Agent skill

Bug Hunter

by digoal in digoal/blog

根据用户给出的行业名称(或默认使用热点社会新闻),抓取最新新闻热点,用"找世界bug"的视角——找出那些打眼一看就不合理的地方——深度分析根因、利益链条、监管盲区,并给出多维度解决思路,输出图文并茂(含SVG/Mermaid/ASCII图形)的Markdown文件,保存到项目markdown/目录。

GPL-2.0Auto-check passedDevelopment

Install Bug Hunter

skills CLI
$ npx skills add digoal/blog --skill bug-hunter -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install digoal/blog bug-hunter --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skills_for_claude_web/bug-hunter .claude/skills/bug-hunter && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bug-hunter
GitHub stars
8.6k
Token cost
~1k tokens
SKILL.md length
156 words
Files
1
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

根据用户给出的行业名称(或默认使用热点社会新闻),抓取最新新闻热点,用"找世界bug"的视角——找出那些打眼一看就不合理的地方——深度分析根因、利益链条、监管盲区,并给出多维度解决思路,输出图文并茂(含SVG/Mermaid/ASCII图形)的Markdown文件,保存到项目markdown/目录。

  • Works in 5 steps: :获取热点新闻 → 5:用户确认(Bug选择) → :Bug识别与分析框架 → …
  • Tasks that involve Diagrams
  • SKILL.md covers 核心理念, 执行步骤, 决策树速查(TL;DR) and 检查点设计(防止自主失控), plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Bug Hunter is an agent skill from digoal/blog. 根据用户给出的行业名称(或默认使用热点社会新闻),抓取最新新闻热点,用"找世界bug"的视角——找出那些打眼一看就不合理的地方——深度分析根因、利益链条、监管盲区,并给出多维度解决思路,输出图文并茂(含SVG/Mermaid/ASCII图形)的Markdown文件,保存到项目markdown/目录。 触发条件:用户提到"找bug"、"社会bug"、"不合理现象"、"帮我分析这个行业的问题"、"帮我找新闻里的bug"、"找热点新闻的漏洞"、"有什么不合理的地方"、"帮我分析为什么会这样"、"bug猎手"等。即使用户只说"帮我找找最近有什么奇怪的新闻"或"这个行业有哪些不合理",也应使用本 skill。

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Diagrams and Markdown. It works with Mermaid. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

  • Tasks that involve Diagrams
  • Tasks that involve Markdown

Example prompts

  • “找世界bug”
  • “帮我分析这个行业的问题”
  • “帮我找新闻里的bug”
  • “/bug-hunter”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. :获取热点新闻
  2. 5:用户确认(Bug选择)
  3. :Bug识别与分析框架
  4. :生成图形
  5. :输出格式

What it can do on your machine

Read from SKILL.md and the folder at commit 69fb793. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bug Hunter loads about 1k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 156 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from digoal/blog at commit 69fb793, republished under its GPL-2.0 licence (© digoal). 156 words, ~1,038 tokens.

Download SKILL.mdSave it as .claude/skills/bug-hunter/SKILL.md (or your agent's skills folder).
name
bug-hunter
description
根据用户给出的行业名称(或默认使用热点社会新闻),抓取最新新闻热点,用"找世界bug"的视角——找出那些打眼一看就不合理的地方——深度分析根因、利益链条、监管盲区,并给出多维度解决思路,输出图文并茂(含SVG/Mermaid/ASCII图形)的Markdown文件,保存到项目markdown/目录。 触发条件:用户提到"找bug"、"社会bug"、"不合理现象"、"帮我分析这个行业的问题"、"帮我找新闻里的bug"、"找热点新闻的漏洞"、"有什么不合理的地方"、"帮我分析为什么会这样"、"bug猎手"等。即使用户只说"帮我找找最近有什么奇怪的新闻"或"这个行业有哪些不合理",也应使用本 skill。

Bug Hunter — 社会Bug猎手

核心理念

找这个世界的 "bug"(打眼一看就不合理的地方),想办法解决它,就能体现你的价值,同时可能有商机。

本 Skill 的目标:从最新热点新闻中,用系统性视角找到那些"明明不对但大家习以为常"的现象,深度拆解根因,并给出可落地的解决路径。


执行步骤

Step 1:获取热点新闻

如果用户给出了行业名称,搜索:

  • {行业名} 最新新闻 热点 2025
  • {行业名} 问题 监管 争议
  • {行业名} 事件 曝光

如果用户没有给出行业,搜索社会热点:

