Docs & writing
16,614 rows, by stacks then stars
3,030 of these skill files have been read, by 1,951 distinct authors, and what they tell an agent counted. What Docs & writing authors agree on, and what they forbid
aoli0919/learn-anything-skills/skills/thread-writer Skill
0★ repoTurn a concept or project into a concise social thread with hook, steps, proof, and caveats.
K95M65/AI_ONBOARD/skills/changelog Skill
0★ repoAssemble release notes / a CHANGELOG entry from Conventional Commits since the last tag. Use when cutting a release or updating CHANGELOG.md. Pairs with the conventional-commit skill.
K95M65/AI_ONBOARD/skills/cloudflare/workers-best-practices Skill
0★ repoReviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
The same file is in 5 other repositories
K95M65/AI_ONBOARD/skills/data-storytelling Skill
0★ repoTurn analysis into a clear, persuasive narrative for a decision-maker — message hierarchy, executive structure, and honest communication. Use when presenting findings, writing a brief or memo, or building a deck from data. Pairs with dataviz.
K95M65/AI_ONBOARD/skills/obsidian Skill
0★ repoRead and write notes in an Obsidian vault — markdown with wikilinks, tags, YAML frontmatter, daily notes, and folder conventions. Use when creating, linking, or organizing notes in an Obsidian vault, or building a note from a template.
K95M65/AI_ONBOARD/skills/retrieve-technical-docs Skill
0★ repoRetrieves version-matched, current technical documentation and release evidence for libraries, frameworks, APIs, protocols, and developer tools. Use when implementation depends on unstable or unfamiliar APIs, migration details, exact configuration, deprecations, or current best practices; do not use for general market research, product recommendations, or repository facts already available locally.
K95M65/AI_ONBOARD/skills/swift-api-design-guidelines Skill
0★ repoWrite, review, or improve Swift APIs using Swift API Design Guidelines for naming, argument labels, documentation comments, terminology, and general conventions. Use when designing new APIs, refactoring existing interfaces, or reviewing API clarity and fluency while preserving source compatibility requirements.
EnosElinsa/mec-paper-writing-skills/skills/writing-mec-methods Skill
0★ repoUse when drafting, revising, or auditing a Method, Proposed Algorithm, or Solution section for MEC, UAV-MEC, HAP-UAV, vehicular edge/fusion, dispersed computing, or related optimization papers, especially when the solver is a population-based evolutionary algorithm or reinforcement learning method and the section lacks model-to-algorithm closure, clear novelty boundaries, constraint semantics, executable pseudocode, deployment details, or defensible complexity analysis.
EnosElinsa/mec-paper-writing-skills/skills/writing-mec-related-work Skill
0★ repoUse when drafting, revising, or auditing a Related Work section for MEC, UAV-MEC, HAP-UAV, vehicular edge/fusion, dispersed computing, or constrained multi-objective optimization papers—especially when the section reads like a paper-by-paper bibliography, repeats the Introduction, uses an arbitrary taxonomy, overexplains citations, or fails to derive the scenario/model/algorithm gap from grouped evidence.
EnosElinsa/mec-paper-writing-skills/skills/writing-mec-system-models Skill
0★ repoUse when drafting, revising, or auditing the System Model and Problem Formulation of MEC, UAV-MEC, HAP-UAV, vehicular edge/fusion, dispersed computing, service migration, or constrained/dynamic multi-objective optimization papers—especially when the model lacks a causal workflow, symbols appear before definition, state transitions are incomplete, constraints are detached from physical meaning, the formulation does not match the preceding model, or a rewrite unnecessarily redesigns an established reference architecture.
tejask0/agent-skills/event-radar Skill
0★ repoScan configured local + online event platforms, find events genuinely worth the user's time based on their configured interests, rank them by VALUE, and deliver a dated ranked markdown report. Trigger on "find events", "event radar", "what should I attend", "scan events", "/eventradar". On first run it asks the user for their location and interests and saves them to config, so it never needs to ask again. Interests are entirely user-defined — professional (AI, agents, LLMs, startups, hackathons, ...) or recreational (book clubs, philosophy salons, film, fitness, ...), any mix. Covers in-person events in the user's city plus online.
tejask0/agent-skills/mobi-to-markdown Skill
0★ repoUse when converting a MOBI, AZW3, or EPUB ebook into a clean Markdown note (e.g. for Obsidian) — covers Calibre ebook-convert, why pandoc produces HTML soup, adding YAML frontmatter, and promoting chapters to headings.
chroline/oliver/skills/oliverspec/oliverspec-scope Skill
0★ repoScope an OliverSpec PRD + TRD into Linear tickets with clear descriptions, acceptance criteria, and explicit blockedBy/blocks relations. Use after oliverspec-propose when the user wants to scope, /oliverspec scope, or oliverspec-scope. Does not write proposal docs to the git repo.
Hedy-Alan/claude-5-step-dev/dev-integration Skill
0★ repo开发流水线第 5 步:联调与文档。前后端端到端联调、按契约裁决不一致、修复缺陷, 然后产出 README、部署文档、联调报告,完成整个开发闭环。 触发词:联调、前后端联调、集成测试、写文档、收尾、交付。 输入前四步的全部产物,产出 docs/dev/04-integration-report.md + README + 部署文档。
trugurpala/divan/plugins/core-pack/skills/writing-plans Skill
28 days old0★ repoUse when you have a spec or requirements for a multi-step task, before touching code
The same file is in 141 other repositories
trugurpala/divan/plugins/core-pack/skills/writing-skills Skill
28 days old0★ repoUse when creating new skills, editing existing skills, or verifying skills work before deployment
The same file is in 91 other repositories
trugurpala/divan/plugins/react-pack/skills/writing-guidelines Skill
28 days old0★ repoReview docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".
The same file is in 56 other repositories
ahtishamshahzad/agent_dev_flow/.ai/skills/database/document-schema-design Skill
0★ repoUse to design MongoDB document schemas — embed vs reference decided per access pattern, document identity and shape per collection, growth-bounded arrays, duplication with consistency ownership, and schema validation despite "schemaless."
ahtishamshahzad/agent_dev_flow/.ai/skills/documentation Skill
0★ repoUse to write or update documentation in the right canonical place, concisely, without duplicating the system. Keeps adapters thin, records decisions and their reasons, and archives stale generated content.
ahtishamshahzad/agent_dev_flow/.ai/skills/web/dashboard-reporting Skill
0★ repoUse to plan dashboard reports and charts — server-side aggregation, date-range/filter state in the URL, chart library evaluation, CSV/PDF export, scheduled reports, and handling slow queries (async generation, caching). Numbers must be verifiably correct before charts get pretty.
lzx-Bill/Project-Factory-Core/.agents/skills/data-api-design Skill
0★ repoUse when modeling entities, writing schema docs, designing APIs, defining state machines, or keeping data and API contracts consistent. Trigger when user says "data model", "schema", "API design", "state machine", "entity relationship", "database schema", "API contract", "endpoint", or when moving from architecture to implementation-ready data contracts. Coordinate with architecture-decisions for module boundaries and with prompt-authoring for API consistency.
lzx-Bill/Project-Factory-Core/.agents/skills/history-sync Skill
0★ repoUse when updating changelogs, decision logs, archives, document history, or writing back requirement, research, architecture, prompt, acceptance, and task changes. Trigger when "implementation feedback" reveals a design gap, when "research结论" contradicts earlier assumptions, when "design changes" affect downstream docs, or when user asks to "update history", "log decision", "archive old version". This skill should be used proactively — do not let design changes go unlogged.
lzx-Bill/Project-Factory-Core/.agents/skills/plain-language-handoff Skill
0★ repoUse when generating a plain-language project summary that anyone can understand — "generate plain summary", "create readable handoff", "non-technical summary", "全员可读概要", "通俗交接文档". This skill compiles a comprehensive yet accessible document from project design docs, written in everyday language that serves both human stakeholders (no technical background needed) and AI agents (complete enough for full design and implementation). Output: implementation-kit/PLAIN-LANGUAGE-SUMMARY.md
lzx-Bill/Project-Factory-Core/.agents/skills/prompt-authoring Skill
0★ repoUse when writing structured implementation prompts, packaging context for AI coding, mapping prompts to tasks, or refining prompt granularity. Trigger when user says "write a prompt", "implementation prompt", "handover prompt", "context packaging", "task prompt", "decompose into prompts", or when moving from delivery-planning to actual prompt generation. The output goes into prompts/ directory. Coordinate with data-api-design for API consistency and with acceptance-design for prompt-to-acceptance mapping.
lzx-Bill/Project-Factory-Core/.agents/skills/stage-review Skill
0★ repoUse when reviewing any project document against a checklist — "review this stage", "check my output", "self review", "自审", "质量检查". This is a GENERAL document review skill usable by any pipeline (express-incubate or gradual). It reads a document, runs a checklist, produces a structured review report with PASS/FAIL per item, and auto-fixes simple gaps. NOT for user-facing code review — for project factory document quality.
Zwin-ux/kit/packages/core/tests/fixtures/valid-add-readme Skill
0★ repoCreate a clear README for a new project.
Zwin-ux/kit/skills/add-readme Skill
0★ repoCreate a clear README for a new or existing project.
Zwin-ux/kit/skills/api-docs Skill
0★ repoDocument a library or service API with clear usage examples.
Zwin-ux/kit/skills/changelog Skill
0★ repoWrite a clear changelog entry for a release or notable change.
Zwin-ux/kit/skills/write-tests Skill
0★ repoAdd focused tests for important project behavior.
Paldom/promptimize/skills/write-agent-goal Skill
0★ repoDrafts or fixes the goal text for an autonomous agent run (/goal, unattended sessions) - checkable success conditions, evidence requirements, scope and permission limits, retry and budget exits. Use when writing an agent goal, run definition of done, or run success criteria, or when a goal gets gamed or marked done early. Not for generic project goals, prompt rewrites, or loop runtime design.
cekrauseee/harness/skills/harness-docs-audit Skill
0★ repoAudit versioned developer documentation and HTML artifacts for structure, routing, broken links, size, accessibility, external dependencies, drift, duplication, and Harness boundary violations. Use when reviewing README.md, docs/, module docs, or docs/artifacts, or before publishing documentation changes.
cekrauseee/harness/skills/harness-docs-init Skill
0★ repoCreate or repair the concise, English, versioned developer documentation baseline for a repository. Use when a project needs a README, documentation index, project overview, architecture guide, development guide, module documentation structure, or artifact index without overwriting existing content.
cekrauseee/harness/skills/harness-docs-maintain Skill
0★ repoMaintain concise, canonical, English developer documentation in README.md and docs/. Use when documenting a project change, architecture, module, setup, command, workflow, contract, or stable decision, or when reorganizing documentation and removing stale or duplicate guidance.
cekrauseee/harness/skills/harness-review Skill
0★ repoReview code, documentation, commits, or pull requests read-only and report evidence-backed actionable findings classified P0-P3. Use when a user asks for a review, audit of a diff, risk assessment, or validation of proposed changes; apply fixes only when separately requested.
Syncfusion aspnetmvc markdown converter
syncfusion/aspnetmvc-ui-components-skills/skills/syncfusion-aspnetmvc-markdown-converter Skill
no license0★ repoGuides implementation of the Syncfusion ASP.NET MVC Markdown Converter (Syncfusion.EJ2.MVC5). Use this skill when the user needs to convert Markdown text to HTML, use the MarkdownConverter utility, configure MarkdownConverterOptions (async, gfm, lineBreak, silence), or integrate the Markdown Converter with the Syncfusion Rich Text Editor for live preview or side-by-side editing in ASP.NET MVC. Trigger when user mentions markdown to HTML conversion, MarkdownConverter, toHtml, markdown preview, or RTE markdown mode in an ASP.NET MVC project.
