Writing plugins

Remove AI writing patterns — strips corporate filler, hedging, and statistical-middle language from any text

1 skill

Guides you through writing your own technical document instead of generating one for you. Covers design docs, RFCs, ADRs, runbooks, postmortems, specs, PRDs, proposals (change proposals included), one-pagers, project plans and briefs, READMEs, and more.

1 skill

Read a document in order like a first-time reader and report on pacing, boredom, unmet setups, and clarity

1 skill

Draft and revise multi-paragraph prose in the author's established voice. With no supplied voice, uses a plainspoken fallback house style while preserving factual claims, uncertainty, caveats, quotations, and deliberate punctuation. Optional visual revision reports are reconstruction-verified and explicit opt-in.

1 skill

Discover your real writing voice through impromptu writing exercises, then package it as a reusable 'write like me' skill.

1 skill

Keeps AI-slop patterns out of READMEs, landing pages, social posts, commit messages, blog posts and emails.

1 skill

A Claude Code plugin that helps authors draft and edit in their own voice — captures style, expands sketches into prose, and runs targeted review passes.

Write Star Wars Old Republic stories with a literary toolkit, era-aware lore, and an interactive project dashboard.

25 skills · 26 commands · 39 agents

Plan, build, draft, and revise novels: a deep planning interview, story bible, outlining, worldbuilding, characters and voices, drafting, editing, custom author style, and fantasy/sci-fi/YA craft.

29 skills · 11 agents

English coach for non-native speakers: a UserPromptSubmit hook shows the corrected English of each prompt, translates prompts in other languages, and refines :: prompts, and Codex works from the clean version. Corrections are logged locally for $claude-english-buddy-today, -stats, -mistakes and -drill; $claude-english-buddy-review and -preview check any text for grammar, tone and clarity. The hook calls Claude Haiku with your own Anthropic credentials and runs once you trust it with /hooks.

23 skills · 10 commands · 4 agents · hooks

Evidence-traceable writing and review, literature search and citation handling, and document processing across PDF, Word, PowerPoint and Markdown. Skills vendored from K-Dense-AI/scientific-agent-skills (MIT).

35 skills

Long-form writing craft, from the author's reusable voice profile through story editing, adversarial sharpening, independent judging, and multi-model jury calibration.

31 skills

AI-first academic writing assistant for Humanities researchers: drafts in your voice from your own sources, checks every citation, and delivers a .docx you can revise from Word comments.

28 skills · 2 agents · hooks

Focused humanize editing plus a multi-agent longform harness. Preserves voice and meaning in existing prose, with five writer personas and parallel critics for pipeline workflows.

2 skills · 10 commands · 18 agents

Multi-agent writing harness that catches AI-default writing patterns before they ship. Five writer personas, parallel critic ensemble, 0-100 sameness score. Built for longform authors, essayists, and editors.

1 skill · 10 commands · 18 agents

AI 웹소설 창작 하네스

10 skills · 18 agents

Documentation-first methodology and multi-agent toolchain for technical non-fiction long-form manuscripts. The Bernoulli-textbook approach: design spec and chapter plans drive the manuscript.

3 skills · 11 commands · 11 agents · hooks

Reusable production-prep engine for feature screenplays: read-only audit agents (continuity, motif, slugline, cast-cue, fact-drift, fidelity, structure, dialogue, rights, pitch) plus reconcile / casting-doc / cast-report / paged-HTML / fdx-convert scripts and eight workflow skills. Project-parameterized — each screenplay supplies a PROJECT_PROFILE.md the agents and scripts read.

8 skills · 15 agents

Documentation-first worldbuilding methodology and prose craft guardrails for fiction projects. The Silmarillion approach: docs ARE the world, story text derives from them.

2 skills · 8 commands · 11 agents · hooks

Write like a person, not an AI: anti-AI-tells engine with isolated judges, voice profiles, plain language, claims integrity and built-in kaizen.

13 skills · 5 agents · hooks

Fiction ebook writing and publishing skills: book profiling, cover design, story planning, editing (structural/line/proofreading), and publishing.

14 skills

Rewrite English with ASD-STE100 structure and no AI tells.

11 skills

Personal-style writing with explicit rules, advisory corpus tendencies, scoped persistent preferences and exact-final-text checks. Authenticated Claude/Codex runtime; optional whole human examples.

4 skills · 4 agents

Check whether a finished draft sounds like the person it is supposed to sound like: build a voice profile, score a draft against it, and get one verdict. The grader diagnoses and never edits.

4 skills · 4 agents

Two read-only critics and one revising transformer for prose. prose-voice-critic: does this sound like the author, judged against their own corpus, with every finding required to cite how they write instead. prose-fidelity-critic: did a revision keep the facts, quotes, qualifications and claim strength of the original, judged against a deterministic scan that is authoritative on presence. prose-reviser: applies a plan of edits and emits a change log the fidelity critic then judges — out-of-plan edits impossible by construction. Never judges quality, never claims anything about who wrote something.

1 skill · 6 agents

Barbara Minto's Pyramid Principle for short-form, long-form, presentations, and audits

6 skills · 1 command

Make Claude write natural Thai: tech teams (Jira, PR reviews, Slack/LINE), office documents, email, slides, academic writing, social posts and articles, personal messages, EN→TH translation

6 skills · hooks

Run deterministic prose checkers over a manuscript and fix what the JSON report reports.

6 skills

Writing skills: READMEs, plain readable prose, stripping AI tells, and drafting in your own voice.

5 skills · hooks

Personal-style writing with explicit rules, advisory corpus tendencies, scoped persistent preferences and exact-final-text checks. Authenticated Claude/Codex runtime; optional whole human examples.

2 skills · 4 agents