Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
korean-prose-skill
Skills이상한 해요체는 이제 그만...!! 한국어 작성 및 교정 스킬
git clone https://github.com/JellyBrick/korean-prose-skill.git -
ProseMap
MCP serversSentence-by-sentence analysis of a prose draft: a score for every sentence and every handoff.
-
Prose Coach
MCP serversDeterministic writing filter. Marks 43 AI patterns with the line and the fix.
-
snifftest
SkillsA prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.
git clone https://github.com/DanRWilloughby/snifftest.git -
sloptrim
SkillsA local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.
git clone https://github.com/seyedehsanhadi/sloptrim.git -
Proseify
MCP serversMCP book-writing server: 81 classics, genre recipes, drafting pipelines.
-
polish-open-source-prose
SkillsAgent Skill for Claude Code + Codex that edits open-source prose without losing facts or voice. Includes zh-Hant-TW.
git clone https://github.com/ting-hong-shieh/polish-open-source-prose.git -
iceberg
SkillsClaude Code plugin: grades every plan Claude writes against 14 Hemingway rules and rewrites docs to an A.
git clone https://github.com/gagoar/iceberg.git -
Zero Slop
MCP serversScore and rewrite AI-assisted prose while preserving names, numbers, quotes, links, and facts.
-
humanizer-lint
SkillsA local, zero-dependency prose, copywriting, UI-text, and code-comment linter that flags stiff, AI-sounding writing (stock phrases, flat sentence rhythm, repeated wording) and tells you what to revise. Includes 8 language packs. A style checker, not an AI detector.
git clone https://github.com/yanstd888/humanizer-lint.git -
claude-terse
PromptsFor those who struggle with how Claude speaks to them. No more essays. No more slogans, metaphors, "it's not X, it's Y". This plugin makes Claude speak normally.
git clone https://github.com/lowenbjer/claude-terse.git -
skills
Skills43 Claude Code skills for making content that doesn't read like a machine made it — prose editing with an offline linter, prompt engineering for 40+ image/video/music models with optional one-command execution, and orchestrators from research to a published carousel, reel or proposal. Russian-first, English throughout.
git clone https://github.com/Mikefluff/skills.git -
better-writing
PromptsAn agent skill for prose that sounds clear, specific, and human.
git clone https://github.com/forjd/better-writing.git -
writing-guidelines
SkillsReview docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".
npx skills add vercel-labs/agent-skills -
visual-storytelling-skills
SkillsAgent skills for AI film production — from prose to picture.
git clone https://github.com/leynos/visual-storytelling-skills.git -
humanizer-ko
Skills한국어 텍스트에서 AI 생성 글의 티를 제거하는 Claude Code 에이전트 스킬. ChatGPT 문체, 이중 피동, 번역투, 문체 혼용 등 33개 패턴 탐지. Korean adaptation of the humanizer agent skill.
git clone https://github.com/IsaacEryn/humanizer-ko.git -
ai-slop-linter
SkillsLinter for AI-writing tells in commit messages, PR descriptions and docs. It does not guess who wrote it. It shows the tells.
git clone https://github.com/Bubblegunn/ai-slop-linter.git -
Federal Criminal
MCP serversFederal criminal prosecutions — US federal court dockets.
@pipeworx/mcp-federal-criminal@0.2.1 -
publishready
MCP serversPublishReady: Deterministic writing control with local-first metrics and AI prose audits.
@veldica/publishready-mcp@1.0.5 -
defluff
MCP serversDeterministic prose linter for LLM text — flags AI slop, filler, buzzwords, hedges, clichés.
defluff@0.1.2 -
Nanotoll MCP
MCP serversCompress prose for LLM context windows. Per-call USDC billing, signed receipt.
-
OpenJEV
MCP serversTyped AI judgments for agents: choice, score, and yes/no probabilities instead of prose.
openjev-mcp@0.2.0 -
sepia
PromptsDe-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).
git clone https://github.com/Nanako0129/sepia.git -
write-human
SkillsStatistical linter that flags the words, phrases and constructions that make text read as LLM output, measured against billions of words people wrote before 2022. Runs offline. CLI on npm plus an Agent Skill for coding agents.
git clone https://github.com/arslanrakh/write-human.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.