ebal/AI-Skills/conventional-changelog Skill
no license0★ repoKeep a Changelog v1.1.0 format for maintaining CHANGELOG.md files. Use when creating, updating, or reviewing changelogs. Covers the standard categories (Added, Changed, Deprecated, Removed, Fixed, Security), Unreleased tracking, version dating, yanked releases, and anti-patterns. Trigger when the user says "update changelog", "write changelog", "release notes", or needs help maintaining a project changelog.
ebal/AI-Skills/conventional-readme Skill
no license0★ repoStandardized README.md structure and best practices based on makeareadme.com. Use when creating, rewriting, or reviewing project READMEs. Covers all standard sections (description, installation, usage, contributing, license), badge guidance, writing style, and common mistakes. Trigger when the user says "write a readme", "improve readme", "readme review", or needs help documenting a project.
ebal/AI-Skills/linux-system-audit Skill
no license0★ repoPerform a comprehensive, read-only, secret-safe audit of an authorized Linux physical server, virtual machine, VPS, cloud instance, or container host, locally or over SSH. Discover system identity, hardware, storage, networking, firewall, SSH, TLS, services, scheduled jobs, Docker or Podman workloads, Compose projects, mail, databases, monitoring, VPNs, logs, and backups, then produce a prioritized Markdown report. Use for requests such as audit this server, VPS report, Linux inventory, system report, migration inventory, security review, or generate a report for a hostname. Do not use for exploitation, active scanning, automatic remediation, or configuration changes.
Gusen1453/creed/skills/tdd Skill
0★ repoUse when implementing any feature, bug fix, refactor, or behavior change — before writing production code. Enforces red-green-refactor (failing test first, watch it fail, minimal code, refactor). Complements test-design (what to assert) with the TDD rhythm (when to write code).
Gusen1453/creed/skills/test-design Skill
0★ repoUse when writing, reviewing, or modifying unit/integration tests, adding test cases, assertions, or mocks, or deciding whether a piece of code is worth testing — especially when tempted to add tests for coverage, over-mock dependencies, or write formalistic tests that just restate the implementation.
Gusen1453/creed/skills/write-plan Skill
0★ repoUse when you have an approved design or clear requirements for multi-step work, before touching production code — break the work into bite-sized TDD tasks with exact files, interfaces, and verification steps.
danielleit241/hs-skills/skills/docs-seeker Skill
0★ repoSearching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel
danielleit241/hs-skills/skills/repomix Skill
0★ repoPackage entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.
wangyu16/orz-claude-plugin/skills/orz-paged Skill
no license0★ repoAuthor and edit single-file, self-editing .paged.html print documents (orz-paged). Use when a user wants to turn Markdown into a paginated, printable document — one portable HTML file that, in any browser, shows the text as real print pages on light paper (paged.js), is edited in-browser, and exports to PDF by printing (Ctrl/Cmd+P → Save as PDF). Covers the document settings block, templates (article, report, exam, letter, cover-letter, three CV styles, note), the curated document elements (title sections with multi-author/affiliation/ORCID support, abstract, toc, letter and CV parts, exam questions), a dynamic switch (print several versions from one source, e.g. an exam with or without its answer key), page breaks, and print-first content guidance.
The same file is in 1 other repository
wu1chenghui/hermes-math-template/skills/document-parser Skill
no license0★ repoParse any document (PDF, DOCX, PPTX, XLSX, PNG, JPG, HTML, web pages) into LLM-readable Markdown via MinerU. Use when the user asks to read, analyze, extract, or convert content from a document — regardless of format. Supports 80+ languages, table/formula/OCR recognition.
wu1chenghui/hermes-math-template/skills/lean-4-proof-writing Skill
no license0★ repoGuide for writing Lean 4 proofs — tactics reference, common proof patterns, and standard techniques for theorem proving. Designed for an AI agent to reference when helping a user write or verify Lean proofs. Covers: core tactics, automation tactics, calc/induction/cases patterns, mathlib tactics, decision tree, English-to-Lean phrasebook, proof templates. NOT about setting up the Lean environment (see lean-4-workflow).
