agentsclimarketplace
Sign in

Shelves

Docs & writing

16,892 rows from 3,895 repositories

Prose as the deliverable, whether it ships to users or to the next maintainer.

What Docs & writing skills agree on

3,030 skill files read, by 1,951 of the 3,904 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 377 measured here is ~1.6k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Use third-person for skill descriptions54 of 1951 in 35 filesalso worded as use third-person perspective for skill descriptions; use third person for skill descriptions
  2. Start descriptions with Use when43 of 1951 in 29 filesalso worded as Start description with Use when; start descriptions with Use when or How to
  3. Run baseline scenarios before writing any skill40 of 1951 in 26 filesalso worded as run baseline scenarios before writing the skill; observe baseline failure before writing any skill
  4. Use active voice40 of 1951 in 36 filesalso worded as Use the active voice; Use active voice for every sentence
  5. Map file responsibilities before defining tasks36 of 1951 in 29 filesalso worded as map out file responsibilities before defining tasks; map out files and responsibilities before defining tasks
  6. Use checkbox syntax for tracking steps35 of 1951 in 27 filesalso worded as Use checkbox syntax for tracking tasks; Use checkbox syntax for tracking
  7. Ask one question at a time35 of 1951also worded as Ask questions one at a time; Ask clarifying questions one at a time
  8. Offer execution options after saving the plan33 of 1951 in 24 filesalso worded as Offer execution choices after saving the plan; Offer execution options after saving
  9. Include complete code in every step33 of 1951 in 27 filesalso worded as include actual code and commands in every step; include actual code for every step
  10. Design units with clear boundaries and interfaces31 of 1951 in 23 filesalso worded as Design units with clear boundaries; design units with clear boundaries and defined interfaces
  11. Announce the skill usage at the start30 of 1951also worded as Announce skill usage at start; Announce skill usage at the start
  12. Verify agent compliance after adding the skill29 of 1951 in 17 filesalso worded as verify agent compliance after writing the skill; verify compliance after writing the skill
  13. Announce plan creation at the start27 of 1951 in 18 filesalso worded as announce plan creation at start; announce plan generation at the start
  14. Use kebab-case for skill names27 of 1951 in 22 filesalso worded as use kebab-case for new file names; Use kebab-case for the filename
  15. Apply test-driven development to process documentation26 of 1951 in 16 filesalso worded as apply test-driven development to documentation; apply test-driven development to procedure documentation

What they tell it not to do

  1. Do not overwrite existing files60 of 1951also worded as do not overwrite existing documentation; do not silently overwrite existing files
  2. Do not use placeholders like TBD or TODO49 of 1951 in 44 filesalso worded as Do not use placeholders like TODO or TBD; do not use TBD or TODO placeholders
  3. Do not use em dashes49 of 1951also worded as Do not use em-dashes; Do not use em or en dashes
  4. Do not summarize the skill process in the description40 of 1951 in 26 filesalso worded as do not summarize skill workflows in the description; do not summarize skill workflow in the description
  5. Do not include narrative storytelling39 of 1951 in 28 filesalso worded as do not use narrative examples; do not include narrative storytelling in skills
  6. Do not create skills for one-off solutions35 of 1951 in 24 filesalso worded as do not create one-off solutions; do not use skills for one-off tasks
  7. Do not use @ links to reference other skills34 of 1951 in 22 filesalso worded as do not use @ to link skills; do not use @ links to other skills
  8. Do not include implementation details in the glossary34 of 1951 in 32 filesalso worded as do not document implementation details; do not include implementation details in glossary
  9. Do not skip testing for simple additions32 of 1951 in 22 filesalso worded as do not skip testing for minor updates; do not skip testing for any reason
  10. Do not reference undefined types or functions29 of 1951 in 23 filesalso worded as Do not reference undefined functions or methods; do not use references to undefined types or functions

What they expect to be installed

  1. git375 of 1951
  2. grep181 of 1951
  3. python3111 of 1951
  4. gh93 of 1951
  5. bash93 of 1951
  6. python81 of 1951
  7. curl78 of 1951 in 76 files
  8. pytest75 of 1951 in 66 files
  9. Read75 of 1951
  10. AskUserQuestion69 of 1951

What they ask it to produce

  1. Markdown file155 of 1951 in 154 filesalso worded as markdown files; Markdown report
  2. SKILL.md106 of 1951 in 83 filesalso worded as SKILL.md file; skill
  3. Updated documentation files92 of 1951 in 88 filesalso worded as updated documentation; updated documentation pages
  4. Implementation plan markdown file61 of 1951 in 50 filesalso worded as implementation plan file; markdown implementation plan file
  5. README.md61 of 1951 in 59 filesalso worded as README; Updated README.md
  6. CLAUDE.md49 of 1951 in 44 filesalso worded as Updated CLAUDE.md; CLAUDE.local.md
  7. Documentation48 of 1951 in 41 filesalso worded as Technical documentation; documentation files
  8. report.md42 of 1951also worded as research.md; review.md

When Docs & writing authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 1,951 authors, with the skills that name each one

How Docs & writing skills are built

15,539 skill directories by 3,361 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 3 files, 15.9 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill1,037 of 3,361 authors, 7,149 of 15,539 skills
  2. files ship beside it2,324 of 3,361 authors, 8,390 of 15,539 skills
  3. executable scripts ship inside993 of 3,361 authors, 2,473 of 15,539 skills

The folders they converge on

  1. references/1,477 of 3,361 authors, 4,289 of 15,539 skills
  2. scripts/815 of 3,361 authors, 2,053 of 15,539 skills
  3. agents/465 of 3,361 authors, 1,090 of 15,539 skills
  4. assets/392 of 3,361 authors, 830 of 15,539 skills
  5. examples/259 of 3,361 authors, 482 of 15,539 skills
  6. templates/235 of 3,361 authors, 394 of 15,539 skills

  • Od contribute

    nexu-io/open-design/.claude/skills/od-contribute Skill

    85,608★ repo

    🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen & 20+ CLIs via BYOK.

  • README

    alirezarezvani/claude-skills/.gemini/skills/README Skill

    24,478★ repo

    345 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 330+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.

  • Docx

    eigent-ai/eigent/resources/example-skills/docx Skill

    15,013★ repo

    Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex

  • Prompt master

    nidhinjs/prompt-master Skill

    11,108★

    A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention

  • Docs

    Agents365-ai/drawio-skill/docs Skill

    7,583★ repo

    Generate draw.io diagrams from natural language — 11 presets (UML, SysML/MBSE, BPMN, network, C4…), 36 tools: codebase/CI/infra-to-diagram, image→editable diagram, mind maps, build-up animation, exec-view compression, click-through runbooks, PR diff bot. Vision self-check, 10,000+ shapes. Exports PNG/SVG/PDF/JPG.

  • Bug report

    inkeep/open-knowledge/packages/server/assets/skills/bug-report Skill

    3,424★ repo

    Beautiful, AI-native markdown IDE and LLM wiki

  • Document review

    open-gitagent/opengap/examples/full/skills/document-review Skill

    2,907★ repo

    A framework-agnostic, git-native standard for defining AI agents

  • Oma academic writer

    first-fluke/oh-my-agent/.agents/skills/oma-academic-writer Skill

    1,226★ repo

    Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with your codebase, conventions, and engineering standards.

  • Clean code guard

    amElnagdy/guard-skills/skills/clean-code-guard Skill

    1,154★ repo

    Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs

  • Symbiotic onboard

    lout33/symbiotic-ai/skills/symbiotic-onboard Skill

    no license733★ repo

    A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.

  • Academic humanizer

    dongshuyan/compass-skills/skills/academic-humanizer Skill

    680★ repo

    司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents

  • Deeppapernote

    917Dhj/DeepPaperNote/skills/deeppapernote Skill

    591★ repo

    DeepPaperNote is an agent skill for deep-reading a single paper and generating high-quality Obsidian-style research notes. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

  • Adversarial spec

    zscole/adversarial-spec/skills/adversarial-spec Skill

    553★ repo

    A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.

  • Ln 21 documentation auditor

    levnikolaevich/claude-code-skills/plugins/codebase-audit-suite/skills/ln-21-documentation-auditor Skill

    535★ repo

    18 standalone skills for Claude Code and Codex: review, audit, optimization, testing, product discovery, and safe repository publishing.

  • Econ write

    hanlulong/econ-writing-skill/skills/econ-write Skill

    529★ repo

    Agent Skill that transforms AI assistants into expert economics paper writers. Synthesizes 50+ guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Kremer. Compatible with Claude Code and OpenAI Codex.

  • Cc changelog

    oliver-kriska/claude-elixir-phoenix/.claude/skills/cc-changelog Skill

    517★ repo

    Claude Code plugin for Elixir/Phoenix/LiveView — 20 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.

  • Ai sdk docs

    malob/nix-config/configs/claude/plugins/ai-sdk/skills/ai-sdk-docs Skill

    459★ repo

    My Nix system configs!

  • Docs

    YurunChen/repo-docs-skills/docs Skill

    no license447★ repo

    Living project docs for coding agents: keep guides, progress logs, change maps, and handoff context updated as your repo evolves.

  • Humanities writing companion

    tizzy916/humanities-writing-companion Skill

    no license357★

    End-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation.

  • Mcp documentation server

    andrea9293/mcp-documentation-server/io.github.andrea9293/mcp-documentation-server MCP server

    341★ repo

    Local-first document management and semantic search for AI coding agents

  • Daily progress report

    datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/1_DDC_Toolkit/Analytics/daily-progress-report Skill

    276★ repo

    221 AI skills for construction: BIM analysis, cost estimation, scheduling, document control, and automation with Claude Code

  • Executive summary

    modu-ai/cowork-plugins/moai-bi/skills/executive-summary Skill

    268★ repo

    모두의 AI (MoAI) — Claude Cowork & Claude Code 한국 실무 도메인 AI 하네스·플러그인 마켓플레이스. 사업계획서·세무·법률·HR·마케팅·커머스·BI·콘텐츠 도메인 스킬·에이전트·워크플로우. Korean B2B + office docs (HWPX/DOCX/XLSX/PPTX/PDF) + AI media (image/video/voice). AI-slop 검수 + humanize-korean 내장.

  • Article writing

    loulanyue/awesome-claude-notes/.cursor/skills/article-writing Skill

    264★ repo

    Community-maintained distribution of reusable AI coding agents, commands, skills, hooks, and cross-harness workflows.

  • Markdown exporter

    bowenliang123/markdown-exporter Skill

    261★

    An Agent Skill and Dify plugin to transform Markdown to files of DOCX, PPTX, XLSX, PNG, PDF, Mermaid, HTML, MD, CSV, JSON, XML.

  • Skills

    majiayu000/spellbook/plugins/rust-dev/skills/rust-best-practices Skill

    260★ repo

    Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

  • Okf

    scaccogatto/okf-skills/skills/okf Skill

    257★ repo

    The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Claude Code plugin + skills.sh.

  • Feishu docx

    leemysw/feishu-docx/.skills/feishu-docx Skill

    247★ repo

    🚀 Feishu/Lark Docs、Sheet、Bitable <-> Markdown | AI Agent-friendly knowledge base exporter and writer with OAuth 2.0, CLI, TUI & Claude Skills support - 飞书文档 <写入/导出> Markdown | AI Agent 友好型导出-写入工具

  • OrchestKit Docs MCP

    yonatangross/orchestkit/io.github.yonatangross/orchestkit MCP server

    218★ repo

    Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.

  • Mcp sap docs

    marianfoo/mcp-sap-docs/io.github.marianfoo/mcp-sap-docs MCP server

    213★ repo

    Fast MCP server for unified SAP docs search (SAPUI5, CAP, OpenUI5, wdi5) with BM25 full-text search

  • Document format skills

    KaguraNanaga/document-format-skills Skill

    211★

    Professional Word document formatting toolkit for Chinese documents

  • 00 start here

    AIDevGTM/gtm-cofounder/skills/00-start-here Skill

    209★ repo

    The GTM co-founder you don't have. Open-source GTM Agent Skills for technical AI/dev-tool founders building alone: positioning, first users, launch, pricing. Built from real dev-tool GTM experience, sharpened by Frankl & Czakon. MIT.

  • Prd

    golbin/agent-skills/skills/prd Skill

    no license209★ repo

    Reusable agent skills for Codex and compatible tools

  • Adr writer

    skrun-dev/skrun/agents/adr-writer Skill

    208★ repo

    Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistral/Koyeb — works with any LLM.

  • Query writing

    Idun-Group/idun-agent-platform/examples/tutorials/text-to-sql-deep-agent/skills/query-writing Skill

    198★ repo

    🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in.

  • Socrates skill

    bevibing/socrates-skill Skill

    197★

    Socratic method teaching skill for Claude Code — guides users to discover answers through questioning

  • Han release

    testdouble/han/.claude/skills/han-release Skill

    195★ repo

    Han: AI skills and agents for "Solo" product engineers and small teams

  • Publish report

    Amal-David/pagecast/.codex/skills/publish-report Skill

    186★ repo

    Publish HTML, Markdown and static mini apps to shareable Cloudflare Pages URLs from the terminal or coding agents.

  • Skill align

    techygarg/lattice/dev-skills/skill-align Skill

    176★ repo

    Install engineering discipline into any AI coding assistant. Composable skills for design, implementation, review, and team standards. Better process, not just better prompts.

  • Recallloom

    Frappucc1no/recall-loom/skills/recallloom Skill

    153★ repo

    Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.

  • Docx

    dog-qiuqiu/invincat/invincat_cli/built_in_skills/docx Skill

    153★ repo

    A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory management.

  • Chapter writing

    danjdewhurst/story-skills/skills/chapter-writing Skill

    149★ repo

    Agent Skills for end-to-end story writing in markdown, packaged as Codex and Claude Code plugins.

  • Grammar checker

    DaleSeo/korean-skills/skills/grammar-checker Skill

    129★ repo

    🇰🇷 Korean language skills for AI agents

  • Xhs writer skill

    JuneYaooo/xhs-writer-skill Skill

    125★

    小红书爆款笔记生成器，基于gpt-image-2，强力超快生成，自然语言修改，超好用！

  • Skill

    serradura/okf-gem/okf/lib/okf/skill Skill

    120★ repo

    Open Knowledge Format for coding agents. Author, validate, lint, search, and visualize portable Markdown knowledge bundles. One gem carries the agent skill, the CLI and Ruby library, and an interactive graph. Docker and Claude Code plugin included, 100% local.

  • Altimate code

    AltimateAI/data-engineering-skills/skills/altimate-code Skill

    118★ repo

    Skills related to Data Engineering Work for Claude Code

  • Docs mcp

    frumu-ai/tandem/ac.tandem/docs-mcp MCP server

    no license114★ repo

    Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.

  • Skills

    zaferayan/skills Skill

    no license113★

    Expo mobile app development skill for Claude Code

  • Social media caption generator claude

    rediumvex/social-media-caption-generator-claude Skill

    105★

    Social media caption generator as a Claude skill — turn any text, script, or screenshot into ready-to-post captions for Instagram Reels, Carousel, TikTok, Threads, Facebook, YouTube Shorts. Algorithm-optimized for shares, saves, and completion rate. Built by @theromanknox (280K+ IG).

  • Neo4j agent memory skill

    neo4j-contrib/neo4j-skills/neo4j-agent-memory-skill Skill

    101★ repo

    Neo4j Skills for Coding and other Agents including Cypher

  • En zh translation polish

    HoraceLuBFA/en-zh-translation-polish Skill

    98★

    英译汉翻译润色 · English→Chinese translate & polish skill (英中对照)

  • Unreal Engine API Documentation

    Codeturion/unreal-api-mcp/io.github.Codeturion/unreal-api-mcp MCP server

    92★ repo

    Accurate UE5 C++ API docs for AI agents. Prevents hallucinated signatures and includes.

  • Docs

    aws-samples/sample-strands-agents-agentskills/docs Skill

    90★ repo

    Agent Skills implementation for Strands Agents SDK

  • Fable audit

    deepklarity/harness-kit/.claude/skills/fable-audit Skill

    89★ repo

    A kit for building with AI agents and also the engineering patterns around it.

  • Cesium context7

    CesiumGS/cesium-ai-integrations/.github/skills/cesium-context7 Skill

    86★ repo

    Cesium AI Integrations is a collection of reference integrations and experiments connecting the Cesium ecosystem with AI systems including Model Context Protocol (MCP) tools, retrieval pipelines, and agent skills.

  • Ppt report skills

    myunwang/ppt-report-skills Skill

    85★

    A Claude Code skill for web report decks — richer ECharts charts, one file per slide (edit one page, save tokens), and complex structure diagrams. 16:9 & vertical, PDF/image export.网页版 PPT 汇报的 Claude Code skill：ECharts 把数据画得更好看、每页一个文件改一页省 token、能做复杂结构图（架构/框架/价值链）。16:9 + 竖屏，导出 PDF 和图片

  • Research innovation explorer

    foryourhealth111-pixel/research-innovation-explorer Skill

    85★

    The automated approach leverages the cross-combination of high-quality papers from top conferences to uncover feasible research and innovation ideas. Through multi-level verification and convergence screening, it identifies research schemes that are feasible and have in-depth value.

  • Sharp writing

    paleo/alignfirst/.agents/skills/sharp-writing Skill

    84★ repo

    Companion products for AI-assisted software work.

  • Promptguard

    mturac/promptguard/skills/promptguard Skill

    82★ repo

    Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.

  • Changelog observer

    claude-world/director-mode-lite/.claude/skills/changelog-observer Skill

    81★ repo

    Use Claude Code like a Director, not a Programmer. MIT toolkit with Auto-Loop, guided setup, 27 commands, 14 agents, and 32 skills.

  • Box0

    risingwavelabs/box0 Skill

    81★

    Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.

All 16,892 in the catalog