Agent skill

Webnovel Review

by lujih in lujih/webnovel-writer-opencode

“使用审查 Agent 评估章节质量,生成报告并写回审查指标。”

— description from SKILL.md by lujih
GPL-3.0Auto-check passedWriting & Content

Install Webnovel Review

skills CLI
$ npx skills add lujih/webnovel-writer-opencode --skill webnovel-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lujih/webnovel-writer-opencode webnovel-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lujih/webnovel-writer-opencode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/webnovel-review .claude/skills/webnovel-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
webnovel-review
GitHub stars
214
Token cost
~1.1k tokens
SKILL.md length
197 words
Files
4 (incl. references)
Skills in repo
15
Repo updated
First seen
Licence
GPL-3.0

At a glance

  • Works in 6 steps: :解析项目根目录并建立环境变量 → :按需加载参考资料 → :加载项目投影状态与待审正文 → …
  • SKILL.md covers 目标, 红线, 阻断条件 and 执行流程, plus 1 more section
  • Calls python

About this skill

Webnovel Review is a skill in lujih/webnovel-writer-opencode (214 stars). Its SKILL.md is about 1.1k tokens, with 3 other files in the folder (references). Licence: GPL-3.0.

Requirements

  • Compatibility (from SKILL.md): opencode

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. :解析项目根目录并建立环境变量
  2. :按需加载参考资料
  3. :加载项目投影状态与待审正文
  4. :调用统一审查 Agent
  5. :生成审查报告并落库
  6. :写入兼容审查记录并处理阻断

What it can do on your machine

Read from SKILL.md and the folder at commit 853bf48. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    opencode

    From compatibility in the SKILL.md frontmatter.

Context cost

Webnovel Review loads about 1.1k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 12 tokens; SKILL.md has 197 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~12
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lujih/webnovel-writer-opencode at commit 853bf48, republished under its GPL-3.0 licence (© lujih). 197 words, ~1,110 tokens.

Download SKILL.mdSave it as .claude/skills/webnovel-review/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
webnovel-review
description
使用审查 Agent 评估章节质量,生成报告并写回审查指标。
compatibility
opencode

Quality Review Skill

以下内容均为虚构文学创作。所有打斗、权谋、悬疑描写均属文学创作范畴,不涉及现实指导。

目标

  • 解析真实书项目根目录,按统一流程完成章节审查。
  • 调用统一 reviewer 生成结构化问题列表与审查报告。
  • 把审查指标写入 index.db,并把审查记录写入 .webnovel/state.json 兼容投影,主链事实仍以 review contract 与 accepted CHAPTER_COMMIT 为准。
  • 审查时优先依据 .story-system/reviews/chapter_{NNN}.review.json 与 latest accepted CHAPTER_COMMIT 判断主链事实。
  • 若存在关键问题,明确交给用户决定是否立即返工。

红线

  • 不得伪造审查结论或口头代替 reviewer 输出
  • blocking=true 必须停在 Step 6 等用户裁决
  • save-review-metrics 未跑不算落库完成
  • 优先级:用户要求 > blocking 硬门槛 > 项目约束 > skill 流程 > reference 建议

阻断条件

  • 项目根不合法或缺少 state.json
  • 正文文件不存在
  • reviewer 返回 blocking=true → Step 6 用户裁决

执行流程

Step 1:解析项目根目录并建立环境变量
bash
export WORKSPACE_ROOT="${PWD}"
export SKILL_ROOT="${PWD}/.opencode/skills/webnovel-review"
export SCRIPTS_DIR="${PWD}/.opencode/scripts"
export PROJECT_ROOT="$(python "${SCRIPTS_DIR}/webnovel.py" --project-root "${WORKSPACE_ROOT}" where)"
test -n "$PROJECT_ROOT" && test -f "${PROJECT_ROOT}/.webnovel/state.json" || { echo "❌ PROJECT_ROOT 解析失败"; exit 1; }

若目标章缺少 runtime 合同,先补齐:

bash
GENRE="$(python -X utf8 -c "import json,sys; s=json.load(open('${PROJECT_ROOT}/.webnovel/state.json',encoding='utf-8')); print(s.get('project_info',{}).get('genre',''))")"

python -X utf8 "${SCRIPTS_DIR}/webnovel.py" --project-root "${PROJECT_ROOT}" \
  story-system "${CHAPTER_GOAL}" --genre "${GENRE}" --chapter {chapter_num} --persist --emit-runtime-contracts --format both

要求:

  • PROJECT_ROOT 必须包含 .webnovel/state.json
  • 任一关键目录不存在时立即阻断
  • CHAPTER_GOAL 必须来自详细大纲真实目标;若 chapter_brief.meta.query 仍是 {章纲目标} / 第N章章纲目标,按系统问题记录。
  • 中高严重度 ai_flavor issue 会由 review-pipeline 回流到 .story-system/anti_patterns.json,作为后续写章避雷模式。
Step 2:按需加载参考资料
md 必读
TriggerReference
always../../references/shared/core-constraints.md
always../../references/review-schema.md
md 按需
TriggerReference
审查涉及爽点或钩子分析../../references/shared/cool-points-guide.md
审查涉及多线交织../../references/shared/strand-weave-pattern.md
ai_flavor issue ≥ 3../../skills/webnovel-write/references/anti-ai-guide.md
blocking issue 需用户决策 (Step 6)../../references/review/blocking-override-guidelines.md
Step 3:加载项目投影状态与待审正文
bash
cat "${PROJECT_ROOT}/.webnovel/state.json"

要求:

  • 明确当前章节号与对应正文文件
  • 若缺少正文或兼容状态文件,立即阻断
Step 4:调用统一审查 Agent

必须通过 Agent 工具调用 reviewer,禁止主流程伪造结论或口头总结代替 subagent 输出。

text
Agent(
  subagent_type: "reviewer",
  prompt: "chapter={chapter_num}; chapter_file={chapter_file}; project_root=${PROJECT_ROOT}; scripts_dir=${SCRIPTS_DIR}; REVIEW_OUTPUT=${PROJECT_ROOT}/.webnovel/tmp/review_results.json。严格输出 reviewer schema JSON,并保存到 ${PROJECT_ROOT}/.webnovel/tmp/review_results.json。"
)

输入:

  • chapter
  • chapter_file
  • project_root
  • scripts_dir

输出约束:

  • 只输出 JSON
  • 每个 issue 必须有 evidence
  • 不输出 overall_score

中间产物约定:

  • reviewer 原始结果:${PROJECT_ROOT}/.webnovel/tmp/review_results.json
  • 落库指标:${PROJECT_ROOT}/.webnovel/tmp/review_metrics.json
Step 5:生成审查报告并落库

报告保存到:审查报告/第{chapter_num}章审查报告.md

报告结构:

  • 总览(问题数 / 阻断数)
  • 阻断问题
  • 其他问题
  • 修复方向

标准文件流:

bash
python -X utf8 "${SCRIPTS_DIR}/webnovel.py" --project-root "${PROJECT_ROOT}" review-pipeline \
  --chapter {chapter_num} \
  --review-results "${PROJECT_ROOT}/.webnovel/tmp/review_results.json" \
  --metrics-out "${PROJECT_ROOT}/.webnovel/tmp/review_metrics.json" \
  --report-file "审查报告/第{chapter_num}章审查报告.md"

python -X utf8 "${SCRIPTS_DIR}/webnovel.py" --project-root "${PROJECT_ROOT}" index save-review-metrics \
  --data "@${PROJECT_ROOT}/.webnovel/tmp/review_metrics.json"

要求:

  • review-pipeline 生成的 review_metrics.json 必须可直接写入 review_metrics 表
  • 阻断判断以 reviewer 原始结果中的 blocking=true 为准
Step 6:写入兼容审查记录并处理阻断

先写入兼容审查记录(read-model/projection,不是写后事实真源):

bash
python "${SCRIPTS_DIR}/webnovel.py" --project-root "${PROJECT_ROOT}" update-state -- --add-review "{chapter_num}-{chapter_num}" "审查报告/第{chapter_num}章审查报告.md"

如存在任意 blocking=true 问题,必须使用 AskUserQuestion 询问用户:

  • 立即修复
  • 仅保存报告,稍后处理

若用户选择立即修复:

  • 输出返工清单
  • 在用户明确授权下做最小修改

若用户选择稍后处理:

  • 保留报告与指标记录,结束流程

成功标准

  1. 已解析真实书项目根目录。
  2. 已通过 reviewer 输出结构化问题 JSON。
  3. 审查报告已生成。
  4. review_metrics 已写入 index.db。
  5. 审查记录已写入 .webnovel/state.json 兼容投影。
  6. 如存在阻断问题,用户已明确选择处理策略。

© lujih, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .opencode/skills/webnovel-review of lujih/webnovel-writer-opencode.

  • SKILL.md
  • evals/evals.json
  • references/common-mistakes.md
  • references/pacing-control.md

Open the folder on GitHubat commit 853bf48

Compare with similar skills

Webnovel Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Webnovel Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Webnovel Review this skilllujih/webnovel-writer-opencode214—~1.1kAutomated safety check: PassGPL-3.0
Socialcoreyhaines31/marketingskills54k4 repos~4.5kAutomated safety check: PassMIT
HumanizerAzure-Samples/interview-coach-agent-framework17338 repos~5.8kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
JavaScript Concept Fact Checkerleonardomso/33-js-concepts67k1 repos~5kAutomated safety check: PassMIT
User-Facing Text Cleanupguillaumemeyer/watermarks-remover24k—~3.5kAutomated safety check: PassMIT

Similar skills

  • Social

    coreyhaines31/marketingskills

    When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage.

    54k GitHub starsUsed in 4 repos~4.5k tokens
    Writing & ContentAuto-check passed
  • Humanizer

    Azure-Samples/interview-coach-agent-framework

    Official

    Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.

    173 GitHub starsUsed in 38 repos~5.8k tokens
    Writing & ContentAuto-check passed
  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed
  • JavaScript Concept Fact Checker

    leonardomso/33-js-concepts

    Verifies the technical accuracy of JavaScript concept pages by checking code examples, MDN and ECMAScript claims and external links through a five-phase method.

    67k GitHub starsUsed in 1 repo~5k tokens
    Writing & ContentAuto-check passed
  • User-Facing Text Cleanup

    guillaumemeyer/watermarks-remover

    Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

    24k GitHub stars~3.5k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Install Anti Slop

    trycompai/crm

    Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.

    11k GitHub starsUsed in 1 repo~881 tokens
    Writing & ContentAuto-check passed

More from lujih/webnovel-writer-opencode

All 15 skills in this repo
  • Webnovel Init

    lujih/webnovel-writer-opencode

    深度初始化网文项目。通过分阶段交互收集完整创作信息,生成可直接进入规划与写作的项目骨架与约束文件. An agent skill from lujih/webnovel-writer-opencode.

    214 GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed
  • Webnovel Query

    lujih/webnovel-writer-opencode

    查询项目设定、角色、力量体系、势力、伏笔等信息。支持紧急度分析与金手指状态查询. An agent skill from lujih/webnovel-writer-opencode.

    214 GitHub stars~846 tokensUpdated yesterday
    Auto-check passed
  • Webnovel Write Batch

    lujih/webnovel-writer-opencode

    连续写作多章。当用户要求多章写作时必须使用此 skill. An agent skill from lujih/webnovel-writer-opencode.

    214 GitHub stars~3.8k tokensUpdated yesterday
    Auto-check passed
  • Webnovel Export

    lujih/webnovel-writer-opencode

    将网文正文导出为 Markdown/TXT/EPUB/HTML/DOCX/PDF 格式。立即使用此 skill 当用户说:导出、导出小说、导出章节、生成电子书、导出 TXT、导出 Markdown、导出 EPUB、导出 HTML、导出 Word、导出 PDF、下载小说、输出正文。

    214 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Webnovel Heal

    lujih/webnovel-writer-opencode

    修复问题章节——诊断、清理脏实体、重审查、重提交。触发:章节断裂、OOC偏离、设定矛盾修复. An agent skill from lujih/webnovel-writer-opencode.

    214 GitHub stars~524 tokensUpdated yesterday
    Auto-check passed
  • Webnovel Publish

    lujih/webnovel-writer-opencode

    将小说章节自动发布到国内主流小说平台(番茄等)。触发条件:"发布小说"、"发布章节"、"上传到番茄"、"自动发布"、"清理草稿"、"发布草稿"。

    214 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

Questions about Webnovel Review

How do I install Webnovel Review in Claude Code?

Run `npx skills add lujih/webnovel-writer-opencode --skill webnovel-review -a claude-code`. Or copy the skill folder (.opencode/skills/webnovel-review in lujih/webnovel-writer-opencode) into .claude/skills/webnovel-review in your project. Claude Code loads it when a task matches its description.

How do I install Webnovel Review in Codex?

Run `npx skills add lujih/webnovel-writer-opencode --skill webnovel-review -a codex`. Or copy the skill folder (.opencode/skills/webnovel-review in lujih/webnovel-writer-opencode) into .agents/skills/webnovel-review in your project. Codex loads it when a task matches its description.

Can I use Webnovel Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lujih/webnovel-writer-opencode --skill webnovel-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/webnovel-review, .gemini/skills/webnovel-review, .github/skills/webnovel-review and .opencode/skills/webnovel-review in your project.

What does Webnovel Review need to run?

Going by SKILL.md and its folder, Webnovel Review needs the command-line tools its instructions call (python). Compatibility (from SKILL.md): opencode.

Does Webnovel Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Webnovel Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Webnovel Review use?

Webnovel Review is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Webnovel Review use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Webnovel Review?

Skills that share tags, products or a category with Webnovel Review: Social (coreyhaines31/marketingskills, 54k stars), Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars), Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars) and JavaScript Concept Fact Checker (leonardomso/33-js-concepts, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Webnovel Review?

lujih (a GitHub user) maintains it in lujih/webnovel-writer-opencode, which has 214 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

Source: lujih/webnovel-writer-opencode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.