topic-brainstormer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Topic Brainstormer

博客主题构思工具

Operator Context

操作上下文

This skill operates as an operator for topic ideation workflows, configuring Claude's behavior for generating blog post ideas that align with a content identity built around solving frustrating technical problems. It implements the Assess-Decide-Generate pattern -- gather signals, filter candidates, prioritize output -- with Domain Intelligence embedded in the content quality filter methodology.

本Skill作为主题构思工作流的操作器，用于配置Claude的行为，使其生成符合“解决棘手技术问题”这一内容定位的博客主题思路。它采用评估-决策-生成（Assess-Decide-Generate）模式——收集信号、筛选候选主题、优先输出——并在内容质量筛选方法中嵌入了领域智能。

Hardcoded Behaviors (Always Apply)

硬编码行为（始终适用）

CLAUDE.md Compliance: Read and follow repository CLAUDE.md before brainstorming
Over-Engineering Prevention: Generate topic ideas only. No outlines, no drafts, no full posts
content quality Filter Enforcement: Every topic MUST pass the vex test (frustration + resolution + value to others)
No Tutorial-Only Topics: Reject topics that are "how to do X" without a struggle narrative
No Opinion Pieces: Reject commentary without concrete hands-on experience
Priority Matrix Required: All outputs must include impact/vex/resolution scoring

遵循CLAUDE.md规范：头脑风暴前需阅读并遵循仓库中的CLAUDE.md文档
避免过度设计：仅生成主题思路，不提供大纲、草稿或完整文章
强制执行内容质量筛选：每个主题都必须通过vex测试（痛点+解决方案+对他人的价值）
拒绝纯教程类主题：淘汰仅为“如何做X”且无痛点叙事的主题
拒绝纯观点类内容：淘汰无具体实操经验支撑的评论类主题
必须包含优先级矩阵：所有输出都需包含影响力/痛点/解决方案评分

Default Behaviors (ON unless disabled)

默认行为（默认开启，可关闭）

Existing Post Analysis: Read existing posts to identify gaps and themes before generating
Multi-Source Generation: Mine from at least 2 different sources per session
Angle Suggestions: Include specific narrative angles for medium-priority topics
Specific Titles: Use failure-mode titles, not vague category titles
Complete Output: Show full brainstorm report with all sections

现有文章分析：生成主题前先阅读现有文章，识别内容空白和主题方向
多来源生成：每次会话至少从2个不同来源挖掘主题
角度建议：为中优先级主题提供具体叙事角度
具体标题：使用故障模式标题，而非模糊的分类标题
完整输出：展示包含所有板块的完整头脑风暴报告

Optional Behaviors (OFF unless enabled)

可选行为（默认关闭，可开启）

Deep Gap Analysis: Exhaustive scan of all cross-references and "see also" mentions
Tech Stack Expansion: Suggest adjacent technologies not yet covered
Series Planning: Group related topics into potential multi-part series

深度差距分析：全面扫描所有交叉引用和“另请参阅”的提及内容
技术栈扩展：建议尚未覆盖的相邻技术方向
系列规划：将相关主题分组为潜在的多部分系列内容

What This Skill CAN Do

本Skill可完成的工作

Generate topic ideas from problem mining (debugging sessions, errors, config struggles)
Identify content gaps based on existing post references and cross-links
Analyze technology patterns in existing content to find expansion opportunities
Apply the content quality filter to validate every topic candidate
Score topics by impact, vex level, and resolution satisfaction
Suggest specific narrative angles for each topic
Estimate word counts and categorize by priority tier

从问题挖掘（调试会话、错误、配置难题）中生成主题思路
根据现有文章的引用和交叉链接识别内容空白
分析现有内容的技术模式，寻找扩展机会
应用内容质量筛选器验证每个候选主题
按影响力、痛点程度和解决方案满意度为主题评分
为每个主题提供具体叙事角度建议
预估字数并按优先级层级分类

What This Skill CANNOT Do

本Skill无法完成的工作

Write blog posts (use blog-post-writer instead)
Create post outlines (use post-outliner instead)
Guarantee topics will resonate with readers (user judgment required)
Generate topics without applying the content quality filter
Accept tutorial-only or opinion-only topics that lack struggle narratives
Skip the priority scoring step

撰写博客文章（请使用blog-post-writer Skill）
创建文章大纲（请使用post-outliner Skill）
保证主题会引起读者共鸣（需用户自行判断）
生成未通过内容质量筛选的主题
接受缺乏痛点叙事的纯教程或纯观点类主题
跳过优先级评分步骤

Instructions

操作步骤

Phase 1: ASSESS

阶段1：评估（ASSESS）

Goal: Gather context about existing content and available topic sources.

Step 1: Scan existing content

Read all posts in the content directory. Document:

markdown

undefined

目标：收集现有内容和可用主题来源的上下文信息。

步骤1：扫描现有内容

阅读内容目录中的所有文章，并记录：

markdown

undefined

Content Landscape

内容现状

Posts found: [N] Content clusters: [list main themes] Technologies covered: [list] Last post date: [date]


**Step 2: Identify available sources**

Determine which topic sources have material to mine:
- Problem Mining: Recent debugging sessions, errors, config struggles
- Gap Analysis: Cross-references in existing posts that lead nowhere
- Tech Expansion: Adjacent technologies not yet covered

**Step 3: Note cross-references**

Extract all "see also", "related", and cross-reference mentions from existing posts. Flag any that point to content that does not exist.

**Gate**: Content landscape documented, at least 2 sources identified with material. Proceed only when gate passes.

已找到文章：[数量] 内容集群：[列出主要主题] 覆盖技术：[列出] 最新文章日期：[日期]


**步骤2：识别可用来源**

确定哪些主题来源有可挖掘的素材：
- 问题挖掘：近期调试会话、错误、配置难题
- 差距分析：现有文章中指向无效链接的交叉引用
- 技术扩展：尚未覆盖的相邻技术

**步骤3：记录交叉引用**

提取现有文章中所有“另请参阅”“相关内容”和交叉引用的提及，标记指向不存在内容的引用。

**准入条件**：已记录内容现状，且至少识别出2个有可用素材的来源。仅当满足条件时才可进入下一阶段。

Phase 2: DECIDE

阶段2：决策（DECIDE）

Goal: Generate topic candidates and filter them through the content quality test.

Step 1: Mine candidates from identified sources

Generate 5-10 raw topic candidates from at least 2 sources. For each candidate, capture:

Source (problem mining, gap analysis, or tech expansion)
Raw topic area
Initial vex signal (what frustration exists)

Step 2: Apply content quality filter to every candidate

Each topic must answer YES to all three questions:

Was there genuine frustration? Real time lost, multiple failed attempts, unclear docs, or unexpected behavior that blocked progress.
Is there a satisfying resolution? Clear fix exists, understanding gained, prevention strategy available, or "a-ha moment" to share.
Would this help others? Problem is reproducible, not too environment-specific, solution is actionable, frustration is relatable.

Step 3: Reject failing candidates

Remove any topic that fails the filter. Document why each rejection failed:

Rejected Topic	Failed Question	Reason
[topic]	[1, 2, or 3]	[why]

Gate: At least 3 candidates pass the content quality filter. If fewer than 3 pass, return to Step 1 with different sources. Proceed only when gate passes.

目标：生成候选主题并通过内容质量测试筛选。

步骤1：从已识别来源挖掘候选主题

从至少2个来源生成5-10个原始候选主题，每个主题需记录：

来源（问题挖掘、差距分析或技术扩展）
原始主题领域
初始痛点信号（存在哪些困扰）

步骤2：对每个候选主题应用内容质量筛选

每个主题必须全部满足以下三个问题：

是否存在真实痛点？ 确实花费了时间、多次尝试失败、文档不清晰，或遇到阻碍进度的意外行为。
是否有令人满意的解决方案？ 存在明确的修复方法、获得了新认知、有预防策略，或有可分享的“顿悟时刻”。
是否对他人有帮助？ 问题可复现、不局限于特定环境、解决方案可落地、痛点具有普遍性。

步骤3：淘汰未通过筛选的候选主题

移除任何未通过筛选的主题，并记录淘汰原因：

被淘汰主题	未通过问题编号	原因
[主题内容]	[1、2或3]	[具体原因]

准入条件：至少3个候选主题通过内容质量筛选。若通过数量不足3个，返回步骤1更换来源重新挖掘。仅当满足条件时才可进入下一阶段。

Phase 3: GENERATE

阶段3：生成（GENERATE）

Goal: Score, prioritize, and present the filtered topic list.

Step 1: Score each passing topic

Apply the priority matrix to every candidate:

Impact (1-5):     How many people face this problem?
Vex Level (1-5):  How frustrating is the problem?
Resolution (1-5): How satisfying is the solution?

Priority Score = Impact x Vex Level x Resolution

  60-125: HIGH PRIORITY    - Write this soon
  30-59:  MEDIUM PRIORITY  - Good candidate with right angle
  15-29:  LOW PRIORITY     - Needs more vex or broader impact
  1-14:   SKIP             - Not enough value for readers

Step 2: Write specific titles

Replace vague category titles with failure-mode titles:

Bad: "Kubernetes Networking Issues"
Good: "Pod-to-Pod Traffic Works But Service Discovery Fails"

Step 3: Present prioritized output

markdown

undefined

目标：为通过筛选的主题评分、排序并呈现。

步骤1：为每个通过筛选的主题评分

对每个候选主题应用优先级矩阵：

影响力（1-5）：     有多少人会遇到这个问题？
痛点程度（1-5）：  这个问题的困扰程度如何？
解决方案（1-5）：  解决方案的满意度如何？

优先级得分 = 影响力 × 痛点程度 × 解决方案

  60-125: 高优先级    - 应尽快撰写
  30-59:  中优先级  - 合适的选题，但需明确角度
  15-29:  低优先级     - 需强化痛点或扩大影响力
  1-14:   跳过             - 对读者价值不足

步骤2：撰写具体标题

将模糊的分类标题替换为故障模式标题：

不佳示例："Kubernetes网络问题"
优质示例："Pod间通信正常但服务发现失败"

步骤3：呈现排序后的主题列表

markdown

undefined

Topic Brainstorm Results

主题头脑风暴结果

Source: [problem mining / gap analysis / tech expansion]

来源：[问题挖掘 / 差距分析 / 技术扩展]

HIGH PRIORITY (Strong vex potential)

高优先级（痛点潜力强）

"[Specific Topic Title]" The Vex: [What frustration this addresses] The Joy: [What satisfying resolution looks like] Fits existing: [Which content cluster this joins] Estimated: [word count range] Score: Impact(N) x Vex(N) x Resolution(N) = [total]

"[具体主题标题]" 痛点：[该主题解决的困扰] 价值：[令人满意的解决方案] 适配现有内容：[所属的内容集群] 预估字数：[字数范围] 得分：影响力(N) × 痛点程度(N) × 解决方案(N) = [总分]

MEDIUM PRIORITY (Good but needs angle)

中优先级（优质选题但需明确角度）

"[Specific Topic Title]" The Vex: [frustration] The Joy: [resolution] Angle needed: [What narrative hook would strengthen this] Score: Impact(N) x Vex(N) x Resolution(N) = [total]

"[具体主题标题]" 痛点：[困扰内容] 价值：[解决方案] 所需角度：[可强化的叙事切入点] 得分：影响力(N) × 痛点程度(N) × 解决方案(N) = [总分]

GAP FILL (Based on existing content)

空白填补（基于现有内容）

"[Specific Topic Title]" Referenced in: [which post mentions this] Missing: [what content would fill the gap] Score: Impact(N) x Vex(N) x Resolution(N) = [total]

"[具体主题标题]" 被引用位置：[提及该主题的文章] 缺失内容：[需填补的内容] 得分：影响力(N) × 痛点程度(N) × 解决方案(N) = [总分]

