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
SWEStash/swe-workflow-skills/plugins/qa/skills/project-documentation Skill
1★ repoWrite and maintain project docs — README, contributing guides, API docs, changelogs, inline docs.
SWEStash/swe-workflow-skills/plugins/security/skills/project-documentation Skill
1★ repoWrite and maintain project docs — README, contributing guides, API docs, changelogs, inline docs.
SWEStash/swe-workflow-skills/skills/api-design Skill
1★ repoDesign RESTful and GraphQL APIs — endpoint naming, request/response contracts, error handling, pagination, versioning, auth patterns, OpenAPI specs. Triggers: design the API, API contract, REST API, GraphQL schema, error response format, pagination, API versioning, OpenAPI, swagger, endpoints. Use architecture-design for REST-vs-GraphQL or monolith-vs-microservices decisions.
SWEStash/swe-workflow-skills/skills/architecture-documentation Skill
1★ repoDesign and maintain architecture documentation with multi-level diagrams (C4) and docs-as-code. Triggers: architecture diagram, document the architecture, C4 diagram, system context, container diagram, component diagram, architecture docs, docs-as-code, PlantUML, Structurizr, D2, Mermaid architecture, infrastructure diagram, runtime flow. Use architecture-design for ADRs.
SWEStash/swe-workflow-skills/skills/prd-writing Skill
1★ repoWrite lightweight agile PRDs and technical RFCs that align stakeholders before implementation. Triggers: PRD, product requirements, RFC, request for comments, technical design doc, design document, tech spec, write requirements, what are we building, spec this out. Produces the WHAT and WHY — feature-planning handles HOW.
SWEStash/swe-workflow-skills/skills/project-documentation Skill
1★ repoWrite and maintain project docs — README, contributing guides, API docs, changelogs, inline docs.
SWEStash/swe-workflow-skills/skills/release-management Skill
1★ repoCut and publish software releases right-sized to the project — semver decisions, changelogs, tagging, automated version bumps (release-please, changesets, semantic-release), publishing gates, npm/PyPI/container registry publishing, pre-release channels, monorepo versioning. Triggers: cut a release, release this, publish to npm, publish to PyPI, publish this package, version bump, what version should this be, semver, changelog, tag a release, release notes, GitHub release, prerelease, release automation, release PR. Deploy-time safety → deployment-checklist; commit/PR hygiene → git-workflow.
SWEStash/swe-workflow-skills/skills/writing-skills Skill
1★ repoUse when authoring, editing, or reviewing a skill in this library — a new SKILL.md, one that under-triggers, or hardening an existing one. Covers description and listing-budget rules, frontmatter, progressive disclosure, the 3-eval rule, and pressure-testing against rationalizations.
feel-flow/agent-skills-examples/review/proofread-facts Skill
1★ repoファクトチェック。研究論文、統計データ、技術的主張の裏付けを検証。
feel-flow/agent-skills-examples/review/proofread-structure Skill
1★ repo章構造・フォーマットチェック。見出しの階層構造と必須セクションの有無を検証。
feel-flow/agent-skills-examples/review/proofread Skill
1★ repo日本語技術書の総合校正スキル。章単位または書籍全体の校正を実行し、重要度別にレポートを出力する。
feel-flow/agent-skills-examples/writing/proofread-document Skill
1★ repo文章校正を実行し、修正提案をレポート出力する。ドキュメント・ブログ記事・マニュアルの校正に使用。
leoluyi/skills/skills/blog-writing-zh Skill
1★ repoMy personal collection of portable SKILL.md agent skills and tooling for Claude Code, Cursor & Codex — currently focused on Traditional Chinese (Taiwan) writing, de-AI editing, and business docs.
leoluyi/skills/skills/briefing-outline Skill
1★ repoMy personal collection of portable SKILL.md agent skills and tooling for Claude Code, Cursor & Codex — currently focused on Traditional Chinese (Taiwan) writing, de-AI editing, and business docs.
leoluyi/skills/skills/formal-doc-structure Skill
1★ repoMy personal collection of portable SKILL.md agent skills and tooling for Claude Code, Cursor & Codex — currently focused on Traditional Chinese (Taiwan) writing, de-AI editing, and business docs.
leoluyi/skills/skills/knowledge-doc-writing Skill
1★ repoMy personal collection of portable SKILL.md agent skills and tooling for Claude Code, Cursor & Codex — currently focused on Traditional Chinese (Taiwan) writing, de-AI editing, and business docs.
leoluyi/skills/skills/plain-speak Skill
1★ repoMy personal collection of portable SKILL.md agent skills and tooling for Claude Code, Cursor & Codex — currently focused on Traditional Chinese (Taiwan) writing, de-AI editing, and business docs.
leoluyi/skills/skills/rfp-writing Skill
1★ repoMy personal collection of portable SKILL.md agent skills and tooling for Claude Code, Cursor & Codex — currently focused on Traditional Chinese (Taiwan) writing, de-AI editing, and business docs.
morzecrew/agent-skills/skills/keep-a-changelog Skill
1★ repoSkills that make AI coding agents prove their work — reproduce before fixing, run before claiming, enforce what you build
The same file is in 4 other repositories
morzecrew/agent-skills/skills/python-google-docstrings Skill
1★ repoSkills that make AI coding agents prove their work — reproduce before fixing, run before claiming, enforce what you build
The same file is in 1 other repository
morzecrew/agent-skills/skills/python-rest-docstrings Skill
1★ repoSkills that make AI coding agents prove their work — reproduce before fixing, run before claiming, enforce what you build
morzecrew/agent-skills/skills/rfc-writer Skill
1★ repoSkills that make AI coding agents prove their work — reproduce before fixing, run before claiming, enforce what you build
The same file is in 4 other repositories
andreab67/agent-skills/session-handoff Skill
1★ repoRun manually before ending a session — `/clear`, `/compact`, switching repos, or any context wipe — to rescue critical context that would otherwise die with the conversation. Trigger phrases include "about to /clear", "before I clear", "wrap up this session", "checkpoint before clearing", "hand off this session", "save context first", "preserve what we just figured out", "I'm switching repos", "/session-handoff". Extracts goals, pending tasks, preferences, working rules, key background, and open questions into the project's auto-memory store, applying a rescue test (skip anything derivable from code/git/CLAUDE.md) with explicit per-entry user approval before writing. Do NOT use for ad-hoc single-fact saves (write the memory file directly — full extraction is overkill), for sessions already captured by a diff and commit, or after `/clear` has already run (context is gone — say so and offer the hook setup). (Six categories, rescue test, and workflow are detailed in the body.)
UniverLab/skills/canopy-sync Skill
1★ repoUse this skill when the Canopy MCP server is available and you are about to act on a shared workspace: writing files, running builds or tests, installing dependencies, or committing. It defines the action-driven sync protocol (sync_get_context, sync_declare_intent, sync_broadcast, sync_report_status) that keeps solo history clean and multi-agent work conflict-free.
lgtm-hq/ai-skills/skills/stand-rust Skill
1★ repoRust coding standards. Use when writing Rust code. Covers edition, error handling with thiserror/anyhow, unsafe policy, type patterns, testing, documentation, and dependency management.
simonkoehler/event-skills/event-sponsors Skill
1★ repoFor B2B event organizers: create and sell sponsorship packages for YOUR B2B event. Manages programs from the organizer's perspective — designing tiers, pricing, tracking fulfillment. B2B context only — not for cause-based galas, charity fundraisers, or sports/entertainment sponsorships. Generates tier structures, prospectus documents, exhibitor guides, outreach emails, fulfillment trackers, and sponsor ROI reports. Triggers for creating sponsorship packages, writing a prospectus, designing tiers, pricing levels, creating exhibitor guides, writing outreach emails, tracking deliverables, planning activations, or reporting on sponsor ROI. Also handles revenue forecasting, retention strategy, in-kind valuation, and communication sequences. This is the organizer side — for evaluating whether to sponsor someone else's event, use the event-exhibition skill instead. Part of the event-management-skills collection.
GustavoGutierrez/engineering-skills/skills/api-spec-writer Skill
1★ repoDesign complete API contracts in OpenAPI 3.0/3.1 YAML with endpoints, schemas, security, pagination, error handling, and RFC 7807 problem details. Use when asking to design an API, create an OpenAPI spec, define API endpoints, write API contracts, or generate a Swagger specification.
GustavoGutierrez/engineering-skills/skills/decision-record-writer Skill
1★ repoWrite Architecture Decision Records (ADRs) using append-only supersession model. Trigger: document architectural decision, create ADR, record decision rationale, architecture decision, technical decision log, or decision record.
GustavoGutierrez/engineering-skills/skills/documentation-architect Skill
1★ repoDesign scalable, navigable documentation ecosystems for onboarding, architecture, operations, ADRs, runbooks, and reference; use when asked to architect docs, plan information architecture, design doc systems, organize knowledge bases, structure living documentation, or fix documentation fragmentation.
The same file is in 1 other repository
GustavoGutierrez/engineering-skills/skills/frontend-spec-writer Skill
1★ repoDesign complete frontend specifications from product requirements: UX flows, component hierarchies, component contracts (props/events), state management, responsive breakpoints, accessibility rules, and API integration mapping. Use when asking to design a frontend spec, component architecture, UI specification, or view specification.
GustavoGutierrez/engineering-skills/skills/gherkin-feature-writer Skill
1★ repoTrigger: Gherkin, .feature file, write feature file, BDD scenario, Given When Then, Cucumber/Behave/SpecFlow, acceptance criteria as scenarios. Write declarative, standard-compliant Gherkin .feature files.
GustavoGutierrez/engineering-skills/skills/prd-writer Skill
1★ repoGenerate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.
The same file is in 1 other repository
GustavoGutierrez/engineering-skills/skills/prp-writer Skill
1★ repoGuides creation of Product Requirements Prompts (PRPs) - comprehensive requirement documents that serve as the foundation for AI-assisted development
The same file is in 1 other repository
GustavoGutierrez/engineering-skills/skills/spec-writer Skill
1★ repoWrite, rewrite, or normalize structured `*.spec.md` specification files for agent-driven development. Use this whenever the user asks for a spec, requirements, acceptance criteria, implementation-ready documentation, feature definition before coding, or wants an existing idea/codebase turned into an actionable spec, even if they do not explicitly say "spec".
The same file is in 1 other repository
GustavoGutierrez/engineering-skills/skills/togaf-writer Skill
1★ repoApply or draft TOGAF-aligned enterprise architecture artifacts using ADM phases, four architecture domains, baseline-to-target analysis, governance, and migration planning.
Sallyn0225/sallyn-skill/skills/translate-srt Skill
1★ repo翻译 SRT 字幕文件到指定语言——修正语音转录错误、联网补充背景知识、按术语表信达雅翻译并复核。Use when the user wants to translate an SRT/subtitle file (翻译字幕、字幕翻译、translate subtitles), or to fix a speech-to-text SRT before translating.
sainzs/santiagosainz-skills/skills/core/domain-modeling Skill
1★ repoModel the domain language, entities, states, aliases, and naming rules from code, docs, ADRs, tests, and user vocabulary. Use when the user asks for glossary work, naming cleanup, project vocabulary, system concepts, or project-language.
Iabstergo1/pdf-to-study-kb/.agents/skills/source-xray Skill
1★ repoGenerate a book-breakdown reading note or synthesis-candidate report from published source/concept/topic content, writing only pipeline-workspace/reports/source-xray/ by default (not the vault). Use when the user says "x-ray this published source / book-breakdown reading notes / source-xray / generate learning-note candidates". It does not preprocess, does not decide windows, does not decide write scope, and does not create or merge concept pages.
rmerk/crewai-headless-flow/.agents/skills/grill-with-docs Skill
1★ repoA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
The same file is in 19 other repositories
rmerk/crewai-headless-flow/.agents/skills/research Skill
1★ repoInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
The same file is in 11 other repositories
rmerk/crewai-headless-flow/vendor/agent-skills/skills/documentation-and-adrs Skill
1★ repoRecords decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
The same file is in 11 other repositories
buildwitharup/cortex/skills/copywriting Skill
1★ repoUse when the user wants to write or improve marketing copy for any page, email, ad, or campaign. Also triggers on "write copy", "homepage copy", "landing page copy", "email copy", "ad copy", "rewrite this", "improve this headline", "value proposition", "tagline", "product description".
buildwitharup/cortex/skills/freelancer-brief Skill
1★ repoUse when the user needs to write a brief for an external freelancer, agency, or vendor. Also triggers on "brief a freelancer", "write a creative brief", "vendor brief", "brief an agency", "content brief for writer", "design brief", "web development brief", "brief external team", "contractor brief", "outsource task".
anarefin/ai-agent-skills/merge-ears-workspace/skill-snapshot Skill
no license1★ repoMerge, combine, or consolidate two or more EARS (Easy Approach to Requirements Syntax) specification .md files into a single coherent EARS spec. Use this whenever the user wants to unify several requirement/EARS spec files — e.g. "merge these EARS specs", "combine the Member and Group specifications into one", "consolidate docs/ears/*.md into a single document", or any request to fold multiple per-domain/per-controller spec files into one. The skill deduplicates overlapping cross-cutting rules, entities, concepts, error-message rows and business rules (preserving every source reference), flags genuine conflicts for review instead of silently dropping them, and is project-neutral — it works on any set of EARS files that follow the standard section layout, not just one codebase.
anarefin/ai-agent-skills/prompt-master Skill
no license1★ repoGenerates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.
The same file is in 3 other repositories
tdyzzsp47/claude-skills/skills/documentation Skill
1★ repoREADME・CLAUDE.md・設計書・ランブック等の技術文書を作成・更新・鮮度管理するスキル。新機能追加時・新規参加者対応時・既存文書の陳腐化を検出したい時に使う。
tdyzzsp47/claude-skills/skills/i18n-localization Skill
1★ repoアプリケーションの国際化(i18n)・ローカライゼーション(l10n)を設計・実装するスキル。海外展開を検討している・多言語対応を後付けで追加しようとしている・ハードコード文字列の外部化が必要な時に使う。
k-anss/whetstone/skills/distill-not-transcribe Skill
1★ repoTurn a written method — a workflow document, protocol, SOP, or an existing popular skill — into a new skill that encodes the author's judgment, not just their steps. Trigger when the user says "make this into a skill", "turn my workflow / protocol / SOP into a skill", "skill-ify this document", "adapt / fork / localize this skill for my case", or "distill my method so an agent can run it". Do NOT trigger for: writing a single prompt, generating documentation or READMEs, building an application, or packaging step-by-step instructions that contain no decisions. If the source material contains no judgment, the correct output is a refusal (see Failure behavior).
k-anss/whetstone/skills/handoff-discipline Skill
1★ repoHand off the working state of one AI session to another that shares no context. Trigger when the user says "write a handoff for the next agent / another Claude / a fresh session", "brief the next instance", "sync state to my other project", or "carry this over without losing what's decided". Produces a self-contained handoff doc that separates what must NOT be reopened from current status from strategic rationale, and defines the receiving agent's role. Do NOT trigger for: summarizing a document for a human reader, writing meeting notes, or compressing a conversation for the same ongoing session (that is summarization, not handoff).
k-anss/whetstone/skills/read-not-decorate Skill
1★ repoUse when someone hands you a finished long-form markdown document (a report, an essay, an archived article, a research write-up) and wants it turned into a single self-contained HTML file meant to be read or kept — not a slide deck, not a marketing page, not a redesign. Trigger on requests like "typeset this report as HTML", "make a clean reading page from this markdown", "archive this article as a standalone HTML I can keep", or "turn this write-up into a page I can send to a client". The skill assembles; it does not rewrite the author's words, add arguments, or add decoration.
k-anss/whetstone/skills/report-deck-zh Skill
1★ repoBuild Chinese work-briefing slides that follow the structural grammar of formal Chinese reporting — parallel (对仗) titles, whole-part-whole (总分总) structure, data pages with caliber/source captions (口径说明), and hierarchical progression — instead of English pitch-deck aesthetics or generic AI-PPT templates. Trigger when the user says "做一份汇报/述职/总结 slides", "中文工作汇报 deck", "把这个做成汇报 PPT(中文正式)", "立项汇报 版式", "复盘汇报排版", or "Chinese briefing slides / formal Chinese report deck". Produces structure, not content. Do NOT trigger for: English pitch decks (use frontend-slides), casual or social-sharing slides, generating the report's actual content or copy (this builds the structural skeleton only), or generic "make this prettier" requests with no formal-briefing context.
k-anss/whetstone/skills/strip-the-ai-voice Skill
1★ repoStrip the "AI voice" from Chinese text by deletion, not rewriting. Removes honorifics (您/请), filler particles (哦/呢), adjective/adverb padding, self-explanation, and reader-conclusions — using a concrete delete-test, not a vague "make it natural". Trigger when the user says "去掉 AI 味", "这段中文太 AI 了 / 帮我改克制点", "strip the AI tone from this Chinese", or "make this Chinese read like a professional / archival document". Direction is subtraction, not addition. Do NOT trigger for: making text MORE casual or human/网感 (that is the opposite, addition — use a humanizer), translating, or editing English. Operates only on AI-generated copy; never alters the user's own source prose.
roronoazoroshao369/vibe-coding-os/skills/agents/writer-critic-pair Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/docs-author Skill
1★ repoFive-section structure (Purpose → When to use → Workflow → Outputs → Failure modes) for authoring skills, commands, and templates that match repo conventions.
roronoazoroshao369/vibe-coding-os/skills/core/writing-plans Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/meta/write-reusable-skill Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
jlreyes/swift-agent-kit/skills/translation-coordinator Skill
no license1★ repoOrchestrates Xcode String Catalog localization: prepares the project via LocalizationPlanner, fetches untranslated keys by state, and delegates batches to translator subagents that use the translation skill. Use when asked to localize an Xcode project or translate String Catalogs. Requires the xcode-tools MCP server. (Content extracted from your local Xcode on install.)
jlreyes/swift-agent-kit/skills/translation Skill
no license1★ repoTranslates a provided list of Xcode String Catalog keys into one provided target locale via the StringCatalog MCP tools, with per-key context lookup. Worker role inside a localization flow — only use when delegated an explicit key list and target locale (normally by translation-coordinator); it aborts without them. Requires the xcode-tools MCP server. (Content extracted from your local Xcode on install.)
rangzen/knowledge-project-skills/skills/kp-staging Skill
no license1★ repoReusable AI agent skills for knowledge projects: ingest PDFs, wikis, and reports, extract structured entities, and build a navigable knowledge base (wiki) your agents can query.
rangzen/knowledge-project-skills/skills/kp-wiki Skill
no license1★ repoBuild or update the wiki in wiki/ from staged content. Generates wiki/glossary.md, one Markdown page per entity, wiki/index.md (Obsidian entry point), and wiki/index.yaml (agent entry point). Reads wiki/queries/ feedback to prioritize topics and surface staging gaps. Use when the user runs /kp-wiki, wants to build or rebuild the wiki, needs to generate the glossary or wiki pages, or wants to add a manually-curated page to the wiki. "kps" is the short name for this project (Knowledge Project Skills) - also activate when the user says "kps wiki".