Docs & writing
16,621 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
Aiweline/WelineFramework/dev/ai/skills/i18n-internationalization Skill
1★ repoDeprecated compatibility alias for historical i18n references.
Aiweline/WelineFramework/dev/ai/skills/文档知识库工程师-文档规范与变更记录 Skill
1★ repoDocumentation engineer skill for module docs, README updates, architecture notes, API change records, and repository-safe documentation placement.
Aiweline/WelineFramework/dev/ai/skills/通用工程师-国际化与用户提示 Skill
1★ repoShared engineering skill for i18n-compliant user text, translation files, and framework-safe user notification patterns.
authenticfake/clike/extensions/vscode/templates/harper-init/.clike/skills/eval-contract-writer Skill
1★ repoRequire every runnable KIT to emit deterministic validation artifacts for EVAL and GATE.
8421bit/NioPD-Skills/plugins/niopd/skills/NioPD-PO-faq Skill
1★ repoGenerates comprehensive FAQ document. Use for product documentation.
JarrydAdaens/agentic_rails_tooling/source/skills/rails-initialize-from-tier0 Skill
1★ repoUse this skill when initializing or populating a newly created repository from the Agentic Rails context starter using a large dictation intake document, dictated project seed, AI-generated research report, transcript, rough requirements dump, or kickoff notes. Use it to preserve the raw dictation, synthesize project-specific left-rail context, replace starter placeholders in design (with its Milestones Index), milestone docs, the story backlog, README, and related context files, and optionally seed initial implementation plans without overwriting reusable Agentic Rails framework material.
JarrydAdaens/agentic_rails_tooling/source/skills/rails-project-appraisal Skill
1★ repoUse this skill when the user asks for a deep project appraisal, project audit, architecture review, viability review, strategic review, or "is this project worth continuing?" analysis of an Agentic Rails project. It reads repository and context-tier material, validates the codebase by building, testing, and (where a UI exists) launching it, inspects git history, performs external grounding via web research, and writes a frank, evidence-led markdown report under context/reports/ that grades the project and recommends a course of action — continue, refine, harden, pivot, split, rebuild, freeze, or abandon. Reserved for deep, deliberate use on projects that matter, not a lightweight orientation pass, a code-execution skill, or a normal planning/implementation workflow.
makigjuro/cloudstack-ai-plugins/plugins/dev-workflow/skills/docs Skill
1★ repoGenerate or update project documentation from code -- API docs, service docs, architecture docs, or runbooks. Use after adding endpoints, entities, events, or infrastructure changes, or when documentation may be stale.
yu-iskw/coding-agent-skills/.cursor/skills/readme-sync Skill
no license1★ repoSynchronizes the list of Agent Skills in the root README.md with the actual skills present in the codebase.
The same file is in 2 other repositories
puku0x/agent-skills-test/.claude/skills/git-commit Skill
1★ repoCreate Git commit messages following Conventional Commits format with automatic type and scope detection. Use when asked to "commit changes", "create a commit", "write commit message", or when ready to commit staged code. Supports feat, fix, docs, refactor, test, build, ci, chore, and revert types with project-specific scope determination based on file paths and directory structure.
puku0x/agent-skills-test/.github/skills/git-commit Skill
1★ repoCreate Git commit messages following Conventional Commits format with automatic type and scope detection. Use when asked to "commit changes", "create a commit", "write commit message", or when ready to commit staged code. Supports feat, fix, docs, refactor, test, build, ci, chore, and revert types with project-specific scope determination based on file paths and directory structure.
bob798/ai-skill-kit/creative/article-writer Skill
no license1★ repoA curated library of reusable AI skills and prompt templates for LLMs and AI agents to enhance reasoning, productivity, and workflows.
bob798/ai-skill-kit/development/ok-itest Skill
no license1★ repoGenerate executable integration-test specs, skeletons, and PR reports for Spring Boot + Spring AI services. Trigger when the user wants to write integration tests, add wire-level ITs, draft an IT spec, or produce a PR test report.
bob798/ai-skill-kit/workflow/weekly-report Skill
no license1★ repo通用周报生成 Skill。4 段结构(总目标 / 本月 / 下周 / 风险)+ 双进度条对比(任务 vs 时间)+ 总目标进度条 + Markdown 文字版(一键复制)。输出单页 PNG(领导面向汇报)。当用户说"做周报"、"出周报"、"本周汇报"、"周五汇报"、"生成周报"、"周会用图"时触发。适用于任意项目的周期性进度汇报。
jovd83/playwright-skill/documentation/root_cause Skill
1★ repoFailure-analysis skill for Playwright runs. Use when Codex needs to investigate a failing test, distinguish likely product bugs from test issues, and produce a concise developer-focused root-cause report backed by evidence.
jovd83/playwright-skill/documentation/test_cases/bdd Skill
1★ repoLegacy Playwright-specific alias for BDD case formatting. Prefer the standalone `test-artifact-export-skill` skill for Gherkin, BDD, and export-ready case rendering, and use this only when Playwright-local conventions must be preserved explicitly.
jovd83/playwright-skill/documentation/test_cases/plain_text Skill
1★ repoLegacy Playwright-specific alias for plain-text case formatting. Prefer the standalone `test-artifact-export-skill` skill for lightweight narrative case output, and use this only when Playwright-local conventions must be preserved explicitly.
jovd83/playwright-skill/documentation/test_cases/tdd Skill
1★ repoLegacy Playwright-specific alias for TDD-style case documentation. Prefer the standalone `test-artifact-export-skill` skill for formatting approved test cases or building export-ready artifacts, and use this only when Playwright-local conventions must be preserved explicitly.
jovd83/playwright-skill/documentation/tests Skill
1★ repoAutomation-code documentation skill for Playwright suites. Use when Codex needs to add or improve human-readable comments, docblocks, or file-level explanations around existing Playwright tests without drowning the code in redundant commentary.
jovd83/playwright-skill/mappers/xray Skill
1★ repoTest-management mapping skill for Xray. Use when Codex needs to apply authoritative Xray test keys or issue IDs back into local Playwright docs, tags, or annotations for reliable traceability and reporting.
jovd83/playwright-skill/orchestrator Skill
1★ repoCentral entrypoint for broad or ambiguous Playwright requests. Use when Codex needs to classify the user's testing goal, choose the right Playwright subskill, and move from intent to implementation, planning, documentation, execution, or reporting without unnecessary menu-driven back-and-forth.
jovd83/playwright-skill/reporting/stakeholder Skill
1★ repoStakeholder-reporting skill for Playwright execution results. Use when Codex needs to turn raw Playwright runs into a concise, non-technical summary of tested scope, release health, business impact, and recommended next actions.
rmzlb/baaton-skills/marketing/create Skill
1★ repoFull content production pipeline: Brief → Research → Write → Audit → Iterate → Publish-Ready. Orchestrates write and audit skills for end-to-end content creation. Use when: creating any new piece of content from scratch (LinkedIn post, thread, email, ad copy, landing page), running a full content sprint, or when you need a systematic pipeline that ensures quality before publish. Trigger words: create a post, write content, content pipeline, production sprint, content from scratch, draft a post, write a LinkedIn post, write a tweet, write an email, write an ad, write a landing page. NOT for: auditing an existing draft (use audit directly), writing assistance only (use write directly), or quick one-shot replies.
rmzlb/baaton-skills/marketing/measure Skill
1★ repoMarketing measurement, reporting, and iteration frameworks. Metrics by platform, attribution models, content performance analysis, A/B testing, and reporting templates. Use when: analyzing content performance, building reports, deciding what to post next, setting up tracking, A/B testing content, or reviewing marketing ROI. Trigger words: analytics, metrics, performance, report, ROI, conversion, A/B test, what's working, engagement rate, attribution, funnel analysis, dashboard. NOT for: writing content (use write), auditing quality (use audit), or defining strategy (use strategy).
rmzlb/baaton-skills/marketing/repurpose Skill
1★ repoTransform one piece of content into multiple platform-optimized formats. 1-to-N content multiplication: LinkedIn post to X thread, email, carousel, video script, and more. Includes platform adaptation rules, not just reformatting. Use when: repurposing a post for other platforms, maximizing content ROI, creating a content series from one idea, or building a multi-channel campaign. Trigger words: repurpose, transform, adapt, cross-post, multi-platform, content multiplication, 1-to-N, carousel, thread from post, atomize. NOT for: writing original content (use write), quality scoring (use audit), or strategic planning (use strategy).
rmzlb/baaton-skills/marketing/write Skill
1★ repoPlatform-specific writing frameworks for LinkedIn, X/Twitter, email, ad copy, and landing pages. Includes brand voice configuration, anti-AI writing rules, algorithm insights, and self-check checklists for each platform. Use when: writing a specific piece of content with platform-specific guidance, applying brand voice to a draft, following the write phase of create, or learning platform best practices. Trigger words: write a LinkedIn post, write a tweet, write an email, write ad copy, write a landing page, apply brand voice, platform framework, how do I write for LinkedIn, hook patterns, post structure. NOT for: full pipeline with audit (use create), quality scoring (use audit), or strategy planning.
