Skip to content
Agentmart
Submit a tool

bug-finding

Use when reviewing existing code for latent logic, flow, feature, state, consistency, requirement, or API bugs with no failing symptom—read-only audit, not…

Skill by shiyuan17

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/shiyuan17-bug-finding

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when reviewing existing code for latent logic, flow, feature, state, consistency, requirement, or API bugs with no failing symptom—read-only audit, not root-cause debugging.

Use cases: backend, security

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/bug-finding

What's inside

Skill name
bug-finding
Description
Use when reviewing existing code for latent logic, flow, feature, state, consistency, requirement, or API bugs with no failing symptom—read-only audit, not root-cause debugging.
License
MIT
Instructions
18 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • openai.yaml · agents/
  • metadata.json

SKILL.md (first lines)

# Bug 查找审查

只读审查常见缺陷，不修改源码、配置、依赖、数据库或外部系统。

## 执行

1. 读取规则、需求/验收、入口、配置、契约、模型、状态定义、测试和相关变更。
2. 建立“需求→流程→状态→数据→事件/缓存→接口”关系链，必要时显式列出状态、事件、合法转换、非法转换、重复执行、撤回、异常恢复和终态。
3. 用已有测试、脚本、fixture 或浏览器执行最小关键路径；记录命令、输入、期望和实际，一次验证一个假设。
4. 工具不可用时停止运行层；静态推导不得声称已复现。继续检查调用方和消费方，确定影响范围。

重点覆盖业务逻辑、流程断链、功能缺失/多余、需求不符、非法状态迁移、数据一致性，以及接口参数、鉴权、错误、超时、重试、幂等和响应契约。对关键流程补列不变量：任何合法操作序列下都必须成立的业务、权限、审计或数据规则，并检查非法转换和恢复路径是否破坏这些不变量。

## 报告

按严重度列出位置、触发条件、期望/实际、证据、影响、根因假设、被破坏的不变量、最小修复方向和回归测试；结尾列未覆盖风险。证据标记为 **已确认事实**、**静态结论**、**待验证假设** 或 **验证受阻**，不把猜测当缺陷。

## 正反例

- 该用：「这个状态机有没有非法迁移」——没有失败症状的只读审查，产出缺陷清单而非修改。
- 不该用：已有失败症状且根因未定（先走系统排障），或本轮目标就是改代码（审查不是修改的替代）。
- 工具不可用：不能执行关键路径时停止运行层，把结论标为「验证受阻」，不把静态推导写成已复现缺陷。

From shiyuan17/Vibe-Harness, MIT.

More from shiyuan17/Vibe-Harness

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 14, 2026 (15 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/shiyuan17/Vibe-Harness
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from shiyuan17

Cite this page

bug-finding skill. Agent Mart. https://agentmart.dev/skills/shiyuan17-bug-finding (last updated 2026-10-24)