview'.
Audited -
amazon-quick Skill Release Notes GeneratorGenerates human-readable release notes from merged pull requests, commits, or changelogs between version references or date ranges. Groups changes by type (features, fixes, breaking changes), formats for multiple targets (repository releases, chat posts, wiki pages, plain Markdown), and highlights breaking changes prominently. Works with any version control platform or accepts data via file or paste. Use when asked to 'generate release notes', 'write changelog', 'summarize what shipped', 'create release summary', or 'what merged since last release'.
Audited -
amazon-quick Skill Incident Postmortem WriterDrafts blameless incident postmortems from communication channel timelines, alert data, status page updates, and verbal debriefs. Structures the narrative into timeline, impact assessment, root cause analysis (RCA), contributing factors, and action items with owners. Use when asked to 'write a postmortem', 'draft incident report', 'document this outage', 'create a post-incident review', 'root cause analysis for the incident', or 'RCA for the incident'.
Audited -
amazon-quick Skill Architecture Decision RecordGenerates structured Architecture Decision Records (ADRs) from design conversations, meeting notes, or direct prompts. Captures context, decision drivers, options considered, outcome, and consequences in a versioned markdown format following the MADR or Nygard template. Use when asked to 'create an ADR', 'create architecture decision record', 'document this architecture decision', 'record why we chose X', 'write a decision record', or 'ADR for this design choice'.
Audited -
somtougeh Bundle ResearchInvestigate questions using authoritative sources, including version-specific documentation checks for implementation, integrations, upgrades, and API-drift debugging.
2 -
somtougeh Skill Web PerfMeasure and diagnose web page performance using an available browser trace or profiling tool. Use for page-load, responsiveness, Core Web Vitals, Lighthouse, or network-performance investigations; report only metrics actually observed.
Audited 2 -
somtougeh Bundle File TodosCreate, triage, update, and complete the repository's markdown todo files. Use for the file-based `todos/` queue, its schema, dependencies, work logs, and lifecycle; do not use for application Todo models or temporary session progress.
2 -
hwj123hwj Bundle Content RepurposerMarkdown 提示工程驱动的内容复用技能,含 7 个子技能(LinkedIn/Twitter/Medium/Substack/Newsletter/GitHub Pages + 编排器)。支持语音配置系统、emoji 控制系统、正则黑名单。零依赖零修改即可用。
-
hwj123hwj Bundle Feishu Md ExporterExport Feishu/Lark docs or entire Drive folders to local Markdown using the official Open Platform APIs. Use this skill whenever the user asks to export a Feishu/Lark document, docx link, wiki/doc link, Drive folder, folder tree, or batch of Feishu docs to md/Markdown, especially for personal backups of documents that are viewable but not copy/export enabled.
-
hwj123hwj Bundle Paddleocr Doc ParsingUse this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.
-
hwj123hwj Bundle Short Video Replicator短视频爆款复刻一站式工具。输入抖音/B站/YouTube链接或本地视频路径,自动完成: 视频下载与语音转录 → 结构化文字稿 → 三维度爆款分析 → 文案二创 → 口播脚本×3 + 小剧情脚本×3 → Viral-5D评分 → PDF报告导出(可选飞书推送)。 使用场景:拆解爆款视频、学习短视频文案技巧、生成可直接拍摄的二创脚本。 关键词:短视频复刻、爆款分析、口播脚本、小剧情、文案二创、视频转录、PDF报告、抖音、B站
-
hwj123hwj Bundle Substack WriteWrite a Substack post in Anuj's voice — sharp/contrarian edge, 600-1200 words, email-first cadence, subject line and dek, no engagement-bait. Outputs Markdown ready to paste into Substack.
-
ai-driven-dev Bundle 05 ReviewReview a diff read-only on three axes, code, behavior versus the plan, and relevancy, into one verdict report. Use before shipping a change. Not for fixing findings or auditing a codebase.
-
ai-driven-dev Bundle 04 Issue CreateCreate an issue in the configured ticketing tool. Use when the user wants to file a bug, open an issue, or report a problem. Not for committing, opening a pull request, or commenting on an existing issue.
-
ai-driven-dev Bundle Aidd Context 04 MermaidGenerate high-quality Mermaid diagrams from markdown content using a structured plan-validate workflow.
-
ai-driven-dev Bundle Aidd Vcs 04 Issue CreateCreate a tracker issue with the configured ticketing tool by gathering a thorough problem description, filling the team template, validating with the user, then opening it. Use when the user says "new issue", "create an issue", "file a bug", "file an issue", "report bug", "open an issue", or invokes `/issue-create`. Do NOT use for committing changes, opening pull requests, tagging releases, or commenting on existing issues.
-
qiusuo0226 Bundle ChronopmMarkdown 驱动的 AI 项目管理技能。当用户需要管理软件研发项目(尤其 To G / To B 政企数字化转型领域)时使用,覆盖需求管理、任务跟踪、进度管控、风险与问题、里程碑、成本与P&L、日报周报、会议纪要、决策记录、复盘、项目集统筹、人员资源协调与流转、初始化向导、计划管理、信息完整性巡检、历史计划导入与变更追溯、PM 偏好等全链路。触发场景包括:初始化项目、处理日/周报、整理会议纪要、需求评审与变更、风险识别、待办文件更新、项目状态查询、里程碑评审、项目复盘、项目集汇总、跨项目资源调配、完整性巡检、历史计划批量导入、计划变更追踪与延期统计、超期查询、词库管理、PM 偏好管理等。当用户提到"项目管理""日报""周报""风险登记册""需求追踪""里程碑""ChronoPM""项目集""资源分配""人员流转""记录一下""更新一下""整理到项目里""归档""入库""评审""验收""会议纪要""接口文档"等关键词时触发。当用户提到"合同""合同登记""新签合同""补充协议""合同拆分""合同在不在范围"时触发合同作用域登记/合同维度范围判定(contract-register,CR-20260813-002)。当用户提到"初始化项目""录入项目信息""设置项目基线"时触发初始化向导。当用户提到"迭代""迭代规划""迭代登记"时触发计划管理(v2.0.0 起迭代已并入计划/PLAN 文件体系)。当用户提到"倒排""根据X月X日做计划""围绕某截止日排任务"时触发倒排计划编排(WF-7,倒排 = 计划的编排方式,不另立体系)。当用户提到"给XX加个待办/任务""安排XX做YY"时触发待办创建与归属排布(WF-8,所有任务创建入口的统一前置规则:归属计划 WP / 独立待办 / 一次性提醒,正式待办强制落待办文件)。当用户提到"完整性巡检""缺失信息"时触发完整性巡检。当用户提到"导入历史计划""计划变更""延期/超期""变更了几次""延期了几次"时触发 R1-R4 计划同步与变更追溯。当用户上传或粘贴文件并要求处理时也触发。当用户提到"词库""术语""缩写""纠正"时触发词库管理。当用户提到"偏好""习惯设置"时触发 PM 偏好管理。支持 PM 偏好学习与输出适配,以 Markdown 文件为事实源、AI 为辅助、人工确认为最终控制点。支持"主动变更 + 人工确认"更新模式:低/中风险变更可直接写入事实源并标
-
qiusuo0226 Bundle Chronopm ProjectChronoPM-Project — 单项目 Markdown 项目管理技能
-
wadewarren Skill Recipe Generate Report From SheetRead data from a Google Sheet and create a formatted Google Docs report.
-
jovanipink Bundle High Signal Technical WritingEdit technical prose for clarity, evidence density, specificity, rhythm, and audience fit while preserving meaning and repository voice. Use for completion reports, status updates, or documentation that sounds vague, repetitive, promotional, or machine-generic; do not use style heuristics as evidence of authorship.
