Writing and docs skills

17,386 tagged Writing and docs, measured the same way as everything else here.

Browse within: agent 183LLM 147skills 85agents 83agentic-ai 82cli 81ai-tools 69seo 63javascript 54ai-coding 49openclaw 45ai-skills 44cursor 44claude-code-plugin 41

source-reading

337

itshen/source-reading-methodology

Skill Claude CodeCodex

A source-code reading method for understanding a large open-source repository and turning it into documentation, a course, or a book. Every technical claim is tied to exact lines in the repository.

not rated 135 +2 17d ago A 229 tokens original MIT

book_writer

338

kandada/aacode

Skill Claude CodeCodex

Guided multi-phase book writing: outline → storyline → chapter-by-chapter writing with verification → final consistency review and polish.

not rated 134 16d ago A 0 tokens GPL-3.0

sales-ai-assistant

339

isjiamu/jiamu-skills

Skill Claude CodeCodex

A Chinese-language sales assistant that turns a business situation into a structured request and sales content. It can create materials such as emails, proposals, and analysis reports.

not rated 134 +2 1mo ago A SkillSpector: pass 38 tokens original MIT

recipe-generator

340

cclank/recipe-generator

Skill Claude CodeCodex

A Chinese-language recipe-writing skill that researches cooking methods and produces detailed recipes, instructions, tips, and prompts for traditional Chinese-style recipe posters.

not rated 133 6mo ago A 98 tokens

auto-improve

341

crimeacs/auto-improve

Skill Claude Code

GAN-style iterative improvement loop for any text artifact. Mutates a file, grades each change against a rubric with a SEPARATE model, keeps only verified wins (pairwise-judged), reverts the rest. The git history is the improvement log. Use when the user wants to autonomously improve the quality of a document, email…

not rated 133 1mo ago A 87 tokens original MIT

architect-implement

342

tikalk/adlc-team-skills

Skill Claude Code

Generate a full Architecture Description (AD.md) from accepted ADRs using multi-agent DAG orchestration. Use when accepted ADRs exist and you need to produce or update unified architecture documentation.

not rated 133 +1 changed 4d ago A SkillSpector: warn 41 tokens original MIT

nature-writing

343

SyntaxSmith/nature-writing-skill

Skill Claude CodeCodex

A Chinese-language academic writing skill for AI and machine-learning researchers preparing papers for Nature journals. It focuses on story, structure, and writing quality for venues such as Nature Machine Intelligence and Nature Communications.

not rated 133 +11 4mo ago A 283 tokens

humanAIzer

345

aiskilloftheweek/claude-ai-skill-of-the-week

Skill Claude CodeCodex

Rewrites AI-generated text to sound like it was written by a real human being. Use this skill every time the user provides a text and asks to humanize it, remove AI tells, make it sound more natural, less robotic, or more authentic. Trigger on phrases like "humanize this", "make this sound human", "remove AI writing…

not rated 130 +1 3mo ago A 142 tokens

use-case-writer

346

phucnt-bazone-vietnam/use-case-writer

Skill Claude CodeCodex

Generate Use Case specifications in English Markdown following the IT BA standard 13-field template (Karl Wiegers / IIBA). Use whenever a BA needs to scope, analyze, document, refine, or review a Use Case. Triggers include "write a use case", "draft UC", "use case specification", "analyze UC scope", "split feature…

not rated 128 +3 3mo ago A 239 tokens

aigc-detector

347

free-revalution/AIGC-Detector-Pro

Skill Claude Code needs its repo

Academic paper AI content detection, rewriting, and thesis writing assistant. Analyzes text for AI-generated characteristics, provides detailed rewrite suggestions, and generates full thesis drafts. Supports .docx files, outputs reports and rewritten/formatted documents. Bilingual: Chinese & English.

not rated 128 +3 3mo ago A 60 tokens original MIT

qingsheng

348

tomwong001/qingsheng-skill

Skill Claude CodeCodex

A Chinese-language assistant for social and romantic conversations. It interprets messages or screenshots and suggests replies, invitations, or next steps across services such as WeChat, Tinder, and Bumble.

not rated 128 +2 4mo ago A 269 tokens original MIT

blog_creator

349

liuyueyi/spring-ai-demo

Skill Claude CodeCodex

A writing aid for creating technical blog posts that explain software and other technical subjects in accessible language.

not rated 127 +2 1mo ago A 48 tokens

anti-slop-writing-id

350

adenaufal/anti-slop-writing

Skill Claude CodeCodex

Tulis teks yang menghindari semua pola penulisan AI dan terasa seperti ditulis manusia. Gunakan saat menulis artikel, esai, posting blog, konten media sosial, atau teks apa pun dalam Bahasa Indonesia yang harus terasa autentik. Aktif saat ada permintaan untuk menulis secara natural, menghindari slop AI, menghindari…

not rated 127 +3 2mo ago A SkillSpector: pass 106 tokens original MIT

docs-ssot

351

hiromaily/go-crypto-wallet

Skill Claude Code needs its repo

Set up docs-ssot SSOT documentation structure — migrate existing docs, build, and validate.

not rated 127 4mo ago A 24 tokens original MIT

api-doc-writing

352

datawhalechina/easy-data-x-ai

Skill Claude CodeCodex

Write clear and consistent API documentation following team standards. Use when creating or editing REST API reference docs.

not rated 126 +8 8d ago A 24 tokens

master-thesis-studio

353

darksider-9/master-thesis-studio-skill

Skill Claude CodeCodex

Use this skill for Southeast University-style master's thesis projects from a Word template or existing draft, including optional reverse parsing of an existing DOCX, user intake, outline planning, chapter drafting, academic asset management, Markdown visualization, references, figures, tables, formulas, and safe DOCX…

not rated 124 +2 4mo ago A 70 tokens original MIT

podcast-to-course

354

Cobb04/podcast-to-course

Skill Claude CodeCodex

Turn any podcast transcript into reusable AI judgment assets — structured frameworks, decision checklists, interview talking points, and an optional interactive HTML course. Use this skill whenever someone wants to extract actionable knowledge from a podcast episode, systematize an interview, build AI product…

not rated 124 1mo ago A 151 tokens

ma-manuscript-quarto

355

htlin222/meta-pipe

Skill Claude CodeCodex

Draft and render a meta-analysis manuscript with Quarto using an IMRaD structure and embedded figures/tables. Use when preparing the final paper from analysis outputs.

not rated 123 +1 yesterday A 39 tokens

typst

356

lucifer1004/claude-skill-typst

Skill Claude CodeCodex

Typst document creation and package development. Use when: (1) Working with .typ files, (2) User mentions typst, typst.toml, or typst-cli, (3) Creating or using Typst packages, (4) Developing document templates, (5) Converting Markdown/LaTeX to Typst.

not rated 123 +1 changed 5d ago A Socket: passSnyk: passSkillSpector: warn 71 tokens original MIT

repo-to-resume-tailor

357

Ssabby1/repo-to-resume-tailor

Skill Codex

Analyze a full code repository and generate one resume-ready project description grounded in repository evidence. Use when Codex is asked to turn a repository into concise project bullets, project summaries, or tailored experience based on either a target role direction or a specific job description for backend, AI or…

not rated 123 +2 4mo ago A 80 tokens original MIT

writing-spec

358

bartstc/vite-ts-react-template

Skill Claude CodeCodex

Collaboratively write a feature spec with the developer. Trigger when a task involves 5+ unconstrained decisions, spans 10+ files, or the developer explicitly asks for a spec. Do NOT trigger for config edits, CSS fixes, helper functions, exploratory prototyping, presentation-only changes, or when the developer…

not rated 121 1mo ago A SkillSpector: warn 69 tokens original MIT

Soul-Brews-Studio/arra-oracle-skills-cli

Skill Claude CodeCodex

Write a complete book from scratch — outline, parallel Sonnet drafting, Thai word break, typst PDF rendering, review, title brainstorm, publish to GitHub. Two size targets: standard <=100 pages (8-12 chapters), short <=50-60 pages (5-8 chapters). Pipeline proven on 'The Oracle Pattern'. TRIGGER when: user says…

not rated 121 4d ago A SkillSpector: warn 139 tokens original MIT

good-story

360

Rimagination/good-story

Skill Claude CodeCodex

Use when the user asks to find, sharpen, evaluate, rewrite, or explain the story in scientific or scholarly materials across disciplines, including manuscripts, grants, paper outlines, abstracts, figures, results, discussions, cover letters, research pitches, high-impact writing, journal fit, significance, novelty…

not rated 120 +5 2mo ago A 73 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: