Skills

story-review

story-review is a skill in zenstory-ai/oh-story-claudecode, last changed 26 Oct 2026. It can run shell commands, name web addresses and bundle scripts. Our pattern check flagged nothing at commit 70d1cf4 on 27 Oct 2026.

Pattern check: nothing flagged · commit 70d1cf4 · 27 Oct 2026

Install
From the author
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。
Licence
MIT
Repo stars
8.1k
Folder last changed
26 Oct 2026 (opens in a new tab)
Publisher
zenstory-ai
Files
22 files
Checked
70d1cf4 (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit 70d1cf4, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit 70d1cf4, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/zenstory-ai/oh-story-claudecode.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 70d1cf426f8cbe3d374e2b06e4c2cbdbd986da06 &&
  git -C "$tmp" sparse-checkout set -- skills/story-review &&
  git -C "$tmp" checkout -q 70d1cf426f8cbe3d374e2b06e4c2cbdbd986da06 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/story-review &&
  cp -R "$tmp"/skills/story-review/. .claude/skills/story-review/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit 70d1cf4. This is how much a skill can do, not whether it is risky.

What it can touch: Scripts or outside hosts

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

  • Bundles scripts

    The folder holds code files the agent may run.

    scripts/tracking_commit.py · scripts/wordcount_core.py

Pattern check

Pattern check: nothing flagged · commit 70d1cf4 · 27 Oct 2026

We checked every text file in this skill, at commit 70d1cf4 on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Outside links we did not follow

  • https://github.com/zenstory-ai/oh-story-claudecode

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses with warnings

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Warning

      The frontmatter uses [ ] or { } values. Most agents accept them, but the spec's validator (skills-ref) rejects the file. F4

      Fix: Write lists as "- item" lines and maps as indented key: value lines, without anchors or tags.

    • Warning

      Fields outside the spec: version. Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1

      Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.

    • Warning

      metadata values should be text; openclaw (a map) is not. The spec's validator turns them into text; other readers may not. O4

      Fix: Quote each value, for example version: "1.0".

    • Note

      The description doesn't say when to use the skill. D6

      Fix: Add a sentence such as "Use when …" naming the requests or files that should trigger it.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

    • Note

      Reference files that SKILL.md doesn't link: references/tracking-initialization.md (linked only from references/tracking-transaction.md) and references/tracking-transaction.md (linked only from references/review-tracking.md). Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/agent-prompts.md (187 lines) and references/tracking-transaction.md (147 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Claude Code ignores fields it doesn't know: version. O1

      Fix: Check the spelling against Claude Code's field list, or delete them.

    • Note

      Reference files that SKILL.md doesn't link: references/tracking-initialization.md (linked only from references/tracking-transaction.md) and references/tracking-transaction.md (linked only from references/review-tracking.md). Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/agent-prompts.md (187 lines) and references/tracking-transaction.md (147 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude apps & API uploadFails

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Error

      Upload and packaging fail on fields outside the spec: version. O1

      Fix: Delete them, and keep your own data under metadata as text values.

    • Note

      metadata values should be text; openclaw (a map) is not. The spec defines metadata as text to text. O4

      Fix: Quote each value, for example version: "1.0".

    • Note

      Reference files that SKILL.md doesn't link: references/tracking-initialization.md (linked only from references/tracking-transaction.md) and references/tracking-transaction.md (linked only from references/review-tracking.md). Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/agent-prompts.md (187 lines) and references/tracking-transaction.md (147 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • OpenAI (Codex & API)Passes with warnings

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Warning

      Fields outside the spec: version. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1

      Fix: Delete them, or move your own data under metadata as text values.

    • Warning

      metadata values should be text; openclaw (a map) is not. OpenAI's upload follows the spec's text-to-text rule. O4

      Fix: Quote each value, for example version: "1.0".

  • VS Code & CopilotPasses

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Note

      VS Code ignores fields it doesn't support: version. O1

      Fix: Delete them unless another agent you target reads them.

SKILL.md

Files

22 files

PathSize
SKILL.md (opens in a new tab)20.6 KB
references/agent-prompts.md (opens in a new tab)13.9 KB
references/banned-words.md (opens in a new tab)10.9 KB
references/batch-review.md (opens in a new tab)2.3 KB
references/expression.md (opens in a new tab)9.5 KB
references/narrative-focus.md (opens in a new tab)6.7 KB
references/quality-rubric.md (opens in a new tab)4.7 KB
references/review-tracking.md (opens in a new tab)2.5 KB
references/rubrics/fanqie.md (opens in a new tab)1.1 KB
references/rubrics/qidian.md (opens in a new tab)1.1 KB
references/rubrics/zhihu.md (opens in a new tab)1.5 KB
references/solo.md (opens in a new tab)3.4 KB
references/story-logic.md (opens in a new tab)5.9 KB
references/style-resolution.md (opens in a new tab)3.7 KB
references/tracking-initialization.md (opens in a new tab)1.5 KB
references/tracking-transaction.md (opens in a new tab)15.3 KB
scripts/check-ai-patterns.js (opens in a new tab)73.5 KB
scripts/check-degeneration.js (opens in a new tab)14.8 KB
scripts/normalize-punctuation.js (opens in a new tab)13.2 KB
scripts/style-whitelist.js (opens in a new tab)1.1 KB
Show 2 more
PathSize
scripts/tracking_commit.py (opens in a new tab)82 KB
scripts/wordcount_core.py (opens in a new tab)17.9 KB

More from zenstory-ai/oh-story-claudecode

  • browser-cdp

    zenstory-ai/oh-story-claudecode

    Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP, agent-browser, 浏览器操作, 操作浏览器, Chrome CDP, 复用登录态, extract token from browser.

    • Touches credentials
    • Runs shell commands
    • +3 more
    Pattern check: Nothing flagged

    MIT · 8.1k repo stars · Updated 17 Oct 2026

  • story

    zenstory-ai/oh-story-claudecode

    网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可启动本地 Dashboard。触发方式：/story、$story、/story dashboard、/网文、「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」。

    • Runs shell commands
    • Reaches the network
    • +2 more
    Pattern check: Nothing flagged

    MIT · 8.1k repo stars · Updated 26 Oct 2026

  • story-cover

    zenstory-ai/oh-story-claudecode

    小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 生成含标题和署名的专业级网文封面；Codex CLI 优先使用内置 ImageGen，无需单独 API Key。触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」。

    • Runs shell commands
    • Reaches the network
    • +1 more
    Pattern check: Nothing flagged

    MIT · 8.1k repo stars · Updated 17 Oct 2026

  • story-deslop

    zenstory-ai/oh-story-claudecode

    网文去AI味。从表达、叙事用笔、故事因果三层诊断并修复文本，保留作者文风与已定剧情。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。

    • Runs shell commands
    • Names web addresses
    • +1 more
    Pattern check: Nothing flagged

    MIT · 8.1k repo stars · Updated 26 Oct 2026

  • story-import

    zenstory-ai/oh-story-claudecode

    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」。

    • Names web addresses
    • Bundles scripts
    Pattern check: Nothing flagged

    MIT · 8.1k repo stars · Updated 26 Oct 2026

  • story-long-analyze

    zenstory-ai/oh-story-claudecode

    长篇网文拆文。保留黄金三章、逐章摘要、剧情、情绪、节奏、角色、设定和文风接口，以连续章节块完成因果、双时间线、关系与三维节奏分析；兼容旧成果直接使用、按需增强和断点续跑。含可选三层灵感库管道（灵感库、跨书灵感聚合、更新灵感库）。触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」或提供小说文本文件路径。

    • Names web addresses
    • Bundles scripts
    Pattern check: Nothing flagged

    MIT · 8.1k repo stars · Updated 26 Oct 2026

All skills in zenstory-ai/oh-story-claudecode