MatrixFounder/Universal-skills/skills/post-writing Skill
1★ repoUse when the user asks to write, draft, or rewrite a post for social media (LinkedIn, Telegram, Blog) or wants content to be more engaging.
mitchuski/agentprivacy-skills/agentprivacy-skills-v5/role/agentprivacy-academic Skill
1★ repoFormal academic specification and research methodology for 0xagentprivacy. Activates when writing papers, proofs, formal specifications, literature reviews, or preparing work for peer review. Use for LaTeX formatting, citation standards, theorem-proof structure, or research presentation. V6 register note (2026-06-10): conjecture and version citations resolve to agentprivacy-docs/research/CONJECTURE_REGISTER_V6.md (head C89); model head: privacy_value_v6_formal_specification.md.
Agentprivacy wiki document plugin
mitchuski/agentprivacy-skills/agentprivacy-skills-v5/wikis/agentprivacy-wiki-document-plugin Skill
1★ repoPublish documentation for a Federated Wiki plugin as wiki pages on plugin.fedwiki.club (the curated plugin-catalog wiki). Activates when documenting a fedwiki plugin or adding it to the catalog. The inverse of fedwiki-to-skill. Kept by the Librarian 🗃️ in the Wikis.
mitchuski/agentprivacy-skills/agentprivacy-skills-v5/wikis/agentprivacy-wiki-document Skill
1★ repoCreating a help page on the wiki for a Claude Code skill — describing what it does and when it fires — and publishing the skill's own SKILL.md as a downloadable asset. The skill-side parallel to documenting a wiki plugin. Part of the git-less onboarding/distribution layer kept by the Librarian 🗃️ in the Tower's Wikis.
Agentprivacy holonic persistence
mitchuski/agentprivacy-skills/mnt/user-data/outputs/role/agentprivacy-holonic-persistence Skill
1★ repoMulti-provider data persistence for privacy-preserving AI agents using holonic architecture. Activates when discussing HyperDrive auto-failover, auto-replication across heterogeneous backends, provider-agnostic storage, privacy-aware routing between shielded and public providers, write-all-or-fail for separation-critical state, or any task where agent data must survive TEE rotation, chain migration, or provider failure. Use when designing persistence layers that span blockchains, databases, and decentralised networks simultaneously. V6 register note (2026-06-10): conjecture and version citations resolve to agentprivacy-docs/research/CONJECTURE_REGISTER_V6.md (head C89); model head: privacy_value_v6_formal_specification.md.
ForeverSc/ai-handrail/skills/legacy-doc-bootstrap Skill
1★ repoUse when a legacy project needs documentation created from scratch or existing implicit knowledge turned into structured docs. Triggers when user says "document this project", "create docs for this codebase", "write up the architecture", or after legacy-discovery has completed analysis.
VALL-dikss/skills/readme Skill
1★ repoWhen the user wants to create or update a README.md file for a project. Also use when the user says "write readme," "create readme," "document this project," "project documentation," or asks for help with README.md. This skill creates absurdly thorough documentation covering local setup, architecture, and deployment.
bingooyong/agent-skills/skills/knowledge-card-generator Skill
no license1★ repoConvert Markdown knowledge base files into structured JSON + YAML LLM Wiki card sets. Use when (1) transforming module/feature/process/rule docs into machine-readable cards, (2) building LLM-consumable knowledge bases from Markdown, (3) generating dependency-linked card sets for Codex or Vibecoding AI, (4) user mentions 'knowledge card', 'wiki card', 'card set', or 'MD to JSON/YAML'. Outputs dual-format card collections with cross-references and index definitions.
bingooyong/agent-skills/skills/project-doc-generator Skill
no license1★ repoGenerate and maintain project documentation systems from structured inputs. Use when (1) creating documentation from spec/requirements/design/tasks, (2) planning doc dependency order and generation sequence, (3) incremental doc updates with consistency checks, (4) generating docs with correct depth for target audience. Focuses on dependency-aware, incremental, audience-appropriate documentation.
yu-iskw/coding-agent-fabric/.claude/skills/manage-changelog Skill
1★ repoManage changelogs using Changie. Provides tools to initialize, add change fragments, batch releases, and merge version notes. Requires 'changie' to be installed.
yu-iskw/coding-agent-fabric/.claude/skills/sync-readme Skill
1★ repoSynchronize technical sections in README.md and CONTRIBUTING.md with the actual project state.
yunseo-kim/agent-toolbox/.agents/skills/doc-coauthoring Skill
no license1★ repoGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
The same file is in 39 other repositories
yunseo-kim/agent-toolbox/.agents/skills/docs-changelog Skill
no license1★ repoGenerates and formats changelog files for a new release based on provided version and raw changelog data.
yunseo-kim/agent-toolbox/.agents/skills/docs-writer Skill
no license1★ repoUnified documentation workflow for writing, reviewing, and updating technical docs across repositories. Use when users ask to write or edit docs, review doc quality, map code changes to doc impact, scaffold new documentation, update README/API guides, or improve docs in `/docs` and `*.md`/`*.mdx` files. Supports self-contained profile-based behavior for generic docs, Next.js docs, and Angular docs.
yunseo-kim/agent-toolbox/catalog/skills/copywriting Skill
no license1★ repoWrite, rewrite, or improve marketing copy for homepages, landing pages, pricing pages, feature pages, and product pages
yunseo-kim/agent-toolbox/catalog/skills/doc-coauthoring Skill
no license1★ repoGuide users through a structured workflow for co-authoring documentation, proposals, technical specs, and decision docs. Use when writing docs, creating proposals, drafting specs, or collaborative documentation tasks.
yunseo-kim/agent-toolbox/catalog/skills/docs-writer Skill
no license1★ repoUnified documentation workflow for writing, reviewing, and updating technical docs across repositories. Use when users ask to write or edit docs, review doc quality, map code changes to doc impact, scaffold new documentation, update README/API guides, or improve docs in `/docs` and `*.md`/`*.mdx` files. Supports self-contained profile-based behavior for generic docs, Next.js docs, and Angular docs.
yunseo-kim/agent-toolbox/catalog/skills/editor Skill
no license1★ repoProfessional editing and proofreading for clarity, grammar, style, and readability improvements across all document types
yunseo-kim/agent-toolbox/catalog/skills/js-docs-fact-check Skill
no license1★ repoVerify technical accuracy of JavaScript documentation by checking code examples, MDN/ECMAScript compliance, and common misconceptions. Use before publishing, after major edits, or during periodic accuracy audits.
allenli178/yuyan-skills/tech-evaluator/skills/report-writer Skill
1★ repo调研报告生成Skill,汇总所有原子Skill的输出,按照报告模板生成技术选型调研报告。
medy-gribkov/arcana/skills/docx Skill
1★ repoUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a "report", "memo", "letter", "template", or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
medy-gribkov/arcana/skills/i18n-localization Skill
1★ repoInternationalization and localization for web applications. Handles next-intl, react-intl, ICU MessageFormat, RTL layouts, and dynamic locale loading.
medy-gribkov/arcana/skills/update-docs Skill
1★ repoThis skill should be used when the user asks to "update documentation for my changes", "check docs for this PR", "what docs need updating", "sync docs with code", "scaffold docs for this feature", "document this feature", "review docs completeness", "add docs for this change", "what documentation is affected", "docs impact", or mentions "docs/", "docs/01-app", "docs/02-pages", "MDX", "documentation update", "API reference", ".mdx files". Provides guided workflow for updating Next.js documentation based on code changes.
dortort/skills/skills/terraform Skill
no license1★ repoWrites Terraform infrastructure code following strict module abstraction principles, proper file structure, and quality standards. Modules are never thin resource wrappers — each represents a meaningful level of abstraction. Always uses the latest stable Terraform and provider releases. Always looks up provider documentation before writing code. Always runs format, init (no backend), and validate before committing. Use when user asks to write, create, add, update, or refactor Terraform code or modules, or mentions "terraform", "IaC", or "infrastructure as code".
sadiksaifi/skills/snap-visual Skill
no license1★ repoCreate a single-page HTML visual brief to explain a concept, plan, architecture, comparison, or proposal — then open it in the browser. Use whenever the user asks to "explain this visually", "show me an HTML page", "make a visual", "diagram this", "visualize X", or wants something rendered as a page instead of prose. Also reach for this proactively when a dense explanation (an architecture, a migration plan, a set of tradeoffs, a design proposal) would clearly land better as a visual document than a wall of text.
iplaylf2/coding-profile/profile/agent/skills/editorial-practice Skill
no license1★ repoUse when the user needs to draft, revise, rewrite, restructure, copy edit, or review prose or documentation, or when a broader task leaves a substantive reader-path, structure, or cohesion decision unresolved. Do not use merely because a specialized artifact contains prose or when its governing artifact rules already resolve the requested wording decision.
skillsdirectory/claude-skills/skills/seo-blog-writer Skill
no license1★ repoSEO-optimized blog post writer with expertise in keyword research, content structure, meta tags, and search engine ranking strategies. Use when creating blog posts, articles, or any content that needs to rank well on Google.
The same file is in 1 other repository
skillsdirectory/claude-skills/skills/technical-writer Skill
no license1★ repoExpert technical documentation writer who creates clear, structured docs including API references, guides, tutorials, and README files. Use when writing documentation, API docs, or developer guides.
The same file is in 1 other repository
corticalstack/flow/.claude/skills/research-codebase Skill
1★ repoDocument the codebase as-is via parallel read-only sub-agents and write findings under flow/research/. Explicit workflow command; run only when invoked via /research-codebase or explicitly asked.
broomva/control-metalayer/.skills/knowledge-graph-memory Skill
1★ repoBridge Claude Code conversation logs to an Obsidian knowledge graph for persistent agent memory. Transforms .entire/ event logs and ~/.claude/ transcripts into searchable, wikilinked markdown docs with full conversation threads, tool call details, and session metadata. Use when setting up conversation history capture, configuring knowledge graph traversal for agents, building episodic memory from session logs, or connecting agent work to an Obsidian vault. Triggers on "conversation history", "session logs to obsidian", "knowledge graph memory", "agent episodic memory", "conversation bridge", "session documentation", or "knowledge traversal".
jtmthf/skills/skills/test-writer Skill
no license1★ repoExpert JavaScript/TypeScript test engineer. MUST use this skill whenever the user asks you to write, add, fix, update, or improve tests — including unit tests, integration tests, component tests, E2E tests, interaction tests, and test coverage. Covers all major JS/TS test frameworks: Vitest, Jest, Node test runner, Playwright, React Testing Library, Vitest browser mode, and Storybook. Also use when users mention test strategy, flaky tests, test structure, mocking approach, testing a component, testing an API, testing a function, testing a hook, or adding test cases for edge cases and bug reproduction. Trigger on any mention of: "write tests", "add tests", "test this", "test coverage", "need tests", "test file", ".test.", ".spec.", "describe(", "it(", "test(", "expect(", "testing library", "playwright test", "vitest", "jest", "storybook play function", or when producing test files even if "test" isn't explicit (e.g., "verify this works", "make sure this doesn't break", "add coverage").
jtmthf/skills/skills/voice-writer Skill
no license1★ repoWrites in Jack Moore's voice and style. Use whenever drafting documents, messages, proposals, announcements, articles, or any text that should sound like Jack. Triggers on "write in my voice", "draft", "write this up", "announcement", "proposal", or when producing text meant to be sent or published as Jack.
duckyman-ai/agent-skills/skills/git-convention Skill
1★ repoWrite conventional git commit messages following the Angular commit convention format. Use this skill whenever writing commit messages, creating commits, reviewing git history, generating changelogs, or any task involving git version control. Triggers when you see "commit", "git commit", "commit message", "changelog", "version control", "git history", "semantic commit", "conventional commit", or when the user asks to commit changes, create a PR, or review commit history. Also use when setting up commit linting or husky hooks for enforcing commit conventions.
d-oit/do-web-doc-resolver/.agents/skills/do-wdr-cli Skill
1★ repoUse the do-wdr (Web Documentation Resolver) CLI binary to resolve URLs and queries into markdown documentation. Use when you need fast command-line access to web documentation resolution, prefer compiled binary over Python, or need to integrate do-wdr into shell scripts and automation.