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.
-
lhohan Skill Check Til RulesUse this skill when reviewing TIL (Today I Learned) entries to verify they follow established content guidelines, including word count, focus, clarity of understanding, and non-blog format. Trigger on requests like check/verify/validate TIL rules, including prompts that say "today I learned" instead of "TIL".
-
liveblocks Bundle Write DocsWrite and review Liveblocks documentation, API reference, guides, and quickstarts. Use when editing files under docs/, documenting a new Liveblocks feature, updating API reference pages, adding docs routes, or reviewing documentation for clarity, discoverability, and consistency.
-
liyown Bundle MarknativeRender Markdown files to paginated PNG/SVG images using the marknative CLI. Use this skill whenever asked to convert, render, or export Markdown to image formats.
-
luohy15 Bundle AlphavantageAlpha Vantage API documentation reference - provides comprehensive information about stock data, forex, crypto, technical indicators, and fundamental data APIs.
-
lupynow Bundle Math Modeling Paper数学建模竞赛论文写作全流程指导。覆盖国赛(CUMCM)和美赛(MCM/ICM),从论文结构规划、各章节撰写、模型检验、参考文献规范到最终格式检查。与math-modeling-solver形成"解题→写作"配对——可接收solver输出的论文草稿片段直接展开写作。当用户提及数学建模论文写作、建模比赛、国赛/美赛/电工杯/亚太杯/深圳杯/华为杯论文、CUMCM、MCM/ICM、数模论文结构、摘要写作、模型检验、灵敏度分析、latex建模模板、word建模排版、Memo/Letter写作、模型命名、Our Work流程图,或需要写/修改/优化/检查建模论文的任何部分时,都必须使用此 skill。
-
lwmxiaobei Skill PDFProcess and extract content from PDF files
-
lynx-family Skill Generate Cdp SpecGenerate or check the Lynx DevTool CDP API reference from the authoritative generated manifest using packages/lynx-cdp/generate_cdp_docs.py, with mandatory Chinese translation after English generation. Use when asked to regenerate the CDP spec or refresh generated CDP documentation.
-
madeyexz Bundle Heptabase LinkingCreate real cross-links between Heptabase cards via the heptabase CLI. Use when the user wants to link Heptabase cards, cross-reference notes, build a card graph, or fix existing `[[Card Title]]` wiki-link text that is rendering as plain text instead of a clickable card pill. Real links require a ProseMirror `card` node written through `heptabase note save`; markdown paths (`note create`, `note append`) cannot create them. Triggers on: heptabase link cards, cross-link heptabase, heptabase cross-reference, heptabase cardId node, heptabase note save, heptabase prosemirror link, heptabase wiki link not working.
-
maimemo Bundle Memo API墨墨背单词 MaiMemo Open API skill for vocabulary learning. Handles: 单词 vocabulary lookup (voc_id), 释义 interpretations (CRUD), 助记 mnemonics/notes, 云词本 notepads/word lists, 例句 phrases/example sentences, 学习数据 study progress/review schedule/study records. Triggers on: 墨墨, maimemo, 背单词, 释义, 助记, 云词本, 例句, study progress, review schedule, words due, forgotten words, study time, export study data.
-
man-group Skill Update DocsCheck and update documentation for ArcticDB code changes
-
manymore13 Skill Report CLI研报查询下载工具。当用户需要查询、下载、分析行业研报、个股研报、策略报告、宏观研究、券商晨报时使用此 skill。
Audited -
manymore13 Skill Report CLI Simple研报查询下载工具(CLI版)。当用户需要查询、下载行业研报、个股研报、策略报告、宏观研究、券商晨报时使用此 skill。
Audited -
input-output-hk Bundle Agda Typecheck ProfileProfile Agda typechecking performance from a cold cache. Supports two modes — project-wide (via `agda --profile=modules`, reporting per-module times and ms-per-line) and single-module (via `agda --profile=definitions`, reporting per-definition times). Can drill from the project-wide report into specific slow modules, and can investigate individual slow definitions by recursively replacing subterms with holes to locate the true hotspot. Use this whenever the user wants to investigate why Agda typechecking is slow, find hot modules or definitions, benchmark typechecking, or hunt down a specific slow hotspot — even if they don't say "profile". Triggers on phrases like "why is Agda slow", "typechecking performance", "profile the build", "which module is slowest", "find the bottleneck", "why does this definition take so long".
-
intentee Skill Running CoverageRuns every test suite in the paddler workspace on the fastest available device, and produces code coverage report. Use when the user asks to run the code coverage, or to check the coverage.
-
intentionaut Bundle FamiliarWrite a newsletter issue about your own work, in your own voice. Familiar interviews you one question at a time, proposes three structures, drafts with a bracket over anything it cannot source, and hands back an editor's report you work through yourself. It also turns a finished issue into a week of social posts and schedules the ones you approve. Every stage stops and waits for you; nothing is applied to your draft and nothing is scheduled without a confirm. Use when the user says 'familiar', wants to start a piece or be interviewed about an idea, has a draft they want read or improved, wants an issue turned into posts, wants approved posts scheduled, or wants Familiar taught their voice. Not for a product requirements doc or feature spec; use `product-brief`. Not for a decision record; use `decision-log`. Not for reflecting on how the week felt; use `weekly-reflection`.
-
itsryanlenk Bundle HumanistImprove an AI-assisted draft so it reads better: strip machine residue, cut filler and inflated significance, and report what is left. Use when someone wants to clean up an AI-assisted draft, edit AI output into publishable prose, remove AI slop, fix corporate or robotic voice, tighten a draft before it ships, or asks why their writing sounds generic. Trigger phrases include "clean up this AI draft", "edit this into something publishable", "remove the AI slop", "this reads like ChatGPT wrote it", "why does this sound robotic", "tighten this before it goes live", "make this draft less generic". Runs a rewrite pass, a mechanical checker that reports and never edits, and a composition read for the tells no regular expression catches. Also covers quoted sources, web-copy extraction, and calibrating the checker to the author's own published voice. It does NOT detect whether text was AI-generated, does NOT make writing pass as human, and does NOT defeat AI-detection or watermarking.
-
ivy-interactive Skill Generate Stack HashGenerate a one-line, similarity-preserving Stack Descriptor Hash (SDH) for a repository. Clones the repo, runs the Ivy.StackAnalyzer CLI to get a factual stack report, then maps it to the canonical hash. Use when the user types /generate-stack-hash <repo-url> or asks for a stack hash / stack signature of a repo.
-
jackwener Bundle Grading BackendGrade a team's backend implementation against its spec on 9 weighted dimensions, producing a markdown report + JSON summary with evidence.
-
jakubrohleder Bundle HevyCreate workout routines in Hevy fitness app. Converts training programs (text/PDF/image) to Hevy JSON format via CLI. Look up exercise IDs, build routine JSON, create via API. Use when: creating gym routines, importing workout plans, looking up exercise IDs, building workout JSON, converting programs (PPL, 5x5, 531, GZCLP, nSuns, Starting Strength, PHUL, PHAT, Upper/Lower, Full Body), syncing to Hevy, or any Hevy API task. Keywords: fitness app, workout tracker, routine builder, gym program, strength training, hypertrophy, exercise database, training log, weightlifting, bodybuilding User-invocable: /hevy
-
jancbeck Bundle Md To PDFConvert markdown files to well-formatted PDF. Use when the user wants to export, render, or convert a .md file to PDF.
-
janklan Skill Jk Docs ReviewVerify project documentation against reality and report findings for review
-
jcardif Bundle MarkdownlintEnsures style consistency and correctness in Markdown files using markdownlint-cli2. Use whenever creating, updating, editing, or reviewing any Markdown (.md) file. Triggers on any task that creates or modifies .md files, including README.md, CHANGELOG.md, documentation, or any file with a .md extension. Also triggers when the user mentions markdown, linting, markdown formatting, markdown style, or markdownlint. Always run the linter after writing or editing markdown content — do not skip this step.
-
jcardif Bundle Scientific PaperWrites and edits scientific and academic papers in LaTeX following rigorous research methodology. Use when the user asks to write, edit, expand, structure, or review any academic paper, research paper, technical report, or LaTeX document. Triggers on mentions of papers, LaTeX, .tex files, abstracts, literature reviews, methodology sections, theorems, proofs, citations, or BibTeX. Covers the full research lifecycle from problem formulation through publication-ready output.
