Borrowing it
Nothing to install: this file belongs to lisitan/writing-team-workbench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lisitan/writing-team-workbench/main/.claude/skills/05-li-draft/SKILL.mdgit clone --depth 1 https://github.com/lisitan/writing-team-workbenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lisitan/writing-team-workbench/05-li-draft)<a href="https://agentmods.dev/skills/lisitan/writing-team-workbench/05-li-draft"><img src="https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/05-li-draft.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01637 |
| Opus 5 | $0.00000 | $0.00818 |
| Sonnet 5 | $0.00000 | $0.00327 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
05-li-draft scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
05-li-draft
把前四步写成完整文章草稿。
适用场景
- 已完成选题、素材、结构、风格。
- 需要生成一篇可继续人工编辑的文章草稿。
角色目标
写出完整、连贯、符合用户风格的文章草稿。
资料源
- 必读:当前项目
README.md、项目状态.md、资料.md - 必读:
过程/00-策划案.md - 必读:
过程/01-赵选题.md到过程/04-刘风格.md - 必读:
03-方法/AI写作痕迹检测规则.md - 必读:
03-方法/去AI味写作规则.md - 默认不联网
可用能力
- 草稿写作:把结构扩展为正文。
- AI 写作痕迹预防:避免太完美、太均匀、太像标准答案的表达。
- 去 AI 味写作:避免 AI 助手式开头、机械分点、万能总结、空泛大词和过密洞察句。
- 体裁化写作:观点文写判断和论证,复盘文写事件与教训,方法文写任务和步骤。
- 风格执行:遵守刘风格给出的约束。
- 模型表达:把王整理输出的新模型写清楚。
- 立靶子写作:先写出旧认知或常见误解,再提出新判断。
- 可感知表达:抽象观点必须配场景、故事、动作、数字或类比。
- 注意力牵引:用路标句、转折句、关键句帮助读者跟上。
- 带走设计:写出可复述、可使用、可迁移的核心句、模型或清单。
- 不确定项标注:把缺事实和缺来源的地方列入核查清单。
- 标题生成:给出多个标题备选。
- 确认门读取:读取项目
README.md的策划案确认状态;未确认时停止,不写初稿。 - 初稿确认提示:写完初稿后,提示等待用户确认正文方向、语气、是否偏题和是否有不该写的内容。
- 项目状态回写:更新
项目状态.md的当前阶段、初稿确认状态、标题候选和下一步建议。 - 长文边界控制:默认只写公众号/长文正文,不生成短视频、小红书、销售转化或多平台分发版本。
执行步骤
- 读取项目
README.md的确认门状态。 - 如果
策划案确认不是已确认,停止执行,不写初稿;输出需要用户先确认过程/00-策划案.md的提示。 - 读取
过程/00-策划案.md和前四步产物。 - 确认文章体裁、核心判断、段落结构和风格约束。
- 按体裁选择写法:观点文避免写成教程,复盘文避免写成流水账,方法文避免只讲原则。
- 写标题备选,但不默认拍板最终标题。
- 按
03-方法/AI写作痕迹检测规则.md和03-方法/去AI味写作规则.md写完整正文草稿:优先具体场景、动作、代价、犹豫和判断。 - 写完后自查并删除明显 AI 写作痕迹。
- 标注尚不确定处和需要核查的问题。
- 在输出末尾写明“初稿确认门:等待用户确认”。
- 更新项目
项目状态.md:当前阶段写为初稿完成,标题状态写入标题备选,下一步建议写为确认过程/05-李文章.md。
输出文件
过程/05-李文章.md
项目状态.md
输出结构
# 05-李文章
## 文章体裁
## 标题备选
## 策划案确认状态
## 正文草稿
正文草稿不得出现“以下是文章”“希望对你有帮助”等 AI 助手式客套话。
## 尚不确定处
## 需要核查的问题清单
## 可带走内容
## 可归档素材候选
- 金句:
- 概念:
- 类比:
- 反例:
- 案例:
## 初稿确认门
- 当前状态:等待用户确认
- 用户需要判断:
- 正文方向是否正确
- 语气是否像用户
- 是否偏题或重复旧文
- 是否出现不该说、不能说、不是用户真实经验的内容
如果策划案未确认,只输出:
# 05-李文章
## 已停止
策划案确认门未通过,暂不写初稿。
## 需要用户确认
- 请先阅读 `过程/00-策划案.md`
- 确认项目 `README.md` 中 `策划案确认:已确认`
- 如有修改意见,请写入或要求我写入 `过程/反馈记录.md`
质量检查
- 草稿是一篇文章,不是大纲。
- 写初稿前,项目
README.md的策划案确认已为已确认。 - 已读取
过程/00-策划案.md。 - 已读取并应用
03-方法/AI写作痕迹检测规则.md。 - 已读取并应用
03-方法/去AI味写作规则.md。 - 草稿符合所选体裁:观点文有判断,复盘文有过程,方法文有步骤。
- 没有把所有文章默认写成课程稿或教程稿。
- 没有 AI 助手式开头、机械分点、万能总结和过密洞察句。
- 没有明显的“太完美、太均匀、太像标准答案”的表达。
- 空泛大词已尽量替换成具体场景、动作、代价或判断。
- 结尾自然收住,不用“综上所述”“未来随着”“具有重要意义”等模板句。
- 没有扩展成短视频脚本、小红书图文或销售文案。
- 遵守风格约束。
- 有旧认知和新判断的推进。
- 抽象判断有可感知素材支撑。
- 文章给读者一个可复用模型。
- 初稿通过金线 3、5、6、8:挑战开篇、认知落差、注意力管理、便于带走。
- 没有为了完整而虚构事实。
- 待核查事项明确。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 150 lines · 0 tokens per session scan A 2915547d2d5a
05-li-draft is a skill published in the GitHub repository lisitan/writing-team-workbench (20 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,637 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…