Recommendations

Examples

示例

Example 1: Problem Mining Session

示例1：问题挖掘会话

User says: "I spent all day debugging a Hugo build issue, brainstorm some topics" Actions:

Scan existing posts for Hugo coverage (ASSESS)
Mine the debugging session for vex signals, filter through content quality test (DECIDE)
Score and present topics with the build issue as high-priority candidate (GENERATE) Result: Prioritized topic list with the fresh debugging experience as top pick

用户提问："我花了一整天调试Hugo构建问题，帮我头脑风暴一些主题" 操作步骤：

扫描现有文章中关于Hugo的内容（评估阶段）
从调试会话中挖掘痛点信号，通过内容质量测试筛选（决策阶段）
为主题评分并将该构建问题列为高优先级候选（生成阶段）结果：以最新调试经验为首选的优先级主题列表

Example 2: Content Gap Analysis

示例2：内容差距分析

User says: "What should I write about next?" Actions:

Read all existing posts, extract cross-references and themes (ASSESS)
Identify referenced-but-missing content, filter through content quality test (DECIDE)
Score gap-fill topics alongside any problem-mined candidates (GENERATE) Result: Prioritized list mixing gap fills with fresh topic candidates

用户提问："我接下来该写什么？" 操作步骤：

阅读所有现有文章，提取交叉引用和主题方向（评估阶段）
识别被引用但缺失的内容，通过内容质量测试筛选（决策阶段）
为空白填补主题和问题挖掘主题一同评分（生成阶段）结果：混合空白填补主题和新候选主题的优先级列表

Error Handling

错误处理

Error: "No Existing Posts to Analyze"

错误："无现有文章可分析"

Cause: Content directory is empty or does not exist yet Solution:

Focus entirely on problem mining instead of gap analysis
Ask user about recent debugging sessions or technical struggles
Check repository CLAUDE.md or project docs for tech stack hints
Generate topics from technology interests alone

原因：内容目录为空或不存在解决方案：

完全聚焦于问题挖掘，而非差距分析
询问用户近期的调试会话或技术难题
查看仓库CLAUDE.md或项目文档获取技术栈线索
仅根据技术兴趣生成主题

Error: "All Candidates Fail content quality Filter"

错误："所有候选主题未通过内容质量筛选"

Cause: Sources lack genuine frustration signals or resolutions Solution:

Ask probing questions: "What broke recently?" or "What took hours to fix?"
Reframe tutorial candidates: "What surprised you?" or "What mistake does everyone make?"
Shift to a different source (e.g., from gap analysis to problem mining)
If no vex exists, acknowledge honestly -- not every session yields topics

原因：来源缺乏真实痛点信号或解决方案解决方案：

提出针对性问题："最近什么东西出故障了？"或"什么问题花了好几个小时才解决？"
重构教程类候选主题："什么内容让你感到意外？"或"大家都会犯什么错误？"
切换到其他来源（例如从差距分析转为问题挖掘）
若确实无痛点，需如实告知——并非每次会话都能产出合适主题

Error: "Topic Too Broad to Score"

错误："主题过于宽泛无法评分"

Cause: Candidate is a category ("Kubernetes networking") rather than a specific problem Solution:

Break into multiple specific failure modes
Ask: "What specific moment was most frustrating?"
Use failure-mode title pattern: "[Thing A] works but [Thing B] fails"

原因：候选主题是一个分类（如"Kubernetes网络"）而非具体问题解决方案：

将其拆分为多个具体故障模式
询问："哪个具体时刻最让你困扰？"
使用故障模式标题格式："[A功能]正常但[B功能]失效"

Error: "Resolution Unclear or Missing"

错误："解决方案不明确或缺失"

Cause: User has an ongoing issue without a resolution, or the fix is a workaround with no understanding Solution:

Ask: "Did you solve it? How?"
If unresolved, defer the topic until resolution is found
If workaround-only, assess whether "understanding why the workaround works" provides enough joy
Consider documenting the investigation so far as a "part 1" topic (requires series planning)

原因：用户的问题尚未解决，或仅有无理论支撑的临时 workaround 解决方案：

询问："你解决了吗？怎么解决的？"
若未解决，推迟该主题直至找到解决方案
若仅为workaround，评估“理解workaround生效原因”是否能提供足够价值
考虑将目前的调查过程作为“第一部分”主题记录（需开启系列规划功能）

Anti-Patterns

反模式

Anti-Pattern 1: Generating Tutorial Topics

反模式1：生成纯教程类主题

What it looks like: "How to Set Up Hugo" with vex listed as "learning a new tool" Why wrong: No actual frustration. "Learning something new" is not a vex. Official docs already cover installation. Do instead: Find the specific friction point. "Hugo Local Build Works But Cloudflare Deploy Fails" has real vex (version mismatch between local and CI).

表现形式："如何搭建Hugo"，痛点列为"学习新工具" 错误原因：无真实痛点。"学习新事物"并非痛点，官方文档已覆盖安装内容。 正确做法：找到具体摩擦点。"Hugo本地构建正常但Cloudflare部署失败"包含真实痛点（本地与CI环境的版本不匹配）。

Anti-Pattern 2: Opinion Without Experience

反模式2：无实操支撑的观点类主题

What it looks like: "Why Go Is Better Than Python for CLI Tools" with vex listed as "other languages are slower" Why wrong: This is debate, not experience. No specific problem was solved, no measurable outcome. Do instead: Ground in measurement. "Rewriting a Python CLI in Go Cut Startup Time by 10x" has concrete vex (400ms startup delay) and concrete joy (40ms result).

表现形式："为什么Go比Python更适合CLI工具"，痛点列为"其他语言速度慢" 错误原因：这是辩论而非实操经验。无具体解决的问题，无可衡量的结果。 正确做法：基于实际数据。"将Python CLI重写为Go后启动时间缩短10倍"包含具体痛点（400ms启动延迟）和具体价值（40ms启动速度）。

Anti-Pattern 3: Skipping the content quality Filter

反模式3：跳过内容质量筛选

What it looks like: Generating 10 topics and presenting all of them without evaluating each against the three-question test. Why wrong: Quantity over quality. Dilutes content identity. User must re-evaluate every topic manually. Do instead: Apply the filter to every candidate. Reject topics that fail any question. Only present topics that pass all three.

表现形式：生成10个主题并全部呈现，未逐一通过三问题测试评估。 错误原因：重数量轻质量，稀释内容定位，用户需手动重新评估所有主题。 正确做法：对每个候选主题应用筛选器，淘汰未通过任意一个问题的主题，仅呈现全部通过的主题。

Anti-Pattern 4: Vague Topic Titles

反模式4：模糊的主题标题

What it looks like: "Kubernetes Networking Issues" or "Docker Problems" Why wrong: Too broad to act on. Which issues? What specifically failed? Reader cannot tell what the post is about. Do instead: Use failure-mode titles. "CoreDNS Returns NXDOMAIN for Internal Services" or "NetworkPolicy Blocks Traffic It Shouldn't" are specific and signal real vex.

表现形式："Kubernetes网络问题"或"Docker故障" 错误原因：过于宽泛无法落地。具体是什么问题？哪里失效了？读者无法知晓文章内容。 正确做法：使用故障模式标题。"CoreDNS为内部服务返回NXDOMAIN"或"NetworkPolicy错误拦截流量"更具体，且传递了真实痛点信号。

Anti-Pattern 5: Missing Priority Scoring

反模式5：缺失优先级评分

What it looks like: Presenting a topic list without impact/vex/resolution scores or priority tiers. Why wrong: No way to prioritize. User must mentally re-evaluate all topics to decide what to write first. Do instead: Always include the priority matrix with scores for every topic. Always include recommendations (top pick, quick win, deep dive).

表现形式：呈现主题列表但无影响力/痛点/解决方案评分或优先级层级。 错误原因：无法区分优先级，用户需手动重新评估所有主题以确定撰写顺序。 正确做法：始终为所有主题提供优先级矩阵评分，并附带推荐建议（首选、快速产出、深度钻研）。

Topic Source Quick Reference

主题来源快速参考

Problem Mining Signals

问题挖掘信号

Signal	Where to Find	Topic Potential
Debugging sessions	Recent git commits, shell history	High - fresh frustration
Stack Overflow searches	Browser history, bookmarks	High - common problems
Error messages	Logs, terminal output	Medium - depends on depth
Configuration struggles	Config file changes, dotfiles	Medium - relatable pain
"This took forever"	User conversation, retrospectives	High - strong vex signal

信号	查找位置	主题潜力
调试会话	近期Git提交、Shell历史	高 - 新鲜痛点
Stack Overflow搜索记录	浏览器历史、书签	高 - 常见问题
错误信息	日志、终端输出	中 - 取决于深度
配置难题	配置文件变更、dotfiles	中 - 普遍痛点
"这花了好长时间"	用户对话、回顾会议	高 - 强烈痛点信号

Gap Analysis Signals

差距分析信号

Gap Type	How to Identify	Value
"See also" missing	Referenced but no post exists	High - reader expectation
Prerequisites assumed	"Assuming you know X" statements	Medium - onboarding help
Incomplete series	"Part 1" with no Part 2	Medium - completeness
Follow-up questions	Comments, emails, feedback	High - proven demand

空白类型	识别方式	价值
"另请参阅"指向缺失内容	被引用但无对应文章	高 - 读者有预期
假设用户已掌握前置知识	包含“假设你了解X”的表述	中 - 帮助新用户入门
未完成的系列内容	有“第一部分”但无后续	中 - 完善内容体系
读者跟进问题	评论、邮件、反馈	高 - 已验证的需求

Technology Expansion Strategy

技术扩展策略

Same tool, different feature (Hugo -> Hugo modules)
Same category, different tool (Hugo -> Zola)
Integration between covered technologies (Hugo + Cloudflare Pages)
Common pain points in the ecosystem

同一工具的不同功能（Hugo -> Hugo模块）
同一类别不同工具（Hugo -> Zola）
已覆盖技术的集成（Hugo + Cloudflare Pages）
生态系统中的常见痛点

References

参考文献

This skill uses these shared patterns:

Anti-Rationalization - Prevents shortcut rationalizations
Verification Checklist - Pre-completion checks

本Skill使用以下共享模式：

反合理化 - 防止捷径式合理化
验证清单 - 完成前检查

Domain-Specific Anti-Rationalization

领域特定反合理化

Rationalization	Why It's Wrong	Required Action
"These are all good topics"	Unfiltered lists waste user time	Apply content quality filter to every candidate
"Close enough to vex"	Weak vex = weak post	Reject or find stronger frustration signal
"Scoring slows me down"	Unscored lists require user re-evaluation	Complete priority matrix for all topics
"The title can be refined later"	Vague titles hide weak topics	Use failure-mode titles now

合理化借口	错误原因	要求操作
"这些主题都不错"	未过滤的列表浪费用户时间	对每个候选主题应用内容质量筛选
"足够接近痛点了"	弱痛点=劣质文章	淘汰或寻找更强烈的痛点信号
"评分太耗时"	未评分的列表需用户重新评估	为所有主题完成优先级矩阵评分
"标题之后再细化"	模糊标题隐藏劣质主题	现在就使用故障模式标题

Reference Files

参考文件

${CLAUDE_SKILL_DIR}/references/content-filter.md

: Detailed filter criteria and examples

${CLAUDE_SKILL_DIR}/references/topic-sources.md

: Mining strategies for each source type

${CLAUDE_SKILL_DIR}/references/priority-scoring.md

: Scoring rubrics and examples

${CLAUDE_SKILL_DIR}/references/content-filter.md

: 详细筛选标准和示例

${CLAUDE_SKILL_DIR}/references/topic-sources.md

: 各来源的挖掘策略

${CLAUDE_SKILL_DIR}/references/priority-scoring.md

: 评分标准和示例