  • 中国 社会热点新闻 今日
  • 热点事件 争议 不合理
  • 消费 食品安全 医疗 教育 热点

搜索要求:

  • 至少搜索 3 轮,覆盖不同角度
  • 优先选择近 30 天内、有争议性、涉及利益冲突的事件
  • 选出 2~3 个最具"bug感"的新闻事件

⚠️ 异常处理:

  • 如果搜索无结果 → 扩大关键词(如加"曝光""投诉""纠纷""骗局"),最多重试2轮
  • 如果仍无结果 → 告知用户"该行业近期未发现典型Bug,建议更换行业或1个月后再试"
  • 如果只有1个事件可用 → 降低要求至1个,但需补充1个跨行业类比案例

Step 1.5:用户确认(Bug选择)

展示备选Bug列表,让用户确认或调整:

📋 已识别Bug候选(2~3个),请选择或补充:

[1] {事件A} — bug感:⭐⭐⭐⭐⭐
    直觉反应:{一句话描述哪里不对劲}

[2] {事件B} — bug感:⭐⭐⭐⭐
    直觉反应:{一句话描述}

[3] {事件C} — bug感:⭐⭐⭐
    直觉反应:{一句话描述}

请回复序号(如"1,2"或"1并补充电商行业"】,或直接描述您观察到的bug

如果用户未回复(等待超5分钟)→ 继续使用默认选择,但报告中注明"基于行业通用判断"


Step 2:Bug识别与分析框架

对每个选出的事件,按以下维度展开分析,每项不超过3句话,防止空洞堆砌:

🔍 Bug定位(表象)— 1句话
  • 这件事打眼一看,哪里"不对劲"?
  • 普通人的直觉反应是什么?
🌐 根因拆解 — 每层1句,共3层
  • Why1(为什么会这样)→ 直接原因
  • Why2(为什么没人阻止)→ 结构性阻力
  • Why3(为什么会一直持续)→ 激励/利益格局
  • 利益链(谁得利/谁受损)→ 用表格列出关键角色
🏛️ 系统性分析 — 选2个框架深用
  • 五力分析:只写3行——权力最强方、动机最强方、维持现状的核心动力
  • 信息不对称:只写2行——谁有信息优势、谁处于盲区
  • 监管盲区:只写2行——失效的具体环节、执法成本为什么高
  • 激励错位:只写2行——每个参与者的错误激励是什么
💡 解决思路 — 4类×3要素

每类解法必须包含:

  1. 具体动作(做什么,不是"加强监管"而是"强制实时上传数据")
  2. 执行路径(谁来做,做什么检查)
  3. 可行性评级(⭐~⭐⭐⭐ + 理由1句话)
  4. 需求侧真伪(是真的痛点愿意付钱,还是伪痛点)

供给侧/需求侧/痛点真伪格式:

供给侧:能提供解决方案的主体(如技术公司/保险公司)
需求侧:真正愿意付费掏钱的人(如央国企IT部门/平台)
痛点真伪:✅真痛点 / ❌伪痛点(理由)
⚠️ 二阶Bug(Bug里的Bug)— 1段话
  • 写出最常见"解法"的局限性(1-2句话)
  • 写出这个解法会让什么问题恶化

Step 3:生成图形

图形优先级(必须/可选):

  1. ✅ Mermaid利益链条图(每个Bug必须)— 嵌入markdown,无需渲染
  2. ✅ ASCII鱼骨图(综合视角必须)— 共性根因展示,对齐整洁
  3. ✅ SVG四象限矩阵(综合视角必须)— 解决方案优先级矩阵

SVG四象限矩阵规范:

  • viewBox="0 0 800 600",深色背景#1a1a2e
  • 四象限颜色:#2d6a4f(绿)/#9d4edd(紫)/#0077b6(蓝)/#d62828(红)
  • 每个象限内放具体解决方案名称(8-12号字体)
  • 坐标轴标注"影响力 →"和"可行性 →"
  • 代码规范:SVG代码直接书写,不使用反引号包裹;保留注释,注释单独成行;每个元素一行;代码内部不能有空行

Step 4:输出格式

输出路径:markdown/bug-hunter-{行业或关键词}-{YYYYMMDD}.md

  • 行业名为中文:直接拼音首字母(如"电商直播"→bug-hunter-dszhibo-20260529)
  • 若markdown目录不存在 → 先创建:/Users/digoal/new/markdown/
文章结构模板
markdown
# 🔍 Bug猎手报告:{标题}

> 日期:{今日日期}
> 行业:{行业名 / 社会热点}

---

## 📰 今日热点速览

{2~3条新闻简介,含来源}

---

## 🐛 Bug #1:{事件名}

### 表象:打眼一看哪里不对?
{直觉描述}

### 根因拆解
{Why × 3层 + 利益链条}

[mermaid 利益链条图]

### 系统性分析
{五力分析 / 信息不对称 / 激励错位 / 监管盲区}

[ASCII鱼骨图]

### 💡 解决思路

| 维度 | 解法 | 可行性 | 潜在商机 | 商业模式 |
|------|------|--------|---------|---------|
| 技术 | ... | ⭐⭐⭐ | 有/无 | 供给侧/需求侧/痛点真伪 |
| 商业 | ... | ⭐⭐ | 有 | ... |
| 制度 | ... | ⭐ | 无 | ... |
| 社会 | ... | ⭐⭐⭐ | 间接 | ... |

### ⚠️ 二阶Bug:解法里的bug
{反思当前常见解法的局限}

---

## 🐛 Bug #2:...

(结构同上)

---

## 🗺️ 综合视角

[SVG四象限矩阵代码,直接书写不包裹反引号,注释单独成行]

{跨bug的共性根因总结}

---

## 🚀 行动建议

### 对个人
- ...

### 对创业者 / 投资者
- ...

### 对政策制定者
- ...

---

*本报告由Bug猎手Skill生成,仅供参考。发现更多bug,欢迎继续探索。*

决策树速查(TL;DR)

用户输入 → 有行业名?
  ├─ YES → 搜索3轮选Bug → Step1.5确认
  └─ NO → 搜索社会热点 → 选Bug → Step1.5确认

Step1.5 → 用户确认 → 分析2-3个Bug
  ├─ 每个Bug:表象→Why×3→利益链→系统分析→解决思路→二阶Bug
  ├─ 综合视角:共性根因→SVG矩阵→行动建议
  └─ 输出:markdown文件到markdown/

异常分支:
  ├─ 搜索0结果 → 扩大关键词重试2次 → 仍无则告知用户
  ├─ 只有1个Bug → 用1个+1个跨行业类比
  └─ 用户5分钟无回复 → 默认选择继续

检查点设计(防止自主失控)

检查点位置问题处理
Bug候选确认Step1.5分析的Bug不是用户想要的必须等用户回复后再深入分析
供给侧真伪Step2解决思路解法无可行商业模式每个解法必须写供给侧/需求侧/痛点真伪
图形完整性Step3缺少必须图形SVG矩阵/ASCII鱼骨图/Mermaid缺一不可
输出路径Step4目录不存在先创建/Users/digoal/new/markdown/再写入

注意事项

  • 保持批判性但建设性:不是为了批评而批评,而是为了找到解法
  • 数据支撑:尽量引用具体数据、案例、政策文件
  • 避免空洞结论:每条解法都要有具体的执行路径,不要超过3句话
  • 商机识别:明确指出哪些bug的解法可能孕育商业机会
  • 图形质量:SVG要精美(viewBox规范、颜色对比清晰)、Mermaid逻辑清晰、ASCII对齐整洁
  • 语言风格:犀利、直接、有洞察力,不说废话,适合公众号/知识社群传播

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/skills_for_claude_web/bug-hunter of digoal/blog.

Open the folder on GitHubat commit 69fb793

Compare with similar skills

Bug Hunter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bug Hunter compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bug Hunter this skilldigoal/blog8.6k—~1kAutomated safety check: PassGPL-2.0
Chatbot Mvp Distillationpdsuwwz/chatgpt-vue3-light-mvp578—~722Automated safety check: PassMIT
Chatbot Mvp Distillation Zhpdsuwwz/chatgpt-vue3-light-mvp578—~414Automated safety check: PassMIT
Markdown Mermaid WritingK-Dense-AI/scientific-agent-skills48k1 repos~4.2kAutomated safety check: NotesApache-2.0
Wiki Ado Convertmicrosoft/skills3.1k—~2.3kAutomated safety check: PassMIT
Markdown Mermaid Writingneflibata-feng/MyArxiv-Agent1265 repos~3.8kAutomated safety check: NotesApache-2.0

Similar skills

  • Chatbot Mvp Distillation

    pdsuwwz/chatgpt-vue3-light-mvp

    Distill the chatgpt-vue3-light-mvp project into reusable architecture for building similar ChatGPT-style web products in other repositories.