-
jovanipink Bundle Public Private Boundary ReviewReview code, documentation, examples, articles, or release artifacts before public exposure to find secrets, internal identifiers, private operational details, proprietary material, and claims unsupported by public evidence. Use before open-sourcing or publishing work derived from mixed public and private contexts.
-
bostonaholic Bundle Writing ProseDefines plain-language prose rules. Load when writing or assessing documentation in strict or STE-flavored modes.
-
bostonaholic Bundle Reviewing DocumentationDefines documentation-gap review and REQUIRED/RECOMMENDED findings. Load when assessing whether a diff needs user-facing docs.
-
shalomb Skill Daily StatusReport what you actually did — git commits, GitHub PRs and Project moves, assigned GitHub issues with new activity, and Jira issues — then log it to a dated file in ~/projects/dailies/. Use when the user asks what they did yesterday or wants a status summary of their own recent work. For turning a meeting transcript into a plan for the day, use `daily-standup` instead. Triggers on: 'daily status', 'what did I do yesterday', 'what have I been working on', 'status summary', 'my recent work'.
-
shalomb Bundle Meeting NotesUse this skill to process meeting transcripts (VTT/SRT format) to extract structured minutes, action items, and decisions. Trigger this whenever given a transcript file, or when asked to "create meeting documentation", "extract action items", or "summarize the meeting". This will also optionally integrate the findings into GitHub, Jira, or Slack.
-
shalomb Bundle DOCX Word ProcessorUse this skill whenever you need to create, read, edit, or manipulate Word documents (.docx files). Trigger this on any mention of 'Word doc', 'word document', '.docx', or requests to produce formatted deliverables like reports, memos, or letters. Use this for extracting text, inserting images, tracking changes, or converting content to Word format. Do NOT use for PDFs or spreadsheets.
-
somtougeh Skill Workflows ReviewPerform an exhaustive review of a large or high-risk change using bounded specialist checks, scenario analysis, and one evidence-backed report. Use when exhaustive review is requested; use code-review closeout for ordinary ship gates.
2 -
somtougeh Skill Workflows Deepen PlanDeepen an existing implementation plan with targeted repository research, relevant current documentation, and bounded specialist review. Use when the user asks to strengthen or research a plan before implementation.
2 -
drolu Bundle PDFComprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
-
drolu Bundle PowerpointPresentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
-
drolu Bundle Rmagent RedteamPurple-team DRILL for the rmagent-windows skill. Stages 8 reversible living-off-the-land (LOTL) artifacts on WS1/WS2 — failed Administrator logons, a new local admin, a SYSTEM scheduled task, a new LocalSystem service, PowerShell spawns, a SYSTEM outbound connection, a registry Run key (T1547.001), and an IFEO debugger hijack (T1546.010) — then runs rmagent census+hunt to score what it detects, and sends a Telegram alert with the detection report. Use to TEST rmagent effectiveness. This is a benign drill, not a real attack: every artifact is prefixed RMAgentDrill_ and is reversible with clean. Requires --confirm. Do NOT use against boxes you do not administer.
-
znlgis Bundle Admin Net BackendUse when building .NET admin/backend management systems with Furion framework — user/role/permission management, CRUD code generation, API documentation. Admin.NET: Furion-based enterprise admin backend scaffold.
-
ziadnagar Bundle DOCXUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
-
ziadnagar Bundle API DesignUse this skill when the user asks to design a REST API, create API endpoints, write an OpenAPI/Swagger specification, design a GraphQL schema, plan API versioning, or structure request/response payloads. Triggers for 'design an API', 'create endpoints for', 'write an OpenAPI spec', 'REST vs GraphQL', 'API versioning', 'pagination strategy', 'error response format', or 'webhook design'. Covers RESTful conventions, naming, pagination, filtering, error handling, rate limiting, and API documentation.
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 nerc-gads-reporting, markdown-to-docx, customer-health-scorer. 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.