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.
-
theveller Bundle To CmsIngest a content package (markdown/archive) into Notion Publisher CMS rows ready for button publish. Auto-detects Layer/Source Tags/Channels from package frontmatter, calling producer skill cms: contract, or heuristics. Never calls publish webhooks. Triggers: /to-cms, "ingesta al CMS", "manda a Notion Publisher".
-
blink-new Bundle Watch VideoAnalyze any public video URL (Loom, YouTube, etc.) and produce a vivid, engineer-grade report of what was shown and said. Use when a user shares a Loom, YouTube, or other video URL and wants it analyzed, summarized, transcribed, or understood by an AI — without needing to watch it themselves.
Audited -
blink-new Bundle Wysiwyg EditorBuild production-grade WYSIWYG editors using Tiptap v3 with proper markdown-style formatting, instant rendering, and bullet/numbered list support
-
jimweller Skill LlmdocsUpdate project documentation (CLAUDE.md + .llmdocs/). Use after significant work to keep docs in sync.
-
jimweller Skill ArcheologyBuild an evidence-based historical report to answer questions. Use when the user asks for archeology, detective work, historical timeline, or historical record.
-
jimweller Skill Review DiffReview every change on this branch against main across 9 perspectives in parallel. Covers committed, staged, unstaged, and untracked work. Returns one consolidated report.
-
kukucaicndy Bundle Easyeda APIEasyEDA Pro API skill for AI agents. Use when working with EasyEDA Pro EDA software, including PCB design, schematic editing, footprint/symbol management, and project operations. Supports live debugging in EasyEDA and EasyEDA extension development. Provides complete API reference (120+ classes, 62 enums, 70 interfaces), extension-development documentation, and a WebSocket bridge server to execute code in the running EasyEDA Pro client. Trigger on: "嘉立创EDA,启动!", "立创EDA,启动!", "EDA,启动!", "EasyEDA", "PCB", "schematic", "footprint", "EDA", "circuit board", "嘉立创EDA", "原理图", "PCB设计". **IMPORTANT**: 嘉立创EDA's English name is **EasyEDA**. They are the SAME product. Never use other transliterations like "EasyEDA Pro" (unless specifically versioned), "EASYEDA", "easyeda", etc. Always use "EasyEDA" for English references and "嘉立创EDA" for Chinese references.
-
marcellourbani Skill Run ScriptsStandalone Phase 7 of SAP UI testing. Rediscovers the configured test folder, program/specs, test cases, prepared data, and target system from disk; then runs Playwright via SAP Testing tools, generates .docx evidence, and diagnoses test script failures. Use when the user asks to execute tests, run TC-XXX, generate evidence, or debug a failed test.
-
marcellourbani Skill Abap Code Review HelperRequirements for ABAP code to avoid mistakes that pass syntax checks but cause wrong results, dumps, lost updates, or slow processing. Use when writing, changing, refactoring, debugging, or reviewing reports, classes, function modules, enhancements, BAPIs, interfaces, and any other ABAP objects. Covers old values left in loop variables, SELECT and FOR ALL ENTRIES, binary search, parallel cursors, duplicate keys, conversions, commits, locks, and retries. Report problems, not lists of passed checks.
-
markuplint Skill DocDocumentation policy — JSDoc-first; no code-derivable markdown. Use when writing or reviewing any repository documentation (JSDoc, README, markdown) or deciding where a piece of documentation belongs. Trigger keywords: documentation, JSDoc, README, markdown policy, docs, comment policy.
-
markuplint Skill IssueAnalyze or create a GitHub Issue and build a TDD resolution plan. Use when given an Issue URL to work on, or when a problem report needs to be filed as an Issue first. Trigger keywords: issue, GitHub issue, file an issue, fix issue, resolve issue, issue triage.
-
markuplint Skill Product ManagerAnalyze, review, and generate documentation for any repository from a Product Manager (PdM) perspective. Language- and framework-agnostic — works with any repository. Use this skill whenever you need to: understand repository structure, read and navigate code, analyze dependencies, generate or review READMEs and documentation, summarize the tech stack, evaluate architecture, assess operational impact of new features, or review PRs. Responds to requests like "what's going on in this repo?", "write a README", "review this change", "is this maintainable?", "what do you think of this PR?". If the task involves repository analysis, review, or documentation, use this skill without hesitation.
-
mrlyk Bundle To CoderGenerate a developer-facing efficiency and focus-area report for a completed Superharness task. Use when the user asks to "生成开发者报告", "开发交接报告", "to-coder", "developer report", or when /superharness:to-coder is invoked.
-
spillwavesolutions Skill Dekc Design ReportUse the DEKC second brain to design a new report/dashboard from existing metrics, gold tables, business objects, and glossary.
-
thinkfleetai Skill ExportExport MemMesh memories for a project/user to a portable Markdown (or JSONL) file for backup, migration, or sharing. Use when backing up, moving to another project, sharing memory state with teammates, or archiving before a cleanup.
-
tradeinsight-info Skill Sentiment ReportThis skill should be used when the user asks for a full sentiment report, comprehensive sentiment analysis, complete sentiment summary, sentiment check, overall market mood, how sentiment looks, or explicitly runs /sentiment-report for a publicly traded company. Also use when the user asks to "analyze sentiment", "run sentiment analysis", or "give me a sentiment overview" for a stock.
-
tradeinsight-info Skill Sec Filing ReaderThis skill should be used when the user asks to read a 10-K, summarize a 10-Q, read an SEC filing, find a proxy statement, look up a DEF 14A, read an 8-K, summarize annual report, read quarterly report, check SEC filings, or look up Form 4 for a specific company or insider.
-
tradeinsight-info Skill Fundamental ReportThis skill should be used when the user invokes "/fundamental-report" followed by a stock ticker. Generates a comprehensive fundamental analysis research note at summary depth covering all 14 analysis areas with key metrics, signal rating, cross-validation, and investment thesis arguments.
-
tradeinsight-info Skill Fundamental Report DetailedThis skill should be used when the user invokes "/fundamental-report-detailed" followed by a stock ticker. Generates a comprehensive fundamental analysis research note at detailed depth covering all 14 analysis areas with full data tables, multi-year trend analysis, and extended commentary.
-
turntuptechnologies-ai Bundle Write ReadmeREADME を新規に作る、または既存の README を実証済みの構成で整え直すとき。「README を書いて/整えて」「README が薄い・構成を揃えたい」等で使う。概要/Stack/Quick start/Configuration/Layout/Documentation/Development/License の構成で、実装から裏を取って書く。
-
vesely Bundle Code StyleAlign recently written or changed code so it matches the surrounding project's established conventions — formatting, naming, imports, comments, and idioms — learned from the codebase itself, then apply the fixes. Use this whenever the user wants their changes to "match the codebase / our conventions / the rest of the app", asks to make a diff or PR style-consistent, wants a style pass or style review before opening a PR, says code "feels off" or inconsistent with the project, or invokes /code-style. Works in any language or framework — it discovers the rules from the repo rather than assuming them. Reach for this even when the user doesn't say the word "style" but clearly wants new code to blend in with existing code. Also covers de-slopping AI-generated artifacts from the diff — over-commenting, defensive checks or try/catch abnormal for the code path, casts to any / type-ignore escape hatches, needless nesting — so use it when the user says "remove AI slop", "de-slop", "this looks AI-written", or wants AI a
-
vesely Bundle Share FileUpload a local file to private R2 temp storage and get back a public direct URL that auto-expires. Use when you need to host a screenshot, screencast, GIF, PDF, log or any artifact so it can be embedded in a PR description, pasted into Slack/Linear, or shared as a preview link — anything you would previously have sent to catbox, 0x0.st or an image host. Triggers on "upload this", "share this file", "host this screenshot", "get me a link for", "put this in the PR", "temp storage", "shareable link", "nahraj tohle", "sdílený odkaz". Default retention 90 days, customizable per upload.
-
qualcomm Bundle Ppt GenGenerate fully editable, high-quality PPTX with python-pptx based on the user's topic, materials, or business goals; defaults to a general-purpose "dark gilded elegant" visual system, with adaptive layout capabilities for cover, table of contents, section/transition, viewpoint statement, image-text mixed layout, multi-card, columns, data, workflow, timeline, comparison, case study, quote, summary, and ending pages.
-
rshade Bundle Tech DebtSystematic technical debt analysis across architecture, testing, documentation, and infrastructure. Investigates the codebase, scores findings by impact and effort, and generates a prioritized TECH_DEBT.md remediation plan. Delegates to specialized skills for code quality (scout) and linting (lint-fix). Use when assessing overall project health, planning cleanup sprints, or onboarding to an unfamiliar codebase.
-
rshade Bundle Cost DriftDrift analysis for Pulumi infrastructure costs. Runs finfocus to compare actual vs projected spend, flags drifting resources against configurable thresholds, generates likely-cause explanations with investigation prompts, and tracks drift trends over time. Produces a terminal summary and COST_DRIFT.md report. Use when investigating cost overruns, validating projections against reality, or monitoring spend drift in CI.
-
rshade Bundle MarkdownlintValidate markdown files against formatting standards. Auto-detects and installs markdownlint-cli if missing. Checks project config or falls back to sensible defaults. Supports auto-fix mode. Use when creating or modifying markdown files, validating documentation, or enforcing markdown conventions.
-
saschb2b Bundle BreadcrumbsHeal codebase understanding gaps exposed during implementation, debugging, or investigation. Use when tracing reveals misleading names, repeated backtracking, disconnected navigation paths, hidden contracts, surprising dependencies, stale documentation, unclear errors, undocumented constraints, false leads, or avoidable complexity. Make the smallest durable improvement at the source through clearer code, types, validation, tests, errors, comments, or existing documentation. Also use when a task was harder to grasp than it should have been or you think "that should have been documented." Do not create a breadcrumb trail, investigation log, freshness system, or separate knowledge store.
-
shalintripathi Skill DiagnoseUse to collect a bug-report diagnostic - "diagnose", "collect debug info", /organic-os:diagnose. Prints a report the user can paste into an issue; never transmits it anywhere.
-
somnio-software Bundle Dora MetricsFetches the DORA metrics Deployment Frequency and Lead Time for Changes, per project and per repo, from GitHub (API, not local git). Use this skill whenever the user asks to run or update the DORA metrics, measure the deployment frequency or lead time of a project (e.g. "Example Project"), generate the biweekly metrics report, or asks how many deploys a project made or how long a change takes to reach production. Also trigger on phrases like: "run the DORA metrics", "metrics for Example Project", "deployment frequency for [project]", "lead time for [project]", "biweekly metrics report", "how many deploys did we do this sprint".
-
dcouple Skill InvestigateInvestigate broken behavior using the shared evidence-driven method, scaling from a normal root-cause pass to a deep falsifiable experiment loop.
-
dcouple Skill Sentry LoopOn-demand Sentry triage loop - sweep every project's errors over a time window, classify each issue (new / recurring / regressed, user-impacting / zero-user, real / noise), root-cause only the clusters that matter, file findings into the work tracker under the loop's label, and annotate Sentry so the state sticks. Use when the user asks to run the sentry loop, triage Sentry, "what's new in Sentry", or wants a period's errors root-caused. Report-only - fixes go through /create-brief then /do.
-
dcouple Skill Web ResearcherResearch external documentation, libraries, and best practices with cited findings for the /do plan stage.
-
eai-org Skill Self ReviewSelf-review a changeset until merge-ready — a fresh-context reviewer checks it as a maintainer would, the author answers every finding, and a compact report for the PR proves the review happened.
Audited -
eai-org Skill Check Ticket ImplementationCheck how much of a ticket is already implemented — split it into requirement blocks, judge each against the code, and save a human-readable TICKET-STATUS report in the planning dir.
Audited -
educlopez Bundle Ps TranslateAutomatiza la detección y traducción de strings sin traducir en una instalación PrestaShop, a CUALQUIER idioma. Detecta el child theme y los locales instalados (DB ps_lang con fallback a filesystem/lando mysql), escanea templates .tpl (Smarty {l s='...' d='...'}) Y, con --include-emails, plantillas de email Twig (mails/themes/**/*.twig), incluyendo también las facturas/albaranes PDF de la raíz /pdf/**/*.tpl que antes se pasaban por alto. Compara contra los XLF existentes del locale objetivo y traduce los strings faltantes usando Claude de forma nativa — sin API key externa. Soporta varios idiomas en una sola corrida. Usa esta skill cuando el usuario mencione: "traducciones PS", "strings en inglés", "ps-translate", "traducir prestashop", "traducir a francés/alemán/español", "i18n pendiente", "hay textos sin traducir en la tienda", "¿qué strings faltan por traducir?", "traducir facturas/PDF", "traducir emails/correos de PrestaShop", o cuando vea texto sin traducir en el storefront, en una factura PDF, o en un e
-
educlopez Bundle Ps Invoice PreviewGenerates a local invoice PDF viewer for PrestaShop projects, deployed as invoice-preview/index.php (subfolder, ROOT = dirname(__DIR__)). Lists the last 50 orders (searchable by reference/customer/id), renders the real PDF invoice for any order straight from classes/pdf/HTMLTemplateInvoice.php + pdf/*.tpl (respecting any themes/{child}/pdf/*.tpl override PS itself resolves) inline in the browser via an iframe, with a "Generar factura" button for orders that don't have one yet. Zero placeholders to fill in — admin dir, Lando URL, DB credentials and shop name are all auto-detected at runtime from config/parameters.php and the PS_SHOP_NAME configuration value. Gated behind backoffice employee auth (Cookie class, always denies on failure). Geist-font UI matching the ps-email-preview visual style. Use this skill whenever the user wants to preview, inspect, or debug PrestaShop invoice/receipt PDF templates without going through the backoffice order page each time, asks "cómo se ve la factura", "quiero ver el PDF de
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 to-cms, watch-video, wysiwyg-editor. 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.