Writing and docs

23,646 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.

ccmds

2497

bjeber/cc-md-search-cli

Cursor rule Cursor needs its repo

Use when user asks about docs, documentation, guides, references, how-to, setup instructions, API reference, configuration, or says "check the docs", "what do the docs say", "find in documentation". Provides markdown search via ccmds CLI.

not rated 2 10d ago A 0 tokens original MIT

doc-library-cleanup

2498

Patrickjbagley/productManagerSkillandRules

Skill Claude CodeCodex

Keeps the project's document library consistent after new or changed PRDs and specs. Discovers or uses the project's index, README, feature/capability pages, and spec listings; proposes and applies updates so new docs are discoverable. Use when new docs are added or changed and the user wants index and related pages…

not rated 2 6mo ago A 81 tokens

rumi-run/ai-truthfulness-rules

Skill Claude CodeCodex

Use when answering strategic, executive, analytical, research, coding, business, financial, compliance, or high-impact questions where the AI must avoid generic trendy advice, separate facts from assumptions, challenge weak premises, compare options fairly, and make evidence, risks, uncertainty, and human verification…

not rated 2 4mo ago A 66 tokens original MIT

iceage-export

2502

pomagrenate/ice_age

Skill Claude CodeCodex

Exports the current chat session to a clean markdown file. Reconstructs the visible conversation from context — user messages, assistant responses, code blocks, tool output — formatted as readable .md. Use when user says "export chat", "save this conversation", "export to markdown", or invokes /iceage-export. Accepts…

not rated 2 4d ago A 73 tokens original Apache-2.0

weekly-report

2503

mikonos/cursor-skill-infra

Skill Claude CodeCodex

A Chinese-language workflow for creating or updating a weekly report with daily notes, links, open tasks, and action records.

not rated 2 7mo ago A 63 tokens original MIT

doc-everything-init

2504

rafaelszago/doc-everything

Cursor rule Cursor

Set up doc-everything in a Cursor project — install the docs-sync stop hook, scaffold the docs/features/ directory with an index, and (only if the defaults don't fit) write a doc-everything.json config so the hook watches the right paths. Apply once per repo when adopting doc-everything in Cursor, or when the stop…

not rated 2 1mo ago A 83 tokens original MIT

prompt-finder

2505

FeixueCode/prompt-finder

Skill Claude CodeCodex

Find a curated AI prompt template for any task — writing, image generation, video, or code. Use this skill when the user wants a ready-made prompt template (not a one-shot request). The skill queries a configurable prompt library backend via a documented /api/skill/ HTTP contract and returns the best match with…

not rated 2 4mo ago A 123 tokens original MIT

audit-reporting

2507

ALTEN-group/coding-pal

Skill Claude CodeCodex

Create predictable, actionable code-audit reports in a strict Markdown contract and validate them before publication. Use when an audit agent reports bugs, security findings, performance risks, or code-quality issues for CI workflows, GitHub issues, or other automated consumers.

not rated 2 11d ago A 54 tokens original MIT

manabuyasuda/dotfiles

Skill Claude CodeCodex

A paragraph-by-paragraph review process for Japanese documents that identifies claims, supporting reasons, connections, and opposing views. It is designed to clarify reasoning, not to guess what the writer intended.

not rated 2 5d ago A 137 tokens

engineered-writing

2509

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 3mo ago A 92 tokens

dissent-kit

2510

bharath-blazecode/dissent-kit

Skill Claude CodeCodex

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 18d ago A 70 tokens original MIT

changelog-formatting

2511

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 7mo ago A 41 tokens original MIT

plainspeak

2512

CoderSufiyan/plainspeak

Cursor rule Cursor

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

not rated 2 18d ago A 1,102 tokens original MIT

project

2513

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 3mo ago A 368 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 3mo ago A 64 tokens original MIT

obsidian-note-expert

2516

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 6mo ago A 37 tokens original MIT

humanizer

2517

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 6mo ago A 0 tokens

mcp-docs

2518

arjshiv/localutils-mcp-server

Cursor rule Cursor

Every MCP implementation must include Mermaid diagrams for.

not rated 2 8mo ago A 2 tokens original MIT

writing-readme

2519

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 5mo ago A ✓ AI review 47 tokens original MIT

aaai-skill

2520

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 1mo ago A 53 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: