Writing and docs

31,820 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.

solomd

145

zhitongblog/solomd

Skill Claude CodeCodex

Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server. 13 tools including AutoGit per-note history, semantic search, and write-with-sandbox via an accept/reject branch. Includes 11 starter agent recipes (weekly review, todo extract, link suggester, …).

not rated 999 +40 today A 69 tokens original MIT

satus AGENTS.md

146

darkroomengineering/satus

Instructions file CodexOpenCode

AGENTS.md instructions for darkroomengineering/satus, covering agents.md - satus engineering standards, stack, enforced rules (ci fails without these), oxlint rules and typescript strict flags (all active in tsconfig.json).

not rated 984 +4 changed yesterday A 6,828 tokens original MIT

pr-comment

147

MadAppGang/claudish

Skill Claude CodeCodex

Write GitHub PR comments in Jack's voice. Use whenever writing, drafting, or posting PR comments — review feedback, thank-you notes, merge comments, close explanations, or change requests. Also use when the user asks to "comment on PR", "review PR", "thank contributor", "close PR", or "write PR feedback". Always use…

not rated 980 +5 yesterday A 90 tokens

draft-release-blog

148

obot-platform/obot

Skill Claude CodeCodex

Draft a release announcement blog post for an obot release, modeled on the existing obot.ai blog voice. Use when the user asks to draft a release blog, write a launch post, or write a blog announcement for a vX.Y.0 release. Outputs a markdown file the user can paste into the CMS. Can also create the post as a…

not rated 976 +8 today A 101 tokens original MIT

imcodes CLAUDE.md

149

im4codes/imcodes

Instructions file

Claude Code instructions for im4codes/imcodes, covering claude.md, commands, build & typecheck, tests (vitest workspace) and server (self-hosted backend).

not rated 973 today A 2,917 tokens original MIT

agent-md-verify

150

iamfakeguru/agent-md

Skill Claude CodeCodex

Use when finishing work in a repository that has agent-md installed; runs the declared checks, updates memory/progress.md, and reports concrete verification evidence instead of self-grading.

not rated 966 4mo ago A 40 tokens original MIT

baibaiAIGC

151

poleHansen/baibaiAIGC

Skill Claude CodeCodex

A text-rewriting skill for Chinese and English technical or academic writing. It uses different rewriting steps and prompt files for each language.

not rated 955 +3 3mo ago A 101 tokens AGPL-3.0

create-notes

152

Human-Agent-Society/CORAL

Skill Claude CodeCodex

Write a note to {shareddir}/notes/ that future agents can actually act on. Use after every coral eval, when a heartbeat (reflect / consolidate / pivot) asks for a note, or when you discover a grader / build / runtime issue that future agents will hit. Covers 4 note variants (experiment / infra / focus / synthesis)…

not rated 951 +12 5d ago A 217 tokens original Apache-2.0

microsoft/wassette

Agent ✓ vendor

Specialized agent for creating, updating, and maintaining Wassette project documentation using mdBook.

not rated 941 +3 2d ago A 21 tokens original MIT

book-internalize

154

wordflowlab/novel-writer

Command

A command that turns book-analysis reports into reusable writing guidance for a Novel Writer project. It creates style, structure, and rhythm configuration files that later writing commands can use.

not rated 939 +5 10mo ago A 0 tokens original MIT

devanshutak25/3d-resources

Instructions file

Claude Code instructions for devanshutak25/3d-resources, covering 3dresources — project rules, project.md (mandatory), controlled vocabulary (entry tags), validation and writing style (user-facing text).

not rated 931 +4 2d ago A 1,067 tokens original CC0-1.0

speak-human-tw

156

Raymondhou0917/speak-human-tw

Skill Claude CodeCodex

A Traditional Chinese editing guide for making public-facing writing sound more natural and less machine-generated. It also checks wording associated with Mainland China and half-width punctuation.

not rated 932 +24 yesterday A 220 tokens original MIT

beans-release-notes

157

hmans/beans

Command Claude Code

Generate release notes from commits since the last version tag and write them to .docs.local/RELEASE.md.

not rated 915 +4 5mo ago A 0 tokens original Apache-2.0

ReadMeABook CLAUDE.md

158

kikootwo/ReadMeABook

Instructions file

Claude Code instructions for kikootwo/ReadMeABook, covering claude.md - project standards & workflow, 1. token-efficient documentation system, why token efficiency matters, documentation structure and 2. using tableofcontents.md (mandatory).

not rated 913 +6 17d ago A 2,624 tokens AGPL-3.0

mantis-calibrate

159

google/mantis

Skill Claude CodeCodex ✓ vendor

Calculates the final risk score based on empirical evidence and architectural impact. Use when findings have been fully processed by previous stages and you need to append final risk scores to the finding files. Don't use for discovering new vulnerabilities or writing patches.

not rated 927 +124 2d ago A 52 tokens original Apache-2.0

huashu-md-html

160

alchaincyf/huashu-md-html

Skill Claude CodeCodex

A document publishing workflow that converts Markdown, a plain-text writing format, into polished web pages and other document formats. It also converts several document and media types into Markdown.

not rated 899 +6 11d ago A 131 tokens original MIT

coji/natural-japanese

Instructions file CodexOpenCode

Repository instructions for a Japanese-language writing skill that helps produce clear business documents, reports, notes, blogs, and essays.

not rated 958 +364 changed today A 757 tokens original MIT

react-svg AGENTS.md

162

tanem/react-svg

Instructions file CodexOpenCode

AGENTS.md instructions for tanem/react-svg, covering agents.md, writing, architecture, build & test and releases.

not rated 883 5d ago A 1,330 tokens original MIT

governance

163

rush86999/atom

Agent

Agent "governance" from rush86999/atom, covering agent governance system, 🆕 2026 enhanced governance, operational layer (fast, automated), architecture and core components.

not rated 883 +4 changed yesterday A 0 tokens AGPL-3.0

nuwax AGENTS.md

164

nuwax-ai/nuwax

Instructions file CodexOpenCode

Repository instructions describing an AI-assisted web IDE that communicates through SSE, a way to stream live events between a server and browser. They cover file management, development servers, chats, sessions, and tool calls.

not rated 879 +3 yesterday A 5,807 tokens original Apache-2.0

scientific-writing

165

LeonChaoX/qinyan-academic-skills

Skill Claude CodeCodex

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting…

not rated 867 +14 1mo ago A 87 tokens original MIT

TalEliyahu/Awesome-AI-Security

Instructions file CodexOpenCode

Instructions for TalEliyahu/Awesome-AI-Security, covering scope, house style (must), github stars (when used), sorting and conflicts.

not rated 862 +3 1mo ago A 759 tokens original MIT

prompt-factory

168

alirezarezvani/claude-code-skill-factory

Skill Claude CodeCodex

World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory…

not rated 856 +1 9mo ago A 118 tokens 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: