Chalk Labs
Need help deploying debug?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/chengxuniucode-debug
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.
About
Reviews
Write a reviewNo 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/debug
What's inside
- Skill name
debug- Description
- 验证失败时的自动修复循环
- License
- MIT
- Instructions
- 141 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Debug Skill
## 目标
当 verify 门禁失败时,自动分析错误并尝试修复。
最多尝试 N 次(默认 3),超过则暂停等待人工。
## 执行流程
```
verify.fail
│
▼
[分析错误类型]
│
├── 编译错误 → 语法/类型修复
├── 测试失败 → 逻辑修复
├── 启动失败 → 配置/依赖修复
└── 安全问题 → 报告给用户(不自动修复)
│
▼
[应用修复]
│
▼
[重新 verify]
│
├── PASS → 继续流程
└── FAIL → 递增计数器
│
├── count < limit → 重新分析
└── count >= limit → 断路器打开
```
## 错误分析策略
### 编译错误
```
1. 提取错误信息(文件、行号、错误类型)
2. 读取相关代码上下文(前后 10 行)
3. 判断错误类型:
- 类型错误 → 修正类型定义
- 导入错误 → 修正导入路径
- 语法错误 → 修正语法
- 缺失定义 → 补充定义
4. 应用修复
5. 重新编译验证
```
### 测试失败
```
1. 提取失败的测试名和断言信息
2. 区分:
- 测试本身有误 → 不修改测试(除非明确是测试 bug)
- 实现逻辑有误 → 修改实现代码
3. 读取测试期望和实际输出的差异
4. 分析 root cause
5. 修复实现代码
6. 重新运行失败的测试
```
### 启动失败
```
1. 检查启动日志
2. 常见原因:
- 端口占用 → 使用其他端口或等待
- 环境变量缺失 → 检查 .env.example
- 依赖未安装 → 运行安装命令
- 配置错误 → 修正配置文件
3. 修复后重新启动验证
```
## 已知问题匹配
在尝试修复前,先检查 `known-issues.md`:
- 如果错误模式匹配已知问题 → 直接应用已知解法
- 节省反复试错的时间
## 修复记录
每次修复都记录:
```markdown
## Debug Attempt {N}
- Gate: {which gate failed}
- Error: {error message}
- Analysis: {root cause}
- Fix: {what was changed}
- Result: {pass/still-fail}
```
## 断路器
```yaml
circuit_breaker:
max_attempts: 3 # 同一错误最多尝试 3 次
consecutive_fails: 2 # 连续 2 个不同错误也触发
cooldown: "human_input" # 暂停等待人工
output_on_break:
- error_summary
- attempted_fixes
- suggested_directions
- related_known_issues
```
## 暂停时输出格式
```markdown
# Debug Paused — Human Input Needed
## 问题
{错误描述}
## 已尝试
1. {尝试 1 及结果}
2. {尝试 2 及结果}From chengxuniucode/ForgeTeam, MIT.
More from chengxuniucode/ForgeTeam
- 0.551score
using-forgeteam
chengxuniucode
ForgeTeam workflow bootstrap: select and apply the existing delivery Skills before starting work
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
ship
chengxuniucode
提交代码、归档 spec、生成 changelog
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
review
chengxuniucode
自动代码评审,检查质量和一致性
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
memory
chengxuniucode
跨会话记忆管理:保存进度 + 提取经验
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
html
chengxuniucode
生成静态 HTML 原型,可视化确认功能与交互后再进入开发
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
propose
chengxuniucode
需求澄清与方案选型,生成 proposal.md
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
evolve
chengxuniucode
自进化能力:感知生态变化、评估融合方案、驱动版本迭代
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
onboard
chengxuniucode
项目画像生成,扫描项目结构并写入 memory
SkillBFreshness: B★ 2Claude Code +9 - 0.544score
integration-mq
chengxuniucode
消息队列集成(Kafka/RabbitMQ/RocketMQ)
SkillBFreshness: B★ 2Claude Code +9 - 0.542score
skillhub
chengxuniucode
Forge-skillHub integration gateway for discovering and managing reusable Forge skills
SkillBFreshness: B★ 2Claude Code +9 - 0.541score
ui-theme
chengxuniucode
企业 UI 主题和设计系统集成
SkillBFreshness: B★ 2Claude Code +9 - 0.541score
deploy-k8s
chengxuniucode
Kubernetes 部署配置生成
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- May 24, 2026 (5 months ago)
- Last release
- Aug 5, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/chengxuniucode/ForgeTeam
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from chengxuniucode
- 0.551score
using-forgeteam
chengxuniucode
ForgeTeam workflow bootstrap: select and apply the existing delivery Skills before starting work
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
onboard
chengxuniucode
项目画像生成,扫描项目结构并写入 memory
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
evolve
chengxuniucode
自进化能力:感知生态变化、评估融合方案、驱动版本迭代
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
memory
chengxuniucode
跨会话记忆管理:保存进度 + 提取经验
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
html
chengxuniucode
生成静态 HTML 原型,可视化确认功能与交互后再进入开发
SkillBFreshness: B★ 2Claude Code +9 - 0.545score
propose
chengxuniucode
需求澄清与方案选型,生成 proposal.md
SkillBFreshness: B★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get debug running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
debug skill. Agent Mart. https://agentmart.dev/skills/chengxuniucode-debug (last updated 2026-10-24)