claudecodex

prose-review

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.

0 on GitHubby Connor Englandv0.8.0MITupdated 3 days agowriting
/

Plugin prose-review from marketplace vonnegut in ConnorBritain/vonnegut. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (1)

  • prose-edit

    This skill should be used when the user wants to read a reviewed draft the way an editor would — section by section, with the critics' notes for each section beside it — deciding which notes to accept, decline or defer, adding their own, and turning the accepted ones into the reviser's plan. It pres

Subagents (6)

  • prose-fidelity-critic

    Read-only critic whose ONLY job is whether a revision kept what it had to - facts, quotes, named entities, qualifications, and the strength of every claim - judged against the original and a deterministic scan of it. Use after any rewrite, and before accepting one. Distinct from prose-voice-critic (

  • prose-medium-critic

    Read-only critic whose ONLY job is whether a piece survives the medium it will be delivered in - read aloud by a text-to-speech voice, scrolled on a phone in a feed, printed in a programme, posted as segments - judged against a medium profile the session supplies and the output of repurpose-check, w

  • prose-reader-critic

    Read-only critic that reads a draft AS ONE NAMED READER - a skeptical CTO, a first-time reader, an acquisitions editor, an adversarial reader - described in a persona block the session supplies, and reports where that reader stops and why, then makes one forced choice. Use when the author asks "read

  • prose-reviser

    The one primitive in this repo that changes prose. Given an original draft and an edit plan, it emits a change log of before/after pairs — one per plan entry it applied, plus explicit refusals for entries it could not apply cleanly. It never reproduces the draft, never touches spans the plan does no

  • prose-structure-critic

    Read-only critic whose ONLY job is whether a draft's structure carries its argument - order, transitions, claims with nothing behind them, section balance - judged against outline-scan's counts and, when one exists, the intended outline. Use on an argument (essay, post, report, talk) after outline-s

  • prose-voice-critic

    Read-only critic whose ONLY job is whether a draft sounds like the author it is supposed to be by, judged against their own corpus and voice card - not whether it is good, and never whether it was machine-written. Use when a draft should sound like a specific person and you have samples of their wri

View source on GitHub

More from ConnorBritain/vonnegut

All 6 plugins →

prose-author

claudecodex

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

0

prose-outline

claudecodex

Outlines for prose: turn a brief into a checkable outline with thesis, claims, evidence slots and open questions (or acts, beats and turns for fiction); read a draft back into the outline it implies with a deterministic scan; diff two outline revisions by node; keep outlines per project in the shared writing-identity registry with undo. Proposes and measures; never drafts prose and never scores it.

3 skills

0

prose-bible

claudecodex

Continuity for multi-file prose projects: a deterministic cross-file index of names, defined terms, attributes, dates and repeated passages with locations; a diff that pairs what differs; a per-project bible in the shared writing-identity registry, proposed from the index and confirmed entry by entry; and a read-only critic that reports contradictions citing two locations or nothing. Never fact-checks against the world and never saves without approval.

1 skill · 1 agent

0

prose-tell-scan

claudecodex

Deterministic prose measurement: a catalogued scan for AI writing tells plus the cadence metrics a model cannot estimate about its own output. Register-aware, calibrated against your own corpus, and report-only — signals for an author about their own draft, never a verdict about who wrote something. Ships no rewriter, by design.

1 skill · 1 command

0

prose-research

claudecodex

Provenance for prose: take sources in (a URL, a file, a PDF's text), keep a dossier of quotable passages with locations and a claims ledger (claim, source, quote, the writer's confidence) in the shared writing-identity registry with undo, and check a draft deterministically — every ledger quote verbatim against its source, every link, every sentence that makes a claim no entry backs. Hands quote provenance to the fidelity critic. Never says a claim is true, never ranks sources, never saves without approval.

1 skill

0

Similar plugins

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.

hooks

anthropics/claude-code 155,476

agentdb

claude

AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server

3 skills · 1 command · 1 agent · 1 MCP server

ruvnet/ruflo 81,589

Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.

1 skill

hugohe3/ppt-master 76,375

humanizer

claude

Rewrite AI-sounding text so it reads like the writer without changing what it says.

1 skill

blader/humanizer 68,461

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

OpenAPI specification generation, Mermaid diagram creation, tutorial writing, API reference documentation

3 skills · 1 command · 5 agents

wshobson/agents 42,461

Maintain prose-review?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins6 plugins