Writing and docs

23,615 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.

paper-agent

1538

Rekin226/paper-agent

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 246 tokens together

Draft, review, revise, proofread, and audit quantitative-science journal manuscripts at submission quality. Five strict modes, Semantic Scholar citation integrity, .docx round-trip.

not rated 8 19d ago A tokens not measured original MIT

obsidian-kb

1539

waelmas/codeplow

Plugin Claude Code

Bundles 8 skills, 8 commands · 1,094 tokens together

Persistent project memory for AI agents + documentation auditor - evidence-based detection of doc rot, powered by Obsidian vaults.

not rated 8 4mo ago A tokens not measured original MIT

esa-mcp-server

1540

kajirita2002/esa-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server for interacting with esa API. Runs locally from the @kajirita2002/esa-mcp-server npm package.

not rated 8 1y ago A tokens not measured original MIT

storyblok-mcp

1541

storyblok/mcp-server

MCP server Claude CodeCodexCursor +2

MCP server for Storyblok integration. Runs locally from the storyblok-mcp npm package.

not rated 8 5mo ago A tokens not measured archived

technical-writing

1542

liquidz00/jamfmcp

Cursor rule Cursor

You are an AI writing assistant specialized in creating exceptional technical documentation for the JamfMCP project using Sphinx with MyST Parser, sphinx-design, and pydata-sphinx-theme.

not rated 8 21d ago A 0 tokens original Apache-2.0

improve-claude-agents

1543

fkguo/nds-mcp

Skill Codex

Improve or normalize repository agent policy docs (CLAUDE.md, AGENTS.md) using a balanced workflow: conditional planning, required verification, scoped subagent usage, and lightweight lessons capture. Use when users ask to tighten agent execution rules, convert rigid rules into practical gates, align CLAUDE/AGENTS…

not rated 8 3mo ago A 79 tokens

text-toolkit

1544

Cicatriiz/text-toolkit

MCP server Claude CodeCodexCursor +2

Text Transformation & Formatting MCP Server for the Cline Marketplace. Runs locally from the @cicatriz/text-toolkit npm package.

not rated 8 1y ago A tokens not measured original MIT

grantmanship

1545

Tar-ive/grants-mcp

MCP server Claude CodeCodexCursor +2

MCP server "grantmanship" as configured in Tar-ive/grants-mcp. Runs locally from the grantmanship npm package.

not rated 8 1y ago A tokens not measured

mcp-bear-notes

1546

netologist/mcp-bear-notes

MCP server Claude CodeCodexCursor +2

MCP server "mcp-bear-notes" as configured in netologist/mcp-bear-notes. Runs locally from the mcp-bear-notes Python package.

not rated 8 1y ago A tokens not measured

humanizer-zh-tw

1548

nagameTW/humanizer-zh-tw

Plugin Claude Code

Bundles 1 skill · 183 tokens together

A Claude Code plugin for making Traditional Chinese writing sound more natural and less machine-generated.

not rated 8 1mo ago A tokens not measured original MIT

infocompressor

1549

OXI-717/ai-native-toolkit

Skill Codex

Use when the user needs to compress, condense, or summarize lengthy content while preserving ALL critical details. Triggers: "compress this", "make it shorter but keep everything", "create a cheat sheet", "dense summary", "reference format", "compact version", "information-dense". NOT for casual summaries—only when…

not rated 8 21d ago A 84 tokens original MIT

content-repurpose

1550

koinod/koino-skills

Skill Claude CodeCodex

Skill "content-repurpose" from koinod/koino-skills, covering content repurpose, description, activation, instructions and step 1: content analysis.

not rated 8 +1 3mo ago A 0 tokens original MIT

pitchdocs

1551

littlebearapps/pitchdocs

Plugin Claude Code

Bundles 16 skills, 15 commands, 4 agents · 1,402 tokens together

Generate high-quality public-facing repository documentation with a marketing edge. Creates READMEs that sell, changelogs that communicate value, roadmaps from GitHub milestones, and audits your docs completeness. Uses benefit-driven language, GEO-optimised structure, progressive disclosure, and the Banesullivan…

not rated 8 4mo ago A tokens not measured original MIT

readability-reviewer

1552

Agent-Engineer-Master/skill-engineer

Agent Claude Code

Independent readability auditor for analytical documents. Two-phase check — Phase A (cheap regex/grep for banned tokens, internal codes, passive voice, jargon) gates Phase B (model-eval for action titles, so-what, specificity-vs-abstraction, consultantese drift). Read-only — never edits the document. Re-invoke with a…

not rated 8 2mo ago A 95 tokens original MIT

seo-page-creator

1553

aiapplications001-art/seo-page-creator-agent

Skill Claude CodeCodex

Create brand-aware, E-E-A-T-oriented SEO page packets with company onboarding, product/category cluster strategy, Google read-only data inputs, image workflows, and CMS-friendly Markdown/JSON outputs.

not rated 8 21d ago A SkillSpector: pass 43 tokens original Apache-2.0

resumasher

1554

earino/resumasher

Command Claude Code

Tailor resume + cover letter + interview prep for a specific job posting.

not rated 8 4mo ago A 14 tokens original MIT

compact

1555

tinesoft/spec-kit-token-budget

Command Claude Code

Compact one or more Spec-Driven Development artifacts in place to reduce token cost on subsequent /speckit. commands. Lossless on requirements, decisions, contracts, IDs; strips template scaffolding, examples, and prose padding. The original is preserved as .full.md the first time an artifact is compacted.

not rated 8 2mo ago A 65 tokens original MIT

humanizer

1556

hannsxpeter/humanizer

Skill Claude Code

Humanize and de-slop AI-sounding prose while preserving meaning, specific detail, and genuine human quirks. When a voice sample or style profile is available, rewrite in that writer's actual voice. Remove recurring AI tells such as inflated significance, stock vocabulary, uniform rhythm, excessive hedging, formulaic…

not rated 8 +1 28d ago A 168 tokens original MIT

website-copywriting

1557

cobibean/shared-skills-registry-mcp

Skill Claude CodeCodex

Use when writing, rewriting, or critiquing website copy for homepages, landing pages, pricing pages, CTAs, product pages, and conversion flows. Produces persuasive, specific, proof-backed copy without fake urgency or trust-damaging pressure.

not rated 8 +1 2mo ago A 55 tokens original MIT

slop-cop

1558

howshannon/slop-cop

Skill Codex

Audit, grade, rewrite, and issue funny evidence-backed tickets for generic AI-slop patterns in prose, social posts, UI/design, and code. Use when asked to de-slop writing, humanize AI copy, grade a draft, review a landing page or generated interface, remove vague claims and repetitive rhetoric, inspect AI-written code…

not rated 8 +1 1mo ago A 101 tokens original MIT

stop-slop

1559

tomerose/stop-slop

Skill Claude CodeCodex

A writing-review workflow that removes common patterns associated with AI-generated prose.

not rated 8 +1 8d ago A 0 tokens

jingtian-style

1560

anhao/jingtian-style

Skill Claude CodeCodex

A Chinese-language rewriting tool based on the first-person, accounting-style prose associated with the essay “My Girlfriend Jing Tian.” It changes how existing material is expressed, not the underlying story.

not rated 8 16d ago A 176 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: