agentleFS
FiredMosquito831FiredMosquito831/my-writing-companion/skills/story-review/SKILL.md

story-review

Skill2 starsChanged 26 days agoApache-2.0View on GitHub

Review work after prose exists: editorial review, craft critique, continuity/voice review, copyediting, proofreading, and synthesis of reader-sim signal. Load when diagnosing a draft rather than rewriting it.

8 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use story-deslop, story-long-write and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • XiaoyangySkill

    story-deslop

    网文去AI味。检测并清除文本中的AI写作痕迹,让文字回归自然、非模板化。触发方式:/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。

    Also in 5 projects that use this

  • XiaoyangySkill

    story-long-write

    长篇网文写作方法论与 novel-studio pipeline 适配器。用于把长篇开书、大纲、日更、续写、重写等需求整理为 pipeline 输入;在 novel-studio 内禁止直接生成正文。触发方式:/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。

    Also in 5 projects that use this

  • worldwondererSkill

    story-cover

    小说封面生成与提示词设计。根据书名、作者名和题材构建封面提示词;用户只要提示词时不生图,要求封面图时调用 GPT-Image-2,Codex CLI 优先使用内置 ImageGen。触发方式:/story-cover、/封面、「帮我做个封面」「生成封面图」「封面提示词」「封面设计」。

    Also in 4 projects that use this

  • worldwondererSkill

    story-import

    逆向导入已有小说。将已写好的小说(半成品或完本)反向解析为标准项目目录结构,兼容 story-long-write / story-short-write 后续写作流程;内部复用 story-long-analyze / story-short-analyze 的拆解管道,按篇幅自动分流。触发方式:/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。

    Also in 4 projects that use this

  • marketcallsSkill

    story-setup

    Set up the story-telling environment. Checks Node, installs dependencies, creates .env from the template, verifies the Sarvam, fal and OpenAI keys, and confirms all Remotion packages are on one version.

    Also in 5 projects that use this

  • +2 more from Xiaoyangy
  • +3 more from worldwonderer

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When review incorporates reader-sim data:

    line 56
  2. Distinctive:

    After any review program — critique fan-out, cold read, demolition, beta read — merge all sources into the revision plan instead of …

    line 65
  3. Distinctive:

    When parallel reader reports disagree (beta four-reader protocol, persona panel, reader-sim lane), run the synthesis protocol before …

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Story Review

Analytical review of existing prose. This skill is for diagnosis, not rewriting. Keep /reader-sim separate when the task needs a felt first-time reader experience rather than analytical critique.

Choose the review level before reading. Start big before small unless the caller explicitly asks for a late-stage pass. The edit levels move from structural to surface, and each assumes the levels above it are stable:

  • Editorial review — holistic third-party book-editor pass. What kind of revision does this draft need, and in what order?
  • Developmental edit — structure, promise, causality, pacing, character arc. Is the draft the right shape?
  • Line edit — voice, rhythm, clarity, texture. Does the prose move well?
  • Copyedit — grammar, usage, punctuation, consistency. Is it correct?
  • Proofreading — final surface pass. What slipped through?

Each level has a dedicated resource with method and checklist:

  • resources/editorial-review.md
  • resources/developmental-edit.md
  • resources/line-edit.md
  • resources/copyedit.md
  • resources/proofreading.md

For adversarial craft critique (as opposed to editorial review), load:

  • resources/prose-critique.md — methodology and focus-area routing.
  • resources/prose-critique/ — deep resources per focus area (structure, character, voice, prose, continuity).

Persona panel

For milestone chapters or disputed judgments, muse fans out @critic with focus: persona:<name>. Each persona critiques the chapter's execution, not its premise (base rule) — how the prose works, not whether the story should exist. Personas load gates/ for the shared quality bar and score the five axes.

  • resources/prose-critique/personas/wood.md — James Wood: sentences, consciousness, free indirect style, the life of detail. (Literary fiction.)
  • resources/prose-critique/personas/king.md — Stephen King: story above all, character, honesty, the hatred of adverbs. (Genre / commercial.)
  • resources/prose-critique/personas/leguin.md — Ursula K. Le Guin: world-building as meaning, prose as music, the moral weight of imagination, the dragons. (Fantasy / SF.)
  • resources/prose-critique/personas/gay.md — Roxane Gay: representation, voice and authenticity, the body, power, emotional truth. (Contemporary / literary.)

The four personas are opus-tier read-only critics. Muse synthesizes their reports (the digest pattern from fiction/agents/review-coordinator.md, MIT, may be used to fan out per-chapter critics and cache reports for 15+ chapter books). A persona panel is advisory; it does not block a gate.

When review incorporates reader-sim data:

  • resources/reader-sim-signal.md — how to interpret and synthesize reader-sim output alongside analytical critique.

From findings to a revision plan

Vellum produces findings in four places (critiques, cold-read issues, demolition logs, the beta report) and the reader-sim lane adds a fifth. After any review program — critique fan-out, cold read, demolition, beta read — merge all sources into the revision plan instead of presenting raw lists: dedupe across sources, triage into buckets, and let the author decide row by row.

  • resources/revision-plan.md — the work/revision-plan.md artifact: append-only rows, triage buckets, the open | in-progress | resolved | declined statuses (declined rows carry the author's reason, verbatim — the muse never re-opens one), the intake protocol, and the per-round definition of done. vellum revision status cross-checks it (report-only).

When reader reports conflict

When parallel reader reports disagree (beta four-reader protocol, persona panel, reader-sim lane), run the synthesis protocol before weighing anything — and never average conflicting verdicts silently:

  • resources/beta-synthesis.md — strip reader identities, cluster notes by passage, classify each preference | craft | friction, apply the frequency rule (singleton preference = declined-by-default; 3-of-n confirms a pattern), and translate every accepted note from symptom to candidate cause for critics to confirm before any edit.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.