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.
-
larsboes Bundle ObsidianOperates the user's Obsidian vault as the single durable knowledge surface — resolves the vault, gates every write on the vault contract, creates and retypes notes, runs bulk property/link sweeps, maintains the wiki layer, and recalls what earlier sessions said. Use for any work inside the vault (notes, frontmatter, MOCs, bases, canvases, clippings, session and planning notes), for "what do we know about X", and for "what did we do last week / where did we leave off". Do not use for generic markdown outside the vault, for prose style (human-writing), or for authoring skills (skill-creator).
-
odere-pro Skill FixAuto-repair what /claude-wiki-pages:lint reports. Idempotent — running twice on a clean tree produces no diff. Trigger when the user says "fix the lint errors", "repair the wiki", "auto-fix", or invokes /claude-wiki-pages:fix directly. Expects a fresh lint report in context, or runs its own lint pass internally.
-
gaintrace Bundle Churn RiskWhen the user wants to know whether a customer will stay, why, and what to do about it — for one account, a book, a segment, or a renewal window. Also use when the user mentions 'something is wrong', 'going to churn', 'at risk', 'churn risk', 'red accounts', 'who should I worry about', 'should I be worried', 'gone quiet', 'usage is down', 'usage has dropped', 'my gut says', 'health check', 'early warning', 'which renewals are in trouble', or 'save list'. Use this whenever someone is working out whether a customer will stay, even if they never say the word 'churn'. For the execution runbook once risk is known, see renewal-prep. For portfolio revenue math, see renewal-forecast. For the intervention on an already-red account, see save-play. For a loss that already happened, see churn-postmortem.
-
gaintrace Bundle Renewal ForecastWhen the user wants a defensible renewal revenue forecast for a book, segment, quarter or year — categories, dollars, confidence, and the arithmetic shown. Also use when the user mentions 'forecast feels wrong', 'pressure test my forecast', 'sandbagging', 'calculate our nrr', 'nrr and grr', 'my renewal number', 'renewal forecast', 'what's my forecast for the quarter', 'available to renew', 'ARR bridge', 'ARR waterfall', 'what's our NRR', 'GRR', 'net revenue retention', 'gross retention', 'commit vs best case', 'roll up my renewals', or 'what do I tell the CFO'. Use this whenever someone is trying to put a number on future renewal revenue — a quarter, a book, a segment or the year — even if they never say the word and whenever they ask how a retention metric was computed. For whether one account will churn and why, see churn-risk. For the per-account T-180→T-0 renewal runbook, see renewal-prep. For rescuing one at-risk account, see save-play. For sizing the expansion line, see expansion-finder.
-
gaintrace Bundle Post Call FollowupWhen the user has just finished a customer call, QBR, renewal conversation, escalation or check-in and needs the follow-up done properly — the customer recap, the internal note, the CRM updates, and the plays the call should trigger. Also use when the user mentions 'just got off a call', 'here are my notes', 'from this transcript', 'follow-up email', 'recap email', 'send them a summary', 'write up my call notes', 'post-call notes', 'action items from the call', 'next steps email', 'summarise the call', 'here's my transcript', 'log this call in Salesforce', 'update the CRM after the call', or 'they didn't commit to anything'. Use this whenever a customer conversation has just ended or notes/a transcript are pasted in, even if they only ask for 'a quick email' and never say the word follow-up. For preparation before the call, see pre-call-brief. For the QBR deck, see qbr-builder. For the renewal runbook, see renewal-prep. For a full risk re-score, see churn-risk. For an escalation war room, see save-play.
-
gaintrace Bundle Proactive OutreachWhen the user needs to decide who to contact, why now, on which channel, and what to say — from one data trigger or across a whole book. Also use when the user mentions 'write me something', 'not just checking in', 'what do i send them', 'who should I reach out to this week', 'what should I send Acme', 'draft an email to', 'write a note to', 'their usage dropped, what do I say', 'they hit their seat limit', 'follow up on this NPS score', 'they just raised a round', 'my accounts have gone quiet', 'outreach list', or 'sequence'. Use this whenever someone is choosing which customer to contact or is about to write to a customer, even if they never say the word 'outreach' — including 'what do I do about this account' and 'can you write this email'. For the risk analysis behind a trigger, see churn-risk. For a booked meeting, see pre-call-brief. For an already-red account, see save-play. For sizing an expansion, see expansion-finder. For the post-call recap, see post-call-followup.
-
gaintrace Bundle Exec Retention ReviewWhen the user has to tell the retention story upward — to a board, an exec staff meeting, an investor update, or an all-hands — and the numbers have to survive a CFO. Also use when the user mentions 'cfo wants to know', 'why nrr dropped', 'present retention to the board', 'board deck', 'board slides', 'I present to the board next week', 'what do I tell the board about churn', 'exec staff update', 'investor update', 'our NRR dropped, what do I say', 'the CFO is going to ask', 'justify a CSM hire', 'headcount business case', 'CS budget ask', or 'board pre-read'. Use this whenever retention numbers are about to be shown to people who do not run CS, even if they never say the word 'board' — the failure mode is a metrics tour with no ask. For the account-level risk sweep that feeds it, see churn-risk. For the portfolio revenue call, see renewal-forecast. For a customer-facing business review, see qbr-builder. For the shared metric definitions, see cs-context.
-
dills122 Skill Planning Files LiteUses persistent markdown files to keep complex multi-step work organized across long sessions. Use when work requires research, many tool calls, multiple phases, or context recovery.
-
anthealaffy Bundle Contributing Upstream维护者时间极稀缺:bug 报告、最小可复现、issue、PR、CONTRIBUTING.md、许可证与安全披露都要信噪比高。 Use when the user wants to report a bug, submit a pull request, contribute to an open-source project, write a minimal repro, or asks whether to fork upstream. 触发于「我要报个 bug/提个 PR/贡献开源/写个复现」。
-
djb258 Skill Sales ProspectProspect Analysis Orchestrator — produces a scored, prioritized, actionable prospect report by launching 5 parallel subagents and synthesizing their results into a unified PROSPECT-ANALYSIS.md. Trigger on `/sales prospect <url>`, or when any task requires full multi-dimensional prospect scoring from publicly available data. Industry-agnostic engine.
-
djb258 Skill Sales ObjectionsObjection Handling Playbook Engine — generates OBJECTION-PLAYBOOK.md with word-for-word response scripts for 15 universal objections, 5 industry-specific objections, competitive battle cards, pricing tactics, and prevention techniques. Uses Feel-Felt-Found (FFR) and Acknowledge-Bridge-Close (ABC) dual-framework structure. Invoked standalone via `/sales objections <topic/industry>`. Industry-agnostic engine.
-
djb258 Skill Sales Report PDFProfessional Sales Report PDF Generator — reads SALES-REPORT.md and prospect files from the current directory, assembles a structured JSON payload, and invokes a Python/reportlab script to produce a polished, multi-section PDF (cover page, score charts, comparison table, top prospects detail, action plan, methodology). Generic engine: PDF layout, sections, color scheme, and JSON schema are constants. Company names, scores, and prospect data are variables.
-
elzawarudo Bundle Krt Document ForgeConvert PDF and DOCX source documents into versionable Markdown artifacts for coding harnesses. Use when a user needs to extract project briefs, requirements, client notes, architecture documents, contracts, or other .pdf/.docx inputs into .md so krt-harness-wise or another planning skill can use them as harness evidence. Runtime aliases may expose this as krt:document-forge.
-
fastrevmd-lab Bundle Firewall Config ConversionConvert parsed configurations among Cisco ASA/FTD, FortiGate, PAN-OS, and Juniper SRX with a fidelity report. Use when migrating objects, policy, NAT, zones, routing, HA, or VPN and producing target-native CLI with converted, caveat, and manual classifications. Parse raw configs first; output is not production-ready.
-
fredrikaverpil Skill ObsidianFind, navigate, read, and edit notes in the user's personal Obsidian vault (an iCloud-synced markdown collection on macOS). Use whenever the user mentions "the vault", "my notes", "Obsidian", a daily note, a meeting note, scratchpad, or asks to look up/jot down something that sounds personal-knowledge-base-like (e.g. "what did I write about X", "add a note about Y", "today's daily note") — even if they don't say the word "Obsidian".
-
techwolf-ai Skill Kb ImportImport knowledge from existing documents into structured KB entries. Reads source documents (Markdown, PDF, DOCX, plain text), extracts key information, and creates properly formatted KB entries with YAML frontmatter.
-
timzaak Bundle T DocGenerate human-readable project documentation — tutorials, getting-started guides, architecture overviews, API references, deployment or onboarding docs — by scanning the codebase for real facts. Output prefers an existing docs-web site over docs/tutorials/. Use when the user asks to write project docs, tutorials, guides, onboarding material, or a module walkthrough. Not for PRDs, technical designs, or API schema generation.
-
timzaak Bundle T Tech ResearchAssess technical feasibility for a feature. Scans codebase, checks dependencies, researches libraries, and writes a structured report under .ai/tech-research/.
-
wellapp-ai Skill Draft InvoiceDraft and create a real invoice record in Well from a conversational description — e.g. "invoice Acme Corp $2,500 for consulting work, due in 30 days." Use when the user asks to "draft an invoice", "create an invoice for [client]", "bill this client for Y", "send an invoice to [company] for [amount]", or "invoice [client] $[amount] for [description]". This is a WRITE skill — it composes the invoice from user-supplied fields (never inventing an amount, tax id, date, or line item) and always shows the full draft for explicit confirmation before creating it. Once created, it also renders the invoice into a print-ready A4 PDF on the issuer's own letterhead and attaches it to the invoice record. Requires a connected Well workspace; if none, this skill walks the user through connecting one first. It creates the invoice record and its attached PDF only — it does not email or send anything to the client.
Audited -
dongzhigang13305312738-art Bundle Transfer Old Latex To New当用户明确要求“迁移 LaTeX 模板”“把旧项目接入 ChineseResearchLaTeX”“把旧标书/论文/毕业论文/简历套进当前模板”“把 Word/PDF/Markdown/零散 tex 整理进现有项目”,或直接提到 `transfer-old-latex-to-new` 时使用。旧别名 `migrating-latex-templates` 可兼容理解。该 skill 只负责把正文内容迁移到当前仓库现有模板的内容层;绝不能修改 `packages/` 内公共包源码、也绝不能修改 `projects/` 内模板样式或入口骨架,只能写入目标项目允许承载正文的内容文件。
-
dongzhigang13305312738-art Bundle Research Literature Review当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研",或要求使用旧名 systematic-literature-review skill 时使用。AI 自定检索词,多源检索→去重→AI 逐篇阅读并评分(1–10分语义相关性与子主题分组)→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作(固定摘要/引言/子主题/讨论/展望/结论),保留正文字数与参考文献数硬校验,强制导出 PDF 与 Word。支持多语言翻译与智能编译(en/zh/ja/de/fr/es)。
-
quriosity-agent Bundle Qcut SlideCLI-first slide deck generator for QCut. Analyzes markdown or text content, creates a slide outline, generates per-slide image prompts, renders slide images through its own local fal-backed renderer, and merges the results into PPTX or PDF. Ships with its own local slide references. Use when the user wants a real command-line slide workflow rather than an interactive slash-skill flow.
-
quriosity-agent Bundle Jianying Text Style ReferenceTrace Jianying (剪映专业版) decorative text and word-art cards from local ressdk catalog metadata to downloaded artistEffect packages, classify TextStyle versus InfoSticker, inspect gradients, textures, strokes, shadows, and SDF runtime dependencies, and plan clean-room QCut parity. Use for 剪映花字, 文字样式, 花字缓存, word art, decorative text, transparent text textures, effectStyle.json, SDFTextSystem, or questions about how a Jianying text style is stored and reproduced.
-
fabioc-aloha Skill Act Documentation HygieneImproves documentation accuracy, discoverability, consistency, and Markdown quality while deferring to repository conventions.
-
fabioc-aloha Skill Act Skill Inventory ReportGenerates a current skill-inventory report from the live Scout host. Use when a user asks to list skills, inventory skills, or report the current ACT skill library.
-
agent-engineer-master Bundle Compliance CheckAssesses US regulatory compliance likelihood for any consumer product before listing for US sale. Accepts a CJ product PID/URL, Amazon ASIN, or product name/description as input. Classifies the product into a regulatory category (children's toys, electronics, cosmetics, supplements, pet products, apparel, kitchen/food-contact, or general consumer goods), determines which US standards apply, gathers market evidence, and produces a structured verdict (🟢/🟡/🟠/🔴). Saves report to a compliance-reports directory. Do NOT use for non-US markets or to produce legal opinions.
-
caslubbers Skill Java Clean CommentsEnforces comment and Javadoc hygiene in Java — no commented-out code, no author or ticket metadata, no comments restating the code, and Javadoc that documents contracts rather than repeating signatures. Use when writing or reviewing Java comments and Javadoc, and when the code shows commented-out blocks, TODO or FIXME banners, @author or date tags, boilerplate Javadoc, or documentation that no longer matches the method.
Audited -
connorgriffin Bundle ResearchInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a research worker.
-
connorgriffin Bundle Openspec AdoptAdopt OpenSpec in a repo that lacks it: scaffold the openspec/ layout, write baseline specs describing the system as it exists today (from code, docs, and git history), and deliver the whole thing as a documentation-only PR. One-time per repo. Trigger when the user asks to adopt openspec, add openspec to a repo, scaffold openspec, or write baseline specs. Invoked as /openspec-adopt <org/repo or path>.
-
ilamanov Skill Lecture NotesTransform a plain-text video lecture transcript into clean, skimmable markdown study notes. Use when the user provides a lecture transcript (or a file containing one) and wants structured notes, a summary, or a study reference from it. Triggers on requests like "make notes from this lecture", "summarize this transcript", "turn this lecture into notes", or when a transcript file is provided with a request for notes.
-
ilamanov Skill Fix Pr ReviewsFetch and triage code review findings from PR comments and/or review markdown files. Pulls review comments from the current branch's open PR (GitHub review comments, inline suggestions, and general comments that look like code reviews — from Claude Code, Codex, Copilot, etc.), classifies which findings are valid versus ignorable, explains how valid findings should be fixed, and sets up a thread watcher for new PR review comments when working against a GitHub PR. Does not modify code unless the user explicitly gives approval to apply fixes. Also accepts local review files. When explicitly asked to commit and push review fixes, pushes the branch and comments "@codex review" on the PR to request a fresh review. Triggers on requests like "fix PR reviews", "fix review comments", "fix PR feedback", "apply review fixes", "fix code review findings", "check new findings", or any mention of fixing/issues from PR comments or review files.
-
ilamanov Skill Create Learning MapInterview the user to understand their learning goal and existing knowledge, then generate an interactive Obsidian-based learning map — a DAG of bite-sized lessons as markdown files linked via an Obsidian canvas.
-
iwanalq Bundle Lark Doc飞书云文档 + 本地 Office Word 一体化文档技能。【飞书/Doubao 文档】当用户给出 feishu.cn 或 doubao.com 的 /docx/、/wiki/ URL 或 token,或要求创建/打开/读取/总结/整理/改写/翻译/审阅/编辑云文档、追加替换删除移动内容、调整排版、插入或下载图片/附件/素材/画板时使用(命令走 lark-cli docs --api-version v2,默认 DocxXML,也支持 Markdown;文档内嵌电子表格/多维表格/画板/同步块时先用本 skill 提取 token 再下钻)。【本地 Office】当用户上传 .docx/.doc/.pdf 并希望产出同类文件,或提到 Word 文档、简历/CV、专利/权利要求书/审查意见、签证文件/表格填写、起诉状/公告/会议通知/公文 等强格式文书时,路由到 office-word 模块用脚本解析与生成 .docx/.pdf。路由依据是输入载体(飞书 token vs 本地文件)和文书类型,而非域名。
-
iwanalq Bundle Lark Markdown飞书 Markdown:查看、创建、上传、编辑和比较 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用。
-
iwanalq 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。
-
idkwhatimd0ing Bundle Demo PrepCreate a timed hackathon or demo-day presentation script, click path, backup plan, rehearsal checklist, and judge Q&A. Use this skill whenever the user is preparing to present, pitch, record a demo video, make slides, rehearse, or turn a working app into a clear story for judges.
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 act-documentation-hygiene, obsidian, fix. 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.