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/01-zhao-topic/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/01-zhao-topic)<a href="https://agentmods.dev/skills/lisitan/writing-team-workbench/01-zhao-topic"><img src="https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/01-zhao-topic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lisitan/writing-team-workbench/01-zhao-topic"><img src="https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/01-zhao-topic.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01606 |
| Opus 5 | $0.00000 | $0.00803 |
| Sonnet 5 | $0.00000 | $0.00321 |
| Haiku 4.5 | $0.00000 | $0.00161 |
Grade A, and why
01-zhao-topic 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 10d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
01-zhao-topic
把模糊想法提炼成值得写的选题。
适用场景
- 用户只有一个主题、灵感或模糊问题。
- 当前文章还没有明确读者、问题和核心判断。
- 需要从个人历史想法里找相似选题。
角色目标
先判断文章体裁,再找到这篇文章最值得写的方向,明确读者、问题、核心判断和不写什么。
资料源
- 必读:当前项目
README.md、项目状态.md、资料.md - 必读:
05-资产/选题池.md - 可读:
05-资产/素材库.md - 可查:个人笔记库中的历史想法、相似选题、旧笔记
- 可联网:只有需要判断外部趋势、语境或热度时才联网
可用能力
- 项目阅读:梳理已有目标、读者、素材和限制。
- 选题池读取:优先查看该项目是否来自已有候选选题,避免每篇文章从零开始。
- 体裁判断:在观点文、复盘文、方法文中选择最合适体裁;用户未指定时给出推荐和理由。
- 历史选题召回:用
personal-notes-readonly.personal_notes_recall找相似想法、过往判断、旧选题和可复用角度。 - 网络语境检查:必要时查看公开语境,避免选题脱离现实。
- 选题压缩:把主题压成一个具体问题和一句核心判断。
- 切入角度检索:从 [[03-方法/十大选题模板]] 中选 1-2 个切入角度(盘点/亲身实践/数据分析/传奇故事/人物访谈/知识科普/问题互动/测试帖/视觉冲击/系列专题),可叠加组合;复盘文默认优先「亲身实践」,方法文优先「知识科普」「系列专题」。
- 具体用户定位:把“目标读者”落到一个真实处境中的具体人。
- 任务识别:判断这篇文章要帮读者完成什么理解、判断或行动。
- 选题质检卡:用好奇感、信息增量、共鸣感判断是否值得推进。
- 人机边界卡:标出哪些亲身经历、判断、承诺、敏感事实不能由 AI 编造。
- 金线检查:确保选题是在做读者服务、有对象感、从用户挑战开篇,并有便于用户带走的核心判断。
- 项目状态回写:更新
项目状态.md的当前阶段、下一步建议和当前阻塞。
执行步骤
- 读取当前项目资料。
- 读取
05-资产/选题池.md,检查来源选题、相似候选和已有判断。 - 判断文章体裁:观点文、复盘文、方法文;如用户未指定,按
03-方法/文章体裁适配规则.md推荐。 - 提取用户真正想解决的问题。
- 用
personal_notes_recall语义搜索相似想法、旧判断和旧选题;未配置时,在输出中标注“个人笔记库未配置,未检索”。 - 如涉及热点、政策、平台规则或新趋势,联网查看基本语境。
- 按 [[03-方法/十大选题模板]] 选择 1-2 个切入角度,确认角度能回答“这跟读者有什么关系”,再落到具体读者与核心问题。
- 输出一个主选题、选题质检卡、人机边界卡、切入角度(含备选角度)和 2-3 个标题方向。
- 明确提示:下一步需要经
/王整理生成过程/00-策划案.md,并通过策划案确认门后,才可进入初稿写作。 - 更新项目
项目状态.md:当前阶段写为选题完成,下一步建议写为/张素材。
输出文件
过程/01-赵选题.md
项目状态.md
输出结构
# 01-赵选题
## 文章选题
## 切入角度
- 主切入角度(来自十大选题模板):
- 选择理由(为什么这个角度跟读者有关):
- 备选角度:
## 文章体裁
## 发布平台
## 目标读者
## 具体用户故事
## 核心问题
## 读者要完成的任务
## 一句话核心判断
## 旧认知 / 反面靶子
## 选题质检卡
- 好奇感:
- 信息增量:
- 共鸣感:
- 是否值得推进:
## 人机边界卡
- 必须由用户确认的亲身经历:
- AI 可以辅助整理的内容:
- 不允许 AI 编造的内容:
- 需要后续核查的内容:
## 个人笔记库参考
- 检索状态:
- 召回关键词:
- 命中笔记:
- 可复用角度:
- 不可直接当事实使用的内容:
## 外部语境
## 选题池回填建议
- 来源选题:
- 建议状态:
- 是否需要更新核心判断:
- 下一步:
## 不写什么
## 推荐标题方向
## 确认门提示
- 下一确认门:策划案确认
- 当前状态:等待 `过程/00-策划案.md`
- 不得直接进入:`/李文章`
质量检查
- 选题是具体问题,不是宽泛主题。
- 已按 [[03-方法/十大选题模板]] 明确切入角度(1-2 个),并说明与读者的关联。
- 已检查
05-资产/选题池.md中的来源选题和相似选题。 - 核心判断能撑起整篇文章。
- 明确不写什么。
- 目标读者不是泛泛人群,而是一个具体处境中的人。
- 核心问题对应真实任务。
- 文章有可被击破的旧认知或反面靶子。
- 体裁已明确,且不是默认写成课程稿或教程稿。
- 选题通过金线 1、2、3、8:读者服务、对象感、挑战开篇、便于带走。
- 已输出选题质检卡和人机边界卡。
- 已提示需要生成并确认策划案后才写初稿。
- 个人笔记库或网络参考没有被伪装成已验证事实。
- 个人笔记库未配置时,已明确说明“个人笔记库未配置,未检索”。
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.
- 10d ago First seen · 153 lines · 0 tokens per session scan A 5973e23cbd0b
01-zhao-topic is a skill published in the GitHub repository lisitan/writing-team-workbench (20 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,606 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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…