Writing and docs

25,000 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

mcp-server-readme

865

redcrab2819-ack84/mcp-server-readme

Skill Claude CodeCodex

A writing skill for creating public README files for MCP servers. MCP, the Model Context Protocol, is a standard for connecting AI agents to tools and data; the README explains installation, authentication, capabilities, and risky actions.

not rated 38 3mo ago A 102 tokens original MIT

interactive-fiction

866

Treasure-hub-agent/interactive-fiction-skill

Skill Claude CodeCodex

A Chinese-language skill for creating choice-driven interactive fiction, or stories where the reader selects what happens next. It covers story setup, consistent viewpoints, saved games, and character profiles.

not rated 38 changed 19d ago A 85 tokens original MIT

content-guidelines

867

MetaMask/metamask-design-system

Cursor rule Cursor

MetaMask content design rules for user-facing strings — capitalization, punctuation, voice, tone, and terminology. Component-specific copy rules live in each component's README (read via Storybook MCP).

not rated 38 yesterday A 0 tokens

infostyle-skill

868

artgas1/infostyle-skill

Plugin Claude Code

Bundles 1 skill · 133 tokens together

Edit Russian text using Ilyakhov's information style. Removes stop-words, cliches, bureaucratic language. Replaces with concrete facts and numbers.

not rated 37 +2 7mo ago A tokens not measured original MIT

bys-work-report

869

qkgecn93/bys-work-report

Skill Claude CodeCodex

A Chinese-language writing assistant for workplace reports such as daily updates, project reviews, promotion documents, and year-end summaries. It turns scattered work details into concise, checkable points and marks information that is missing.

not rated 37 3mo ago A 549 tokens original MIT

brief-me

870

jinhanbuilds/brief-me

Skill Codex

A reporting workflow that turns a long, complex analysis into an interactive HTML briefing for a decision-maker. It organizes conclusions, evidence, comparisons, and visual explanations around a specific decision.

not rated 37 changed 1mo ago A SkillSpector: pass 76 tokens original MIT

agents-spec

871

leftzzzz/agents-spec-skill

Skill Codex

Audit, reorganize, split, migrate, and maintain AGENTS.md, optional platform instruction files, and current-only engineering Specs with cross-agent routing and SDD-aligned docs/specs, docs/requirements, and docs/technical directories. Use when cleaning up agent instructions, organizing engineering standards…

not rated 37 changed 1mo ago A SkillSpector: warn 121 tokens original MIT

writing-with-agents

872

Jeffallan/writing-with-agents

Plugin Claude Code

Bundles 10 skills · 368 tokens together

10 specialized writing skills implementing Betty Flowers' Madman-Architect-Carpenter-Judge framework with Bryan Garner's whirlybird technique, SEO optimization, quality rubric, and multi-article content strategy. Features collaborative oscillation between AI and human across all phases.

not rated 37 changed 23d ago A tokens not measured original MIT

problem-based-srs

873

RafaelGorski/Problem-Based-SRS

Plugin Claude Code

Bundles 2 skills · 230 tokens together

Problem-Based Software Requirements Specification methodology for AI-assisted requirements engineering. Provides structured approach to capture Customer Problems (WHY), Customer Needs (WHAT), and Functional Requirements (HOW) with full traceability.

not rated 36 changed 1mo ago A tokens not measured original MIT

ad-creative-paid-ads

874

ItamarZand88/awesome-agent-conventions

Skill Claude CodeCodex

Skill "ad-creative-paid-ads" from ItamarZand88/awesome-agent-conventions, covering ad creative, before starting, 1. product & offer, 2. audience and 3. platform & stage.

not rated 36 +1 3mo ago A 0 tokens original MIT

newsletter-writer

875

travsteward/openwriter

Skill Claude CodeCodex

Channel-master writer for email newsletter. Weekly pipeline: scaffold structure, gather data, query the author, synthesize in their voice, review, send. Companion doc workflow. Voice-matched via the authors-voice skill. Works for any behind-the-scenes weekly newsletter built on proven content. Use when…

not rated 36 changed 23d ago A 118 tokens original MIT

deprecation-notice

876

fastlion2018-tpwqr/deprecation-notice

Skill Claude CodeCodex

A communication pack for telling users that an API, software-development tool, or product feature will be removed or replaced. It covers dates, the replacement, the period when both versions work, and notices for different channels.

not rated 36 3mo ago A 109 tokens original MIT

thread-writer

877

bytecrab1524-1h8bx/thread-writer

Skill Claude CodeCodex

A writing tool that turns long posts, product releases, or ideas into short, connected posts for X, Jike, or Threads. A thread is a sequence of posts that develops one idea across several updates.

not rated 36 3mo ago A 81 tokens original MIT

zhy-wechat-writing

878

zhylq/yuan-skills

Skill Claude CodeCodex

Use when generating a complete WeChat article from a topic, with optional source research, evidence tracking, illustration, HTML conversion, and draft-box publishing.

not rated 35 7mo ago A 36 tokens original MIT

reviewwrite

880

songhai-dg/review-write

Skill Codex

Review before rewriting Chinese or English professional prose, then optionally audit DOCX/PPTX delivery typography and render gates. Use for academic papers, grant proposals, public articles, policy briefs, policy documents, reports, official documents, executive memos, marketing copy, bilingual writing…

not rated 35 changed 2mo ago A 116 tokens original MIT

brand-voice

881

TribeAI/claude-cowork-brand-voice-plugin

Plugin Claude Code

Bundles 3 skills, 3 commands, 5 agents, 7 MCP servers · 1,509 tokens together

Transforms scattered brand documents and conversation transcripts into enforceable AI guardrails. Searches across Confluence, Google Drive, Box, SharePoint, Slack, and conversation intelligence platforms like Gong and Granola to discover how your company actually communicates. Creates LLM-ready brand guidelines and…

not rated 35 5mo ago A tokens not measured original MIT

scalvert/docusaurus-plugin-mcp-server

Skill Claude CodeCodex

Expose a Docusaurus site's docs as an MCP server for AI agents — add the build-time plugin, deploy the MCP endpoint to any web-standard serverless/edge runtime, run it locally, serve Agent Skills over MCP, or add the install button. Load when working with docusaurus-plugin-mcp-server or its /adapters or /theme entry…

not rated 35 changed 7d ago A SkillSpector: pass 81 tokens original MIT

COMMANDS

883

yzyydev/agentic-coding-structure

Command Claude Code

The .claude/commands/ directory provides a powerful mechanism for creating and invoking custom commands within Claude Code. These commands allow users to streamline repetitive operations, standardize workflows, and create reusable templates for Claude Code interactions.

not rated 35 1y ago A 0 tokens

smart-blog-skills

886

rainday/smart-blog-skills

Plugin Claude Code

Bundles 35 skills, 8 agents, 1 hook · 4,434 tokens together

Anti-hallucination blog engine with 34 sub-skills: write, analyze, rewrite, outline, schema, seo-check, geo, image, audio, repurpose, factcheck, cannibalization, persona, taxonomy, translate, localize, multilingual, locale-audit, audit, flow, notebooklm, google, monitor, strategy, cluster, brief, calendar, llmstxt…

not rated 34 5mo ago A tokens not measured

oh-my-writing-skill

887

z0gSh1u/oh-my-writing-skill

Plugin Claude Code

Bundles 9 skills · 514 tokens together

Multi-platform content creation system for Chinese content - from research and image sourcing to writing, humanizing, and platform-specific formatting for Zhihu, Xiaohongshu, and WeChat.

not rated 34 8mo ago A tokens not measured original MIT

claude-writing-skills

888

xiaomoBoy/claude-writing-skills

Plugin Claude Code

Bundles 5 skills · 379 tokens together

Claude Code skills for long-form content workflow: research collection via NotebookLM, multi-platform publishing via wechatsync, viral-score evaluation, single-article rewrite loops, and yt-dlp media helpers.

not rated 34 5mo ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: