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.

tech-decision

1057

kcwoodfield/LifeOS-OSS

Skill Claude Code

Triggers: "Help document this technical decision", "Create ADR", "Technical decision record", "Document this architecture decision".

not rated 20 7mo ago A 0 tokens

humanizer

1058

newstler/template

Skill Claude Code

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 20 yesterday A 92 tokens

mine-design

1059

ProsusAI/prism

Skill Claude CodeCodex

Extract design decisions, trade-offs, and non-obvious behaviors from a codebase's current source code. TRIGGER when: starting the design analysis pipeline, running /mine-design (Claude Code) or @mine-design (Cursor) before /synthesize-decisions (Claude Code) or @synthesize-decisions (Cursor), capturing the reasoning…

not rated 20 2mo ago A 97 tokens original Apache-2.0

subtext-annotate

1060

TheoryVentures/subtext-skills

Skill Claude CodeCodex

Convert raw text (emails, meeting notes, markdown documents, pasted prose) into a subtext JSON document — a sentence-level document tree where every sentence has a stable ID and metadata — then interview the user with clarifying questions about anything a reader might find unclear, attaching the answers to the exact…

not rated 20 1mo ago A 100 tokens original MIT

生成求职文档

1061

Shilren/interview-doc-agent

Skill Claude CodeCodex

A job-application document generator for product managers and other applicants. It uses an experience library and templates to create resumes, interview scripts, and versions tailored to a job description.

not rated 20 3mo ago A 99 tokens original MIT

xhs-notes-skill

1062

azlll/xhs-notes-skill

Skill Claude CodeCodex

A writing assistant for 小红书 (Xiaohongshu), a Chinese social platform for image-and-text posts. It describes workflows and individual functions for creating, reviewing, and breaking down posts.

not rated 20 2mo ago A 165 tokens original MIT

extract

1063

zby/llm-do

Skill Claude Code

Extract structured knowledge from source material. Two modes — extract (default) for comprehensive atomic claim extraction, and analyze for design proposals where one impact-analysis note replaces claim decomposition. A relevance filter ("does this change how we build our project?") applies to all modes. For extract…

not rated 20 6mo ago A 102 tokens

prd-assistant

1064

AB-Lindex/github-copilot

Agent Claude Code

Product Requirements Document generator for your project. Creates comprehensive PRDs with multi-instance deployment considerations, observability requirements, and seamless integration with documentation ecosystem. Serves both technical teams and AI agent consumption. Cloud-agnostic with automatic provider detection.

not rated 20 6mo ago A 48 tokens

agent-academic-writer

1065

nguyenvanduocit/research-kit

Agent Claude Code

Academic writing specialist for creating publication-ready research outputs. Use when writing research papers, reports, executive summaries, or any formal research documentation. Handles citations, formatting, and academic style.

not rated 20 6mo ago A 42 tokens fork MIT

korean-prose

1066

JellyBrick/korean-prose-skill

Skill Codex

A skill for writing and editing natural, consistent Korean prose. It covers commit and pull-request text, README files, technical documentation, interface wording, and multi-line code comments.

not rated 20 4d ago A 125 tokens

interactive-fiction

1067

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 20 13d ago A 54 tokens original MIT

great-writer

1068

d-wwei/great-writer

Skill Claude CodeCodex

Universal writing skill for AI agents. 9 writing modes (tech articles, marketing copy, research reports, Xiaohongshu notes, technical docs, GitHub READMEs, creative writing, rewrite/polish, editorial review) + 9 core modules (research, core-finding, writing DNA, humanizer/polish, review, style learning, adaptation…

not rated 20 +1 5mo ago A 104 tokens original MIT

grounded-copy

1069

HiroHyun/grounded-copy

Plugin Claude Code

Bundles 1 skill, 1 command · 74 tokens together

Puts the grounded prose ruleset in session context at startup and repeats a one-line reminder each turn, so the rules reach chat replies as well as copy tasks.

not rated 20 +3 changed 3d ago A tokens not measured original AGPL-3.0

prd-writer

1070

Panix22/prd-writer-skill

Skill Claude CodeCodex

A guided process for discovering a product idea and writing a PRD, or product requirements document. A PRD records what should be built, for whom, and how it should work.

not rated 20 +1 3mo ago A 119 tokens original MIT

silly-geese/estonian-mcp

Skill Claude CodeCodex

Use this skill whenever the user is writing, editing, proofreading, or studying Estonian text and the estonian-mcp connector is available — even if they don't explicitly ask. Covers proofreading (spellcheck first, then verify lemma and case forms via lemmatize and analyzemorphology on uncertain words), tone-aware…

not rated 20 +1 changed 5d ago A SkillSpector: pass 294 tokens original Apache-2.0

linkedin-cringe

1072

matteobaccan/LinkedInCringe

Skill Claude Code

Genera post LinkedIn cringe (italiano di default, ma funziona in qualunque lingua), calibrati su livello di cringe (1-10), registro (credibile / parodico / surreale deadpan alla Lynch) e moduli cringe scelti da un catalogo di 47, con la possibilità di partire da un fatto reale (una notizia data dall'utente o cercata…

not rated 20 +1 changed yesterday A SkillSpector: pass 157 tokens original MIT

webhook-docs-brief

1073

bytebear7286-32ffw/webhook-docs-brief

Skill Claude CodeCodex

A guide for writing documentation for outbound webhooks, which are automatic messages a service sends to another system when an event occurs. It covers events, message data, signature checks, retries, duplicate handling, and examples.

not rated 20 1mo ago A 114 tokens original MIT

npo-program-sop

1074

bytehawk1990-v9786/npo-program-sop

Skill Claude CodeCodex

A standard operating procedure for running a small nonprofit education or community program. It covers steps, staff roles, supplies, child safety, limited data collection, emergencies, and a checklist.

not rated 20 +1 1mo ago A 117 tokens original MIT

daily-reporter-skill

1075

freestylefly/daily-reporter-skill

Skill Claude CodeCodex

A reporting assistant that turns scattered work notes, meeting records, and chat messages into structured daily, weekly, or monthly reports. It groups work by results, progress, routine tasks, risks, and learning.

not rated 20 5mo ago A 159 tokens original MIT

resume-generator

1076

Alenryuichi/openmemory-plus

Skill Claude CodeCodex

A résumé-generation workflow that extracts work experience from project documents and writes it in JSON Resume format. It uses the XYZ pattern: what was achieved, how it was measured, and how it was done.

not rated 20 6mo ago A 67 tokens original MIT

laconic

1077

GabrielBarberini/laconic

Plugin Claude Code

Bundles 1 skill · 39 tokens together

Brief prose. Short common words. Trust context. State what matters. Omit what reader can infer.

not rated 19 2mo ago A tokens not measured original MIT

finnish-humanizer

1078

Hakku/finnish-humanizer

Skill Claude Code

Tunnistaa ja poistaa AI-generoidun suomenkielisen tekstin tunnusmerkit. Tekee tekstistä luonnollisempaa ja ihmisen kirjoittaman kuuloista. Käytä pyyntöihin humanisoimaan tai "tee paremmaksi".

not rated 19 4mo ago A 63 tokens original MIT

Lambenthan/paper-discipline-skills

Skill Claude CodeCodex

Instructions for checking that a research paper's main claims, assumptions, methods, and conclusions remain logically consistent after edits.

not rated 19 4mo ago A 155 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: