Index of every page on this site: llms.txt
All skills
lingfengqaq avatar

/webnovel-doctor

@04e485d
by 聆风lingfengqaq/webnovel-writer8k stars
1,299
Run it yourself

对网文项目做只读体检/诊断(/webnovel-doctor)——检查目录、文件、JSON、SQLite、RAG 配置、依赖与 Dashboard 构建产物是否完整。

Use this Skill: https://skilld.dev/gh/lingfengqaq/webnovel-writer/webnovel-doctor

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈46 tokens for metadata: the name and description. ≈333 when used: this file.

Description uses 1.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈101 characters, or 1.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Webnovel Doctor

目标

只读诊断当前书项目:确认所处阶段应有的目录、文件、JSON、SQLite、RAG 配置、Python 依赖与 Dashboard 构建产物是否完整。

原则

  1. 只读诊断:不写项目文件、不自动修复、不安装依赖、不启动 Dashboard。
  2. 先 project-status 取短状态,再 doctor 做阶段感知检查。
  3. 统一用 python -X utf8,避免中文路径编码问题。
  4. 缺失项按 runtime 推导的阶段解释影响与修复建议,不把 init 刚结束的项目按已写多章项目检查。

执行

准备路径:

export WORKSPACE_ROOT="${CLAUDE_PROJECT_DIR:-$PWD}"
export SCRIPTS_DIR="${CLAUDE_PLUGIN_ROOT:?}/scripts"

短状态:

python -X utf8 "${SCRIPTS_DIR}/webnovel.py" --project-root "${WORKSPACE_ROOT}" project-status --format summary

标准体检:

python -X utf8 "${SCRIPTS_DIR}/webnovel.py" --project-root "${WORKSPACE_ROOT}" doctor --format text

指定章节加 --chapter {chapter_num},深度体检加 --deep。

输出方式

汇报包含:当前 phase 与 target_chapter、是否有 blocker、缺失或异常文件路径、RAG / Python / Dashboard 配置是否缺失、每个问题的影响和建议修复动作。

不执行真实修复,不展示或要求粘贴 API key。

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts5mo3 checks · Risk SAFE
  • Gen Agent Trust Hub5mo

    The skill provides a read-only diagnostic utility to check the integrity and configuration status of a webnovel project. It operates safely within the local project environment without network access or data modifications.

  • Socket5mo

    No alerts

  • Snyk5mo

    Risk: LOW · No issues

Signed by skilld at 04e485d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 6 months ago
version
0.1.0
argument-hint
[--chapter N] [--deep]
All 1 allowed tools
Read Bash

README badge

README badge for lingfengqaq/webnovel-writer/webnovel-doctor