-
jeasonstudio Bundle Slides RevealjsUse when creating or updating presentation decks with reveal.js, including setup, slide authoring, plugins, animation, navigation, and export.
-
jezweb Bundle Build Plan PackTurn a construction job folder (PDF plan sets, engineering, approvals, specs) into a queryable plan pack — synthesised sheet register, object database with provenance+confidence, takeoff quantities with shown workings, topic wiki, per-sheet renders. Use when asked to "build a plan pack", "index these plans", "do a takeoff", or process a folder of construction drawings for AI querying.
-
jezweb Skill Onboard Trade ClientTurn a trade business's existing files (past plans, quotes, price data) into a calibrated planpack workspace, ending with a trust report that re-quotes their own past jobs blind. Use when onboarding a trades business to planpack, processing a back-catalogue of past jobs, or asked to "set up my business on planpack".
-
jiadizhunine Bundle Suda ThesisUse when generating or editing Suzhou University undergraduate thesis DOCX files, including 苏州大学论文, 苏大毕设, 毕业论文, 论文正文, 文献综述, 文献翻译, 任务书, 中期检查, literature review, literature translation, task book, midterm-check forms, or Chinese academic DOCX formatting that must follow Suzhou University thesis style.
-
jigx-com Bundle Jigx AcumaticaUse when building Jigx apps that integrate with Acumatica ERP, including REST and OData functions, Acumatica config values, acuerp access tokens, .value payload wrappers, lookup sync, expand selection, local-first sync, command queue retry, file uploads, PDF attachment, and service order submission.
-
jihe520 Skill PDFProcess PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.
-
jiotv-go Skill Change ConfigurationAdds or changes JioTV Go configuration options consistently across schema tags, defaults, example files, documentation, consumers, and tests. Use when adding, renaming, removing, defaulting, or changing behavior of a JIOTV_* environment variable or JSON, YAML, or TOML config key.
-
jlevy Skill MarkformMarkdown-based form system for structured data collection by AI agents and humans. Inspect, fill, validate, and export .form.md files with typed fields and role-based workflows. Use when working with .form.md files, filling forms, validating fields, exporting data, or when the user mentions markform, forms, form filling, structured data, or field validation.
-
joaniberian9588 Bundle Paper PDF DownloadSilently batch-download research-paper PDFs by DOI from major publishers using authorized open, institutional, campus, library, or publisher-API access. Verifies the requested main article, rejects supplements, records challenge/auth states, resumes batches, and can hand verified PDFs to the optional paper-pdf-to-markdown skill. Use when the user asks to download, fetch, save, or batch-retrieve paper PDFs or DOI lists.
-
johnnydecimal Skill JdexRead and write to the user's JDex — their Johnny.Decimal index. Use this skill whenever the user mentions their JDex, asks to check, fetch, or update their own documentation, references a Johnny.Decimal ID (e.g. 12.34, W0189), invokes you from a folder with an ID in its name, asks to find a file or document, asks where a document belongs in their JD system, or asks a factual question about their own life or business (e.g. "where does X money go?", "what's the process for Y?", "trace where Z ended up"). The JDex is their knowledge base — treat any investigative or research question about their own information as a JDex lookup first.
-
jordancoin Skill DocmapNavigate markdown, PDF, and YAML documentation structure without reading full files. Use before opening any large .md file, to locate specific constructs (code blocks, callouts, tables), to jump to a line number's context, or to see what changed in docs since a git ref.
-
joshfng Skill RtfmRead the project's own documentation before planning, answering, or writing code. Use when the user says "rtfm", "RTFM", "read the manual", "read the docs", or "check the docs", and before starting any task in a repo that carries a docs/ directory.
-
jovd83 Bundle Example Weather FetcherExample fixture skill bundled with skill-vetting-reporter. It fetches a public weather forecast for a city and returns a one-line summary. It exists only to demonstrate what a vetting report looks like — including a deliberate false positive — and is not meant to be installed or used for real work.
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 slides-revealjs, check-til-rules, write-docs. 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.