    578 GitHub stars~722 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Chatbot Mvp Distillation Zh

    pdsuwwz/chatgpt-vue3-light-mvp

    将 chatgpt-vue3-light-mvp 项目蒸馏为可迁移到其他项目的中文架构指南。适用于设计或实现类似 ChatGPT 的 Web 对话产品,包括 SSE/fetch 流式响应、模型适配器契约、打字机渲染、Markdown/代码/KaTeX/Mermaid 渲染、推理过程展示,以及从本 Vue 3 MVP 迁移到其他项目的方案规划。

    578 GitHub stars~414 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Markdown Mermaid Writing

    K-Dense-AI/scientific-agent-skills

    Writes scientific Markdown documentation and Mermaid diagrams for workflows, relationships, timelines, and schemas.

    48k GitHub starsUsed in 1 repo~4.2k tokens
    DevelopmentAuto-check: notes
  • Wiki Ado Convert

    microsoft/skills

    Official

    Converts VitePress/GFM wiki markdown to Azure DevOps Wiki-compatible format.

    3.1k GitHub stars~2.3k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Markdown Mermaid Writing

    neflibata-feng/MyArxiv-Agent

    Comprehensive markdown and Mermaid diagram writing skill that establishes text-based diagrams as the DEFAULT documentation standard.

    126 GitHub starsUsed in 5 repos~3.8k tokens
    DevelopmentAuto-check: notes
  • Bm Md

    miantiao-me/bm.md

    使用 bm.md 写作、改写、排版或渲染 Markdown;生成 Mermaid 与 AntV Infographic,设置图片尺寸、高亮重点,以及执行 HTML/纯文本转换和 Markdown lint

    616 GitHub stars~2.1k tokensUpdated 8 days ago
    Media & CreativeAuto-check passed

More from digoal/blog

All 98 skills in this repo
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated 10 days ago
    Auto-check passed
  • Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated 10 days ago
    Auto-check passed
  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated 10 days ago
    Auto-check passed
  • 从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated 10 days ago
    Auto-check passed
  • Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

    8.6k GitHub stars~1.8k tokensUpdated 10 days ago
    Auto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated 10 days ago
    Auto-check passed

Works with

Questions about Bug Hunter

What does Bug Hunter do?

根据用户给出的行业名称(或默认使用热点社会新闻),抓取最新新闻热点,用"找世界bug"的视角——找出那些打眼一看就不合理的地方——深度分析根因、利益链条、监管盲区,并给出多维度解决思路,输出图文并茂(含SVG/Mermaid/ASCII图形)的Markdown文件,保存到项目markdown/目录。. Bug Hunter is an agent skill from digoal/blog.

When should I use Bug Hunter?

Bug Hunter fits situations like: tasks that involve Diagrams; tasks that involve Markdown.

How do I install Bug Hunter in Claude Code?

Run `npx skills add digoal/blog --skill bug-hunter -a claude-code`. Or copy the skill folder (skills/skills_for_claude_web/bug-hunter in digoal/blog) into .claude/skills/bug-hunter in your project. Claude Code loads it when a task matches its description.

How do I install Bug Hunter in Codex?

Run `npx skills add digoal/blog --skill bug-hunter -a codex`. Or copy the skill folder (skills/skills_for_claude_web/bug-hunter in digoal/blog) into .agents/skills/bug-hunter in your project. Codex loads it when a task matches its description.

Can I use Bug Hunter in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill bug-hunter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bug-hunter, .gemini/skills/bug-hunter, .github/skills/bug-hunter and .opencode/skills/bug-hunter in your project.

What does Bug Hunter need to run?

SKILL.md names no scripts, command-line tools or credentials: Bug Hunter is instructions for the agent only.

Does Bug Hunter access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bug Hunter safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Bug Hunter use?

Bug Hunter is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bug Hunter use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Bug Hunter?

Skills that share tags, products or a category with Bug Hunter: Chatbot Mvp Distillation (pdsuwwz/chatgpt-vue3-light-mvp, 578 stars), Chatbot Mvp Distillation Zh (pdsuwwz/chatgpt-vue3-light-mvp, 578 stars), Markdown Mermaid Writing (K-Dense-AI/scientific-agent-skills, 48k stars) and Wiki Ado Convert (microsoft/skills, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bug Hunter?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,587 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on September 28, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.