writing-team-workbench: Skill for Claude Code

.claude/skills/01-zhao-topic/SKILL.md

01-zhao-topic is a skill for Claude Code from lisitan/writing-team-workbench. It costs 0 tokens per session (1,606 once invoked), scanned A, original, MIT.

An editorial planning workflow for turning a vague idea into a focused article topic. It identifies the intended reader, main question, central argument, article type, and boundaries.

In plain words
What is it for?
Use it to choose an angle for an opinion, retrospective, or how-to article; search prior notes; check relevant public context; and record the project's next step.
Why use it?
It prevents writing from starting before the topic and audience are clear, and can surface related ideas and supporting material from the project.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is lisitan/writing-team-workbench's own configuration. It tells Claude Code how to work on writing-team-workbench itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything writing-team-workbench configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/lisitan/writing-team-workbench/main/.claude/skills/01-zhao-topic/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lisitan/writing-team-workbench

Made for: Claude Code.

Wrote 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.

agentmods badge for 01-zhao-topic

README.md
[![agentmods](https://agentmods.dev/badge/skills/lisitan/writing-team-workbench/01-zhao-topic/github.svg)](https://agentmods.dev/skills/lisitan/writing-team-workbench/01-zhao-topic)
Your own site
<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.

agentmods 80×15 button for 01-zhao-topic

Your own site · 80×15
<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>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,606 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 5973e23cbd0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

.claude/skills/01-zhao-topic/SKILL.md · 153 lines

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

  1. 读取当前项目资料。
  2. 读取 05-资产/选题池.md,检查来源选题、相似候选和已有判断。
  3. 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。
  4. 提取用户真正想解决的问题。
  5. 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”。
  6. 如涉及热点、政策、平台规则或新趋势,联网查看基本语境。
  7. 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。
  8. 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。
  9. 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。
  10. 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”。

Read the full file on GitHub · 153 lines

Changes

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.

  1. 10d ago First seen · 153 lines · 0 tokens per session scan A 5973e23cbd0b

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens