This is a deep initialization agent for Chinese webnovel projects that won't let you start writing until you've actually thought things through. It walks you through seven collection steps: story hook and commercial positioning, character structure and flaws, golden finger mechanics with mandatory costs, worldbuilding and power systems, then generates 2-3 creativity constraint packages with anti-trope rules before you can proceed. The gatekeeper logic is intentional. It blocks the init_project.py script until you've locked in protagonist desire plus flaw, world scale, power system type, and at least one anti-trope rule with hard constraints. Includes an optional reference book deconstruction agent that extracts borrowable patterns while flagging what not to copy. Good for writers who keep restarting chapters because they didn't nail the premise.

skills.sh installs
707
GitHub stars
7.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add lingfengqaq/webnovel-writer --skill webnovel-init --agent claude-code

Installs into .claude/skills of the current project.

Files

Project Initialization (Deep Mode)

目标

  • 结构化交互收集足够信息,避免"先生成再返工"。
  • 产出可落地骨架:.webnovel/state.json、设定集/*、大纲/总纲.md、.webnovel/idea_bank.json、.story-system/MASTER_SETTING.json。
  • 保证后续 /webnovel-plan 与 /webnovel-write 可直接运行。

执行原则

  1. 先收集,再生成;未过充分性闸门,不执行 webnovel.py init。
  2. 分波次提问,每轮只问"当前缺失且会阻塞下一步"的信息;用户已明确的不重复问,冲突让用户裁决。
  3. 参考书拆解只返回结构化结果;用户确认前不得写入 idea_bank.json、.story-system、设定集、大纲、正文、.webnovel/state.json 或任何 canon/read model 文件。

引用加载策略

路径说明:references/ 指 skills/webnovel-init/references/;../../references/ 指共享 references。详细采集字段见 references/init-collection-schema.md(按需区段读,逐项收集,必填项以「充分性闸门」为准)。

Sponsors

Details

Repository
github.com/lingfengqaq/webnovel-writer
First seen
Jun 3, 2026

More from lingfengqaq/webnovel-writer

All 6

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs