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.
-
coleam00 Bundle Diy Yt CreatorUse when the user wants to create a new YouTube Short using one of the templates in this repo's templates/ folder. Spawns the project folder, drafts the script from a topic, generates TTS, fills the composition with real content sync'd to word-level timestamps, lints + inspects, and opens preview. Never auto-renders.
-
flyingtimes Bundle Vision这个技能接收用户给出的图片、pdf文件,按照用户的要求进行描述、综述、解释、界面截图复刻等功能。
-
frane Bundle Debug Failed ActionWhen your last `vs_act` returned an unexpected result (NOT_FOUND, no visible state change, suspected silent failure), run this skill with the action's pre-token. Pulls console errors, network failures, and current performance into one report.
-
isomoes Bundle Isomoes WritingUse when drafting, rewriting, or polishing weekly reports, technical blog posts, or similar long-form technical writing, especially when the user wants objective technical prose, stronger narrative flow, or format-specific adaptation between report and blog styles.
-
layer5io Skill Quota AxiReport local Claude, Codex, Cursor, GitHub Copilot, and Grok quota windows via the quota-axi CLI - remaining percentages, reset times, and provider status read from local auth sources, with no routing, recommendation, or provider mutation. Use before deciding whether it is safe to keep spending a provider's quota, when the user asks about usage, rate limits, or remaining quota, or when comparing local provider headroom.
-
dmmulroy Skill JsdocsWrite, insert, or update Effect public API JSDoc so it satisfies the jsdocs oxlint rule. Use when adding or fixing JSDoc comments, resolving jsdocs diagnostics, preparing docs for JSON extraction, or reviewing public API documentation.
-
drpwchen Skill Paper DigestProduce a content/knowledge digest of ONE paper for fast absorption of its full content — not a quality critique. Use when the user wants to "整理內容", "快速吸收", "知識整理", "內容平讀", or when /paper-sync dispatches a 📚內容 pick. The digest reorganizes the paper's full text into a teaching-style structured note (structure routed by paper type) plus self-test review cards pushed to the 複習頁 (configured `review_site.url`). REQUIRES full text: no full text → STOP and report 缺全文, never produce an abstract-only digest. NOT a critical appraisal (that is /paper-review) and NOT a multi-paper synthesis.
-
drpwchen Bundle Paper ReviewDeep single-paper academic analysis — journal credibility, author profiling, reference verification, citation impact, and critical appraisal. Like a teaching hospital journal club report. Use this skill whenever the user wants to deeply review, evaluate, or dissect a single academic paper, prepare a journal club presentation, verify a paper's references, check an author's track record, or do any thorough paper-level analysis. Also trigger when the user says "review this paper", "深度評讀", "journal club", "論文評讀", "幫我看這篇", or provides a DOI/PMID asking for analysis. NOT for multi-paper systematic reviews or standalone evidence grading.
-
dubzzz Skill Javascript Testing ExpertExpert-level JavaScript testing skill focused on writing high-quality tests that find bugs, serve as documentation, and prevent regressions. Advocates for property-based testing with fast-check and protects against indeterministic code in tests. Does not cover black-box e2e testing.
-
ekuris-repos Skill Markdown FrontmatterAdd and maintain YAML frontmatter in Markdown files. Use this whenever creating or substantially editing any .md content in this repository.
Audited -
embedpdf Bundle Embedpdf ConventionsApply EmbedPDF repository architecture and implementation conventions. Use when adding or changing plugins, permissions, package names, viewer entry points, engine services, CloudPDF server adapters or migrations, PDFium runtime concurrency or isolation, or documentation architecture.
-
emmansun Bundle Base64 Loong64 Lasx实现 LoongArch64 架构下 LASX(256-bit SIMD)加速的 BASE64 编解码 Go 汇编代码。Use when: 在 loong64 平台扩展 base64 实现、编写 LASX 汇编、处理 XVSHUFB/XVSSUBBU/XVSLTBU 等 Go 1.25 中缺失的 LASX 指令 WORD 编码、loong64 Go assembly SIMD optimization。
-
emmsixx Skill Lecture NotesTransform lecture materials (slides, PDFs, text snippets, transcripts, audio, or video recordings) into comprehensive, exam-ready Markdown notes for Obsidian. Use when the user provides lecture content, study materials, or asks to take notes, summarize lectures, or create study guides. Outputs structured notes with key concepts, definitions, LaTeX math, and exam-important callouts.
Audited -
erweixin Skill Render BenchRun RaTeX rendering performance benchmarks (100-formula PNG/SVG/PDF, cold-vs-hot font cache timing, phase breakdown). Use when profiling render performance or comparing before/after optimization changes.
-
esphome Skill Create Blog PostUse this if the user wants to convert a blog post from Google Docs markdown to the format used on the ESPHome website, or wants to publish an externally linked (crosspost) blog post that redirects to an article hosted on another site.
-
eternityspring Bundle Video Shots拉片:把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面。 分工刻在骨子里:**能量的都由代码量**(切点来自 ffmpeg 场景检测,时长是切点相减, 运动量是逐帧差分的中位数),模型只判断它真正该判断的那几件事(景别 / 类别 / 运镜 / 画面 / 节奏), 然后每一条判断都被代码当场对账——**声称推拉摇移却实测几乎不动,门直接拦**。 看片走联系表(每镜起手帧 + 收尾帧各拼一张大图,一屏二十几个镜头,a/b 对照就是运镜), 不是一张张翻。检测漏刀多刀用 recut 补刀并刀,自动重编号重算时长,手改边界过不了门。 产出 shots.json + Markdown 镜头表 + **单页交互式拉片报告**:内嵌播放器(播放时同步高亮镜头、 点镜头跳转)、镜头节奏带、可搜索可筛选可排序的镜头表(列表 / 卡片两种视图、首尾关键帧并排、 点图开大图)、景别类别运镜分布、出场人物、质量门、导出 JSON。单文件零依赖,离线双击能开。 15 道质量门全部由脚本确定性检查。 零依赖、零 API key,只要 node 和 ffmpeg。 Use when asked to 拉片、拆镜头、分析视频镜头、镜头时长、景别、运镜、镜头表、 video shot breakdown、shot list from video。
-
ethereumjs Skill Update Est FixturesUpdates EthereumJS execution-spec test fixtures from an ethereum/execution-specs release, then (after a human merge) points the monorepo submodule, updates VM npm scripts, reports a first test run, and implements ordered “what we need” items in two gated steps each. Use when the user asks to update EST, EELS, or execution-spec tests/fixtures, bump a fixture release, integrate a fixtures-repo change into the monorepo, or implement a “what we need” / Amsterdam spec-delta item from a first-round report.
-
extend-hq Skill Extend APIUse when writing code against the Extend document processing API or SDKs - building extraction, classification, splitting, parsing, PDF form-filling, or workflow integrations, authoring extraction schemas, or handling Extend webhooks - in Python, TypeScript, Java, or Go.
-
extend-hq Skill Extend CLIUse when extracting structured data from PDFs or images, parsing documents to text or markdown, classifying or identifying the type of a document (e.g. telling MSA from SOW from NDA), splitting multi-document bundles into segments, filling PDF forms via a values schema, detecting form fields to scaffold an edit schema, running multi-step document AI workflows, inspecting, watching, or listing Extend runs by ID (exr_, pr_, clr_, splr_, edr_, sgr_, workflow_run_), or uploading documents to an Extend workspace and managing the resulting file_xxx IDs - even if the user describes the task without naming Extend (e.g. "pull line items from these invoices", "OCR these receipts", "categorize this contract", "fill out this PDF form", or "split this combined PDF into individual statements").
-
cbetz Bundle Hcris AnalystAnswer questions about U.S. nonprofit hospital financials, beds, staffing, charity care, and community benefit by querying CMS Medicare Cost Reports (HCRIS) and IRS Form 990 Schedule H filings. Use when the user asks about a specific hospital's cost-report numbers, peer context across hospitals, the meaning of a worksheet/line/column code, the difference between related CMS and IRS charity-care reporting fields, or any analytical question over the trove project's published HCRIS+990 data bundles.
-
chantastic Skill Run Chan Dev ResearchCoordinate raw analysis and publish a normalized research entry into chan.dev's `src/content/research/`. Use when research should become a durable chan.dev report.
Audited -
charles1614 Bundle Paper ReaderRead AI/CS academic papers and generate detailed Chinese analysis reports in both Markdown and LaTeX formats. Use this skill whenever the user wants to analyze, summarize, review, or read an academic paper. Supports local PDF files and arxiv links. Triggers on: paper analysis, arxiv link, PDF paper review, academic paper summary, 论文分析, 论文阅读, 读论文, 分析论文.
-
chenshuo2004 Bundle Cs Web Slides制作精美、可交互的网页幻灯片,或把现有 PPT/PPTX 转成保留品牌图片资产的网页演示。适用于演讲、产品发布、路演、课程和网页化演示;不用于只需静态 PNG 或可编辑 PPTX 的任务。
-
chialin Bundle Weekly Budget ReportWeekly budget analysis report. Produces this-week spending, MTD vs. budget, YTD progress, next-week allowance, and AI recommendations; writes to a configured local folder. Trigger with `/weekly-budget-report`. Best run Sunday evening after daily bookkeeping.
-
chris-peterson Skill EndClose a work session: read what actually landed, refuse to close on work that isn't durable yet, record the deliverable on the tack route, hand off the retro, and report the commands still owed rather than sequencing them. Triggers on "wrap up", "all done", "close this out".
-
cjinhuo Skill Blog Markdown Format博客 Markdown 格式规范。当需要迁移、完善或生成博客文章时,必须调用此 skill 以确保符合 frontmatter 头部信息和 Markdown 语法规范。
-
clickblipclick Skill Ingest Resume HistoryUse when the user has dropped existing resume PDFs, markdown notes, or text files into inbox/ and wants to bootstrap or update content/master.yaml. Extracts text via bun run ingest, then reconciles into master.yaml with per-change reasoning and explicit approval.
Audited -
conorluddy Bundle Obsidian Github Issue FetcherFetch GitHub issues into Obsidian as markdown notes — turn your vault into an issue tracker with Dataview queries, tags, and graph view. Fetch issues as notes, GitHub issues in Obsidian, issue tracker in vault, Dataview issues dashboard. Four modes: `/obsidian-github-issue-fetcher` (fetch, default), `/obsidian-github-issue-fetcher status` (last fetch info), `/obsidian-github-issue-fetcher init` (configure vault path), `/obsidian-github-issue-fetcher --dry-run` (preview without writing). Also supports `--force` to re-fetch all issues regardless of changes.
-
consensys-incorporated Skill Author PageScaffold or draft new Teku documentation to editorial standards. Use when creating a new page, writing a first draft, or helping a contributor structure content correctly.
Audited -
consensys-incorporated Skill Style ReviewReview Teku documentation for editorial compliance (voice, terminology, formatting, content type, and workflow checks). Use before submitting a PR or when auditing pages.
Audited -
copilotkit Skill Openbot Data AccessGoverns how the OpenBot browser app reads and writes server data — every request goes through `client` in app/src/lib/client.ts, every read is a queryOptions factory in app/src/lib/<entity>/queries.ts, every write is a mutationOptions factory in app/src/lib/<entity>/mutations.ts, and components consume them through useQuery/useMutation. Use when adding or changing a screen that loads server data, calling a /api/... endpoint from the browser, adding a query key, writing a create/update/delete flow, deciding where a fetch belongs, or reviewing a diff that contains the word fetch under app/src. Don't use for server-side route handlers under server/ (that is not browser code), for form validation schemas (those live in lib/<entity>/form.ts), for page layout and Item rows, or for the AG-UI stream itself, which the runtime carries rather than the client.
-
correctroadh Bundle Harness LintUse when installing, configuring, migrating, authoring, debugging, or fixing `harness-lint` rules in a code repository. Covers command setup, shared/local rule packs, config upgrades, converting recurring feedback into local rules, writing rule Markdown/GritQL, inspecting a specific rule after lint failures, and fixing code without weakening rules.
-
anklecrusher Bundle Ppt Evidence PrepUse when preparing evidence for a PPT before slide creation: collect papers, manuals, webpages, patents, figures, quote screenshots, evidence matrices, manual crop briefs, and an evidence-linked PPT outline so the deck can be made later without re-searching sources.
-
ansys Skill DocWrite, review, or edit PyMechanical documentation. Use when writing reStructuredText (RST) files, Python docstrings, Sphinx configurations, example scripts, README files, or any doc content for the PyMechanical library. This covers NumPy docstrings, RST file formatting, Google developer style guide rules, Sphinx extensions, Vale linting, and content structure.
-
apcamargo Bundle Touying AuthorAuthor, refactor, and troubleshoot Typst slide decks built with Touying
-
aquasecurity Bundle Shell Style GuideEnforce Tracee shell standards with shellcheck and shfmt. Use when editing shell scripts, YAML run blocks, or shell code blocks in markdown.
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 ppt-evidence-prep, diy-yt-creator, vision. 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.