代码 First Respond
- 作者仓库星标 0
- 作者仓库 nano-core
Code First Responder
When to use this skill
- Use when the user request matches this skill's domain and capabilities.
- Use when this workflow or toolchain is explicitly requested.
When not to use this skill
- Do not use when another skill is a better direct match for the task.
- Do not use when the request is outside this skill's scope.
When to load this skill
- Incoming task references failing tests, stack traces, or recent merges.
- User explicitly wants a "quick triage", "first look", or "rough fix plan".
- Another skill (e.g., Rapid Research) flagged new code issues that need confirmation.
Guardrails
- Never edit files before the failure is reproduced locally.
- Capture the exact command + exit code inside the debug report template.
- Prefer minimal diffs; defer major refactors to a follow-up task.
- If the failure cannot be reproduced quickly, escalate with the captured evidence and leave the repo untouched.
Five-step micro-playbook
- Snapshot context
- Record branch, latest commit hash, and dirty files.
- Paste the failure summary into
templates/debug_report_template.md.
- Reproduce fast
- Run the narrowest test or script possible.
- Store the exact CLI command and snippet of output.
- Isolate scope
- Identify the component or file set causing the issue.
- Outline suspected root causes without editing yet.
- Propose fix plan
- List concrete actions (edit file X, update test Y, run command Z).
- Mark each action as
must,optional, orblocked.
- Optional patch
- If the fix is obvious (<30 lines), apply it and run validation.
- Update the debug report with the diff summary and test status.
Output checklist
Refer to templates/fix_checklist.md and ensure every box is addressed:
- Failure reproduced?
- Minimal scope understood?
- Plan or patch documented?
- Validation command + result captured?
- Handover note written?
Response snippet to send back to the user
## Debug Status
- Branch/commit: ...
- Failure reproduced: yes/no (command)
- Root-cause hypothesis: ...
- Next actions: ...
## Attachments
- debug_report_template.md (updated)
Companion tools
run_commandfor fast tests.read_file+search_codefor targeted inspection.write_filefor updating the templates and final report.
- 流狐分类
- AI 智能
- 作者声明 Agent
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 作者 / 版本 / 许可
- @0-CYBERDYNE-SYSTEMS-0 · 未声明 license
- 流狐 Token 估算
- 低消耗
- 流狐接入估算
- 需简单配置
- 是否需要外部 API Key
- 未发现要求
- 检测到的系统要求
- 未声明
- 底层运行要求
- 未声明
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 检测到的网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
作者没有在当前 SKILL.md 中定义固定输出样例。 Use when the user request matches this skill's domain and capabilities. Use when this workflow or toolchain is explicitly requested.
Do not use when another skill is a better direct match for the task. Do not use when the request is outside this skill's scope.
Incoming task references failing tests, stack traces, or recent merges. User explicitly wants a "quick triage", "first look", or "rough fix plan". Another skill (e.g., Rapid Research) flagged new code issues that need confirmation.
Never edit files before the failure is reproduced locally. Capture the exact command + exit code inside the debug report template. Prefer minimal diffs; defer major refactors to a follow-up task.
Snapshot context Record branch, latest commit hash, and dirty files. Paste the failure summary into templates/debugreporttemplate.md.
Refer to templates/fixchecklist.md and ensure every box is addressed: Failure reproduced? Minimal scope understood?
# Code First Responder
## When to use this skill
- Use when the user request matches this skill's domain and capabilities.
- Use when this workflow or toolchain is explicitly requested.
## When not to use this skill
- Do not use when another skill is a better direct match for the task.
- Do not use when the request is outside this skill's scope.
## When to load this skill
- Incoming task references failing tests, stack traces, or recent merges.
- User explicitly wants a "quick triage", "first look", or "rough fix plan".
- Another skill (e.g., Rapid Research) flagged new code issues that need confirmation.
## Guardrails
1. Never edit files before the failure is reproduced locally.
2. Capture the exact command + exit code inside the debug report template.
3. Prefer minimal diffs; defer major refