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.
-
creatorland Skill Creator Diligence Audience ReportPremium, audience-verified creator diligence one-pager. Use when the user wants a procurement/legal-grade vetting doc that INCLUDES real audience demographics, geo, and a fake-follower (credibility) score — e.g. "deep diligence on @creator", "audience-verified diligence", "is this creator's audience real and on-brand", "vetting one-pager with audience data". This is the PAID/token tier — it pulls a full audience report. For the cheaper profile-only version use creator-diligence-report.
-
imtangyujing Bundle Qbit WordQbit document conversion router for Feishu/Lark and Word workflows. Use when the user asks to export a confirmed Feishu/Lark outline to the Qbit Word template, convert/download a Feishu document as Word, rename a Word output from a Feishu title, save Qbit .docx files to the current project directory, or import a local Markdown draft into a real Feishu docx document while preserving Qbit article line breaks and rendering Markdown-linked images/videos as real media blocks.
-
imtangyujing Bundle Jay WriterJay的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于:写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说"帮我把这个写成文章"或"用我的风格写一下",只要上下文涉及内容创作和公众号输出,都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说"帮我写篇文章"的场景。标题生成(用qbitai-title skill)。
-
imtangyujing Bundle Hv Analysis横纵分析法(Horizontal-Vertical Analysis)深度研究Skill。由数字生命卡兹克提出,融合了索绪尔的历时-共时分析、社会科学的纵向-横截面研究设计、商学院案例研究法与竞争战略分析的核心思想。 当用户想要系统性研究一个产品、公司、概念、技术或人物时使用。核心是双轴分析:纵轴追踪从诞生到当下的完整生命历程(以叙事故事呈现),横轴在当下时间截面上与竞品/同类进行系统性横向对比,最后交叉两条轴产出独到洞察。最终产出一份结构完整、可直接阅读和继续编辑的Markdown研究报告。 触发词包括但不限于:横纵分析、研究一下、帮我分析、深度研究、做个研究、调研一下、竞品分析、帮我看看这个东西怎么样、这个产品/公司/概念是怎么回事、帮我摸清楚、帮我搞懂、帮我做个deep research。 即使用户只是说"帮我了解一下XX"或"XX是什么来头",只要上下文暗示需要系统性的深度研究(而非简单的概念解释),都应该触发。也适用于用户丢来一个产品名、公司名、技术名词说"帮我研究一下这个"的场景。 不要用于简单的名词解释(用户只是问"XX是什么")、不要用于公众号写作(那个用khazix-writer)、不要用于纯标题摘要生成(用wechat-title)。
-
imtangyujing Bundle Lark Slides飞书幻灯片:以 XML 格式读取和管理 PPT 页面。创建演示文稿优先用 `+create`;XML API 主要用于读取 PPT 全文信息、创建和删除幻灯片页面。当用户需要创建 PPT、读取 PPT 内容、管理幻灯片页面时使用。
-
imtangyujing Bundle Khazix Writer数字生命卡兹克(Khazix)的公众号长文写作skill。当用户需要撰写公众号文章、写稿子、续写文章、根据素材产出长文时使用。触发词包括但不限于:写文章、写稿子、帮我写、续写、扩写、公众号文章、长文、出稿、按我的风格写。即使用户只是说"帮我把这个写成文章"或"用我的风格写一下",只要上下文涉及内容创作和公众号输出,都应该触发。也适用于用户丢过来一个PDF、brief、新闻链接、语音转文字或任何素材说"帮我写篇文章"的场景。不要用于短内容(小红书帖子、推特、朋友圈)或纯标题摘要生成(那个用wechat-title skill)。
-
imtangyujing Bundle Lark Markdown飞书 Markdown:查看、创建、上传和编辑 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取或修改时使用。
-
imtangyujing Bundle Qbit Lark EditEdit Qbit Feishu/Lark draft documents from unresolved sidebar comments while preserving human review visibility. Use when the user asks Codex to apply teacher, editor, client, or collaborator feedback in a Feishu doc, especially small copy edits, insertions, deletions, paragraph breaks, Markdown-friendly formatting, or review-pass changes that must keep comments alive. Always mark additions and rewrites with yellow highlight, represent deletions with strikethrough instead of removing source text, and do not resolve comments unless explicitly requested.
-
imtangyujing Bundle Qbit Aigc SummitUse when the user wants to run or automate the Feishu AIGC summit summary workflow end to end: build the overall draft skeleton, create empty per-speaker docs, monitor Feishu Minutes by naming convention, extract viewpoint bullets into the overall draft, sync confirmed sections to individual docs, export Word files, and update the status table after every stage.
-
imtangyujing Bundle Jay Multimodal ContextConvert multimodal source material into usable writing context, especially articles, internet video/audio links, local recordings, Feishu Minutes transcripts, event transcripts, or raw Chinese interview transcripts that need polished interview-style Markdown or Obsidian notes. Use when the user provides article text, article links, Bilibili/video/podcast/audio links, local audio/video files, Feishu Minutes material, or raw transcript text and asks for note extraction, transcription, or interview polishing. This skill coordinates article-note routing, low-bitrate source audio retrieval, Feishu Minutes transcription, event transcript handling, and interview-polish editing while keeping orchestration, transcription, polishing, and final path routing responsibilities separate.
-
imtangyujing Bundle Qbit Academic SubmissionProcess academic投稿/学术投稿 materials into the Scholar Feishu Base SOP. Use when the user gives an academic manuscript, Word/docx file, author name, institution, paper/project description, conference info, Feishu群聊消息/@机器人上下文, or later provides a WeChat article link to match and write back to the投稿Base.
-
imtangyujing Bundle Feishu Aigc Summary SplitterUse when the user asks to process a Feishu/Lark conference summary assignment document, verify speaker names/titles/topics against a Feishu Base guest sheet, create or rebuild one overall draft plus per-section docx drafts, open editable sharing permissions, clean up older generated drafts, and return links grouped by assignee. Optimized for AIGC summit summary workflows using lark-cli docs v2 and Base records.
-
imtangyujing Skill Lark Workflow Standup Report日程待办摘要:编排 calendar +agenda 和 task +get-my-tasks,生成指定日期的日程与未完成任务摘要。适用于了解今天/明天/本周的安排。
-
imtangyujing Skill Prospectus Decoderhenry的招股书解读写作skill。当用户需要解读、拆解、详解一份招股书,把上百页的IPO文件写成一篇可读的科技媒体长文时使用。触发词包括但不限于:解读招股书、招股书详解、火线解析、IPO拆解、上市拆解、招股书写成文章、把这家公司的招股书写一篇、prospectus解读、S-1拆解、聆讯文件解读。也适用于用户丢过来一个招股书PDF或链接说"帮我写一篇"的场景。不要用于普通的公司分析、财报解读(用财报skill)、或者新闻消息稿。这个skill是henry-writer的专项延伸,继承henry所有的写作风格DNA,在其之上叠加招股书这种特殊文本的处理方法论。
-
ulpi-io Bundle Plan Founder Review 3Technical founder review of a plan before execution. Reads a plan from .ulpi/plans/<name>.md, verifies file paths exist, checks markdown/JSON consistency, challenges scope and architecture decisions, audits prerequisites/contracts/risk coverage/test gaps, scores sections, and delivers a verdict (APPROVE/REVISE/REJECT). Invoke via /plan-founder-review or when user says "review my plan", "check the plan".
-
ulpi-io Bundle Plan To Task List With Dag 3Language-agnostic build planner — explores the codebase, challenges scope with the user, identifies prerequisites and contracts, decomposes work into atomic TASK-NNN entries with dependency mapping, and emits canonical JSON + rendered markdown plans for parallel execution. Use when you need a structured task DAG that is safe to execute, not just easy to read.
-
ferroxlabs Skill Support 3Customer support orchestrator. Routes to the right sub-skill based on your verb - reply, kb-article, faq, escalation, refund-script, sla-review, nps-analysis, churn-investigate, or report.
37 -
davie521 Skill CleanupEnd-of-session cleanup: shut down every process the session started, find code-vs-doc mismatches and update the DOCS to match the code (code is the source of truth; never rewrite code just to match a doc), drive leftover tasks to zero (finish or explicitly report), and persist lessons learned to memory. Each phase must end with an explicit done / not-needed verdict — no silent skipping. Use when the user says 'cleanup', '收尾', '清理现场', '打扫', wants to wrap up a work session, or before handing off / ending a long task.
-
davie521 Skill Doc CoauthoringGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
-
davie521 Skill Visa Doc TranslateProduce an UNCERTIFIED draft English translation of visa application document images as a bilingual PDF (original + translation). Output is a draft for a human translator to review and certify — it is not a certified translation and must not be filed as one.
-
davie521 Skill Content Hash Cache PatternCache expensive file processing results using a composite key of SHA-256 content hash plus processor version and config — path-independent, auto-invalidating, with service layer separation. Use when caching costly file-processing outputs (PDF parsing, OCR, text extraction, image analysis) that recur across runs and the cache must survive file moves/renames while auto-invalidating on content change.
-
yenhao-huang Bundle Daily News OpsCoordinate the personal daily-news and official tech-blog digest workflows, write reverse-date Markdown under ~/Desktop/daily, and publish the resulting changes through Git. Use when the user requests either digest, both digests together, a manual rerun, or repair of missing daily output.
-
yenhao-huang Bundle Daily Reuters AI DigestRead the latest Reuters artificial-intelligence coverage and write a grounded Traditional Chinese daily Markdown digest under the current workspace. Use for the migrated Reuters AI cron, a manual daily digest, or repair of a missing Reuters report.
-
yenhao-huang Bundle Financial Report AnalysisAnalyze company financial reports with current Yahoo Finance data, show three-to-five-year numeric evidence for valuation, income statement, balance sheet, and cash-flow checks, then save and publish a Traditional Chinese report. Use for company comparisons, financial screening, 財報整理, or 財報指標檢查.
-
ariehmahoukou-web Skill PopupsWhen the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "[...]
-
cookiemonsterdev Bundle Rabbitmq DocsUse when users ask how to install, configure, publish to, consume from, cluster, secure, monitor, or troubleshoot RabbitMQ brokers and messaging applications, including AMQP 0-9-1, AMQP 1.0, queues, exchanges, bindings, routing, streams, publishers, consumers, management UI, plugins, or production operations, especially when they need official RabbitMQ documentation, exact links, or docs-grounded guidance.
-
bejeweledme Bundle Technical WritingCreate or revise technical documentation, architecture and design docs, API references, runbooks, troubleshooting guides, benchmarks, experiment reports, and engineering analyses.
-
bejeweledme Bundle Information PresentationCreate presentation and slide content for live delivery or independent reading, with supported claims, informative visuals, and a decision- or learning-oriented narrative.
-
bejeweledme Skill Information Research SynthesisResearch a question across sources and synthesize evidence into a decision-useful finding, survey, or report.
-
uwayxt Bundle QA Feedback Loop Orchestrator**Quality is not a final gate — it is a loop. Every finding that can be fixed automatically must be. Every finding that cannot must reach a human with full context, not just a bug report.**
-
ashermahonin Bundle Documentation Graph CuratorMaintain project documentation and Obsidian-first knowledge graph using Markdown notes, wikilinks, ADRs, artifact indexes, Mermaid diagrams as visual layer, change logs, and graph hygiene. Use when syncing docs after code changes, creating a project vault skeleton, updating project memory, linking requirements to architecture and tasks, cleaning stale notes, or making sure agents can navigate the project without confusion.
-
cookiemonsterdev Bundle Kafka DocsUse when users ask how to build, explain, configure, tune, secure, operate, replicate, or troubleshoot Apache Kafka clusters and applications, including topics, partitions, producers, consumers, consumer groups, KRaft, brokers, replication, exactly-once semantics, Kafka Connect, Kafka Streams, ACLs, SASL, SSL, tiered storage, monitoring, or upgrading, especially when they need official Apache Kafka 4.3 documentation, exact links, or docs-grounded guidance.
-
cookiemonsterdev Bundle Nginx DocsUse when users ask how to install, configure, proxy, load-balance, secure, reload, or troubleshoot NGINX as a web server, reverse proxy, mail proxy, or TCP/UDP stream proxy, including nginx.conf syntax, server blocks, location matching, upstreams, SSL/TLS, HTTP/2, HTTP/3, QUIC, rewrite rules, rate limiting, caching, FastCGI, WebSocket proxying, njs scripting, or module directives, especially when they need official NGINX documentation, exact links, or docs-grounded guidance.
-
cookiemonsterdev Bundle Bullmq DocsUse when users ask how to create, configure, process, schedule, retry, rate-limit, monitor, or troubleshoot BullMQ job queues and workers in Node.js, including queues, workers, jobs, flows, job schedulers, events, telemetry, Redis compatibility, NestJS integration, patterns, or production deployment, especially when they need official BullMQ documentation, exact links, or docs-grounded guidance.
-
cookiemonsterdev Bundle Stripe DocsUse when users ask how to build, configure, integrate, test, secure, or troubleshoot Stripe payments, billing, subscriptions, Connect marketplaces, Checkout, Elements, webhooks, or the Stripe API, especially when they need official Stripe documentation, exact links, docs-grounded guidance, or the correct API/SDK behavior for handling money.
-
cookiemonsterdev Bundle Object ObjectUse when users ask how to {primary-capabilities}, especially when they need official {Product Name} documentation, exact links, or docs-grounded guidance.
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 creator-diligence-audience-report, qbit-word, Jay Writer. 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.