wu1chenghui/hermes-math-template/skills/mathematical-writing Skill
no license0★ repoWrite mathematical papers that read like professional mathematics, not development logs. Covers paper organization, motivation, English usage, notation, voice, AMS formatting, and modern 21st-century practices. Synthesized from Tao, Halmos, AMS, Conrad, Poonen, Serre, and Pak.
idylle-cynique/solo-dev-skills/skills/update-docs Skill
0★ repoプロジェクトドキュメント(repository-overview.md, development-guidelines.md)を最新の状態に更新する
idylle-cynique/solo-dev-skills/skills/url-to-markdown Skill
0★ repoWebページのURLをhtml2text経由でMarkdown形式のテキストに変換するスキル。html2text CLIはURLを直接受け付けずファイルパスとして解釈してしまうため、事前にHTTPで取得してから変換する。 ユーザーがURLを渡して「Markdown化して」「テキストで見たい」「html2textで変換して」「内容を確認したい」と言ったときは、明示されていなくてもこのスキルを参照すること。
clsaa/littlepowers/skills/writing-plans Skill
0★ repoWrite an executable Littlepowers lean/full plan. Use only when routed by using-littlepowers or active state phase=plan.
clsaa/littlepowers/skills/writing-specs Skill
0★ repoWrite testable Littlepowers full-route requirements. Use only when routed by using-littlepowers or active state phase=spec.
atomgunlk/skills/skills/engineering/jira-writing Skill
0★ repoUse when creating or editing Jira issues via the Atlassian MCP (createJiraIssue / editJiraIssue) — composing descriptions and acceptance criteria, bulk-editing or find-replacing across ticket bodies, or when a link must render as an inline smartlink chip (📄 card). Symptoms — "link shows as plain text not a chip", "chips survive a markdown round-trip" (they don't), <custom data-type="smartlink">, ADF vs markdown, renaming a field across ticket bodies, acceptance criteria / EARS notation.
TheEdoRan/skills/skills/explain Skill
0★ repoRead-only analysis of a feature's implementation (or the work just completed in the conversation) across security, performance, maintainability, and edge cases. Writes findings to a markdown report file for the user to act on; changes no code. Verifies security and library best practices against current documentation via Context7. Invoke only when the user explicitly requests `/explain` or `$explain`, optionally naming the feature, paths, or diff to analyze.
pecigonzalo/agent-skills/skills/role-technical-writer Skill
0★ repoUse this skill for user-facing documentation, public API guides, release notes, migration notes, or documentation reviews where audience, structure, examples, or scope need deciding. Routes to documentation and Markdown standards without duplicating them.
pecigonzalo/agent-skills/skills/standards-documentation Skill
0★ repoUse this skill when writing or reviewing READMEs, API references, setup guides, and code comments that need concise documentation conventions and templates. Use role-technical-writer instead when the task requires broader information architecture or audience strategy.
pecigonzalo/agent-skills/skills/standards-markdown Skill
0★ repoUse this skill when writing or reviewing Markdown syntax, headings, lists, links, code fences, tables, or layout. Pair it with documentation guidance when content structure or audience needs also matter.
rvdsmaile/working-backwards/.agents/skills/write-announcement Skill
no license0★ repoDraft or improve a future-facing product announcement or blog post using Working Backwards. Use when a product idea needs a compelling customer narrative before implementation planning.
rvdsmaile/working-backwards/.agents/skills/write-faq Skill
no license0★ repoCreate or refine a customer FAQ for a Working Backwards announcement. Use when readers need clear answers about audience, problem, experience, boundaries, and next steps.
rvdsmaile/working-backwards/.agents/skills/write-internal-faq Skill
no license0★ repoCapture optional internal operating, commercial, product, and delivery questions for a Working Backwards initiative. Use when a team needs decisions beyond the customer FAQ; do not require it for handoff.