Writing and docs

25,035 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.

engineered-writing

2545

hgzty1000/engineered-writing

Skill Claude CodeCodex

A writing workflow that treats a document like a software project: it gathers context, checks reference material while drafting, runs quality checks, and compares related pieces for consistency.

not rated 2 5mo ago A 92 tokens

dissent-kit

2546

bharath-blazecode/dissent-kit

Skill Codex

Give candid, verdict-first feedback on writing, plans, decisions, and arguments, then supply a concrete correction. Use Direct Review for ordinary critique. Use Deliberation only when the user requests it or the decision has material downside, competing values, or is hard to reverse. Do not use for factual lookups or…

not rated 2 2mo ago A 70 tokens original MIT

changelog-formatting

2547

mattppal/shipping-szn

Skill Claude CodeCodex needs its repo

Format changelog content according to Replit's changelog template structure. Use when converting raw changelog content into properly structured documentation with correct frontmatter, sections, and media formatting.

not rated 2 8mo ago A 41 tokens original MIT

plainspeak

2548

CoderSufiyan/plainspeak

Cursor rule Cursor

Plain Voice. Write like a human. No em dashes, no AI vocabulary.

not rated 2 2mo ago A 1,102 tokens original MIT

project

2549

lordmos/meridian

Cursor rule Cursor

A reusable toolkit for operating and promoting open-source projects, with instructions in Chinese. It covers project pages, documentation, branding, AI context, and search-related materials.

not rated 2 5mo ago A 368 tokens

wechat-article-writer

2550

Daniel123jia/wechat-article-generator-skills

Skill Claude CodeCodex

A Chinese writing skill that turns source material—such as a GitHub project, news event, academic paper, product experience, or tutorial—into a complete Markdown article.

not rated 2 changed 1mo ago A 68 tokens

Kinneyzhang/source-faithful-summary-skill

Skill Claude CodeCodex

Use when summarizing text, video transcripts, audio transcripts, podcasts, lectures, interviews, demos, or meetings where the output must preserve the source's main thread, attention weight, decision model, concrete examples, and evidence instead of becoming a polished but source-drifting essay.

not rated 2 5mo ago A 64 tokens original MIT

obsidian-note-expert

2553

LeoLB-Wang/pensieve-obsidian-skill

Skill Claude CodeCodex

Obsidian Knowledge Architect based on Progressive Summarization. Generates three-layer structure: Index -> Summary -> Detail. Always appends, never overwrites.

not rated 2 8mo ago A 37 tokens original MIT

humanizer

2554

ankshvayt/humanizer

Skill Claude CodeCodex

You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.

not rated 2 8mo ago A 0 tokens

mcp-docs

2555

arjshiv/localutils-mcp-server

Cursor rule Cursor

Every MCP implementation must include Mermaid diagrams for.

not rated 2 10mo ago A 2 tokens original MIT

writing-readme

2556

weiliu1031/writing-readme

Skill Claude Code

Use when creating or improving a README for any project — open source libraries, CLI tools, GUI applications, APIs, or internal tools. Triggers on: writing README, improve README, project documentation, onboarding docs.

not rated 2 7mo ago A ✓ AI review 47 tokens original MIT

aaai-skill

2557

CHB-learner/Awesome-Conference-Skills

Skill Claude CodeCodex

Use corpus-backed AAAI accepted-paper patterns to guide venue fit, paper structure, experiments, reproducibility, response planning, and presentation preparation. Use when preparing or auditing a AAAI-targeted conference paper, while separately verifying current official policy.

not rated 2 3mo ago A 53 tokens

one-pager

2558

ouachitalabs/skills

Skill Claude CodeCodex

This skill guides engineers through the process of creating a compelling one-pager proposal using the Heilmeier Catechism framework. The goal is not to immediately produce a document, but to thoroughly understand the problem space first, then distill that understanding into a single page that earns every word.

not rated 2 15d ago A 0 tokens original Apache-2.0

quarto-authoring

2559

Leev1s/skills

Skill Claude CodeCodex

Writing and authoring Quarto documents (.qmd), including code cell options, figure and table captions, cross-references, callout blocks (notes, warnings, tips), citations and bibliography, page layout and columns, Mermaid diagrams, YAML metadata configuration, and Quarto extensions. Also covers converting and…

not rated 2 4mo ago A 200 tokens CC-BY-4.0

deslop

2560

gopinav/skills

Skill Claude Code

Remove AI tells from copy. Finds and fixes the habits that make writing feel machine-generated (inflated importance, AI vocabulary, em-dash overuse, forced triplets, contrastive pivots, sterile rhythm) while keeping the meaning and the author's voice intact, then puts life back into the draft. Run explicitly with…

not rated 2 5mo ago A 85 tokens

polaralias/skills

Skill Codex

Use when the user says repository docs are stale, wrong, duplicated, scattered, or hard to search; asks where something is documented; wants a decision or glossary term written down properly; or when RCC exposes a gap in canonical docs. Maintains the trusted documentation, reading order, decisions, glossary, and…

not rated 2 10d ago A 113 tokens original Apache-2.0

ms-style-reviewer

2563

anaxite/agent-skills

Skill Claude CodeCodex

Review content against the Microsoft Writing Style Guide, reporting issues by severity (Critical/High/Medium/Low) with specific fixes. Use this skill whenever the user asks you to review, edit, or check text for compliance with Microsoft style, including documentation, UI strings, developer docs, blog posts, error…

not rated 2 2d ago A 93 tokens original

humanizer

2564

tgoapple/skills

Skill Claude CodeCodex

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…

not rated 2 3mo ago A 93 tokens

book-translation-guide

2565

madeyexz/ian-skills-agents

Skill Claude CodeCodex

Workflow for translating entire books using AI agents. Split markdown books into chapters, batch translate 5 at a time, and verify completeness. Works with any language pair.

not rated 2 8mo ago A 38 tokens

readme-design

2566

TimBeyer/agent-skills

Skill Claude CodeCodex

Design engaging, visually distinctive README.md files that stand out from generic boilerplate. Use when the user asks to create, redesign, or improve a README or project documentation landing page. Produces polished GitHub-flavored markdown with intentional structure, diagrams, and visual craft.

not rated 2 7mo ago A 58 tokens

pr-explain

2567

a1f/agent-templates

Skill Claude Code

Use when the user invokes /pr-explain or wants a reader-facing explainer page for a pull request. It is a plain-words page with five chapters. They are: what & why, a walkthrough of the whole diff, every test enumerated, a scored proof, and confirm commands run with their real output. It is published as a private…

not rated 2 2mo ago A 87 tokens original MIT

ez-explain

2568

caosiwei97/agent-skills

Skill Claude CodeCodex

A tool that turns one or more information sources into a new article written in simple language. It keeps the main facts and reasoning while using original wording, structure, and examples.

not rated 2 changed 2d ago A 236 tokens

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: