BD xt-webnovel-writing
中文网络小说写作 agent 的总入口。处理网文构思、写开头、设计主线、起书名、写大纲、写简介、设计剧情、加爽点、改文笔、拆解参考文本、自检错误、续写连载等任何中文网文生成类任务。内部路由到 6 个模块：text-analysis / story-blueprint / plot-design / excitement-and-craft / pitfalls / memory。内置反 AI 味硬约束（18 主条款 + 7 子条款 · 共 25 项：节拍器 **+ A-补充 章首刺点与好奇缝隙 + A-补充2 章首入场模板池** / 句式复用 / 主语熵 / **单句段连续 ≤ 2 且占比 ≤ 0.3** / 信息密度与世界自主生活（含闲笔密度 / 配角自主议题 / 废选项戏剧化 / D-4 句法缀笔 · 回滚级）/ 情感标签含独段与粗体 / 反应套餐 / signature 明牌化 / 设定说明书 / 9 种定义体模板 / 角色 PPT 直讲 / 算法思维链 / 爽点链条过完整 / 质量曲线过稳定含粗体主题句点题 / 角色灵魂缺位含首登即生效 **+ O-在场 禁元叙事（上一章/读者等）** / **剧情算法化/想象力贫血（含怪异预算/废选项/延迟兑付/反套路检查 · 回滚级）** / **转场机械/黏滞转场（含 5 类桥/禁用转场词/摩擦点必填 · 回滚级）** / **说明书式排除枚举+教程体微动作链（R-1/R-2/R-3 · 回滚级）**），其中 D / M / N / N-细 / O / P / Q / **R** / G+1 / E（独段+粗体）/ K（0 长段 **或 K-补充 场景块违规 ≥ 5**）/ C（≥ 6 连续单句段或占比 > 0.5）/ **A-补充（opening_hook / curiosity_gap / flat_atmosphere）** / **A-补充2（opening_mode_streak / wakeup_opening_count）** / **O-在场（meta_language_hits ≥ 1）** 为**回滚级硬门**，任一命中强制整章退回指定 workflow 重写；每个有名出场 ≥ 2 次角色（含动物 / 灵兽 / 反派）和本章首登的关键角色都必须带独立内部状态并在当章非功能性地"被偶然看见"（deletion_verified）；项目型写作默认走 memory 持久化流程（仅一次性短文可豁免），所有文件严格落在 **project_root** 下的固定子目录（book.yaml / fingerprint.md / bible / characters / arcs / chapters（`chNNNN_短标题.md` 仅 H1+正文）/ state（含 `chapter_meta/chNNNN.yaml` 章元）/ index / .webnovel-memory），禁止散落。触发词：写网文、写网络小说、构思小说、写玄幻、写仙侠、起书名、大纲、人设、爽点、开头、签到流、系统流、重生、打脸、装逼、改文笔、AI 味、续写、接着写、第 X 章、连载、webnovel、web novel。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1349 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6110 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 6110 tokens
- 100Steps. 95 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1349: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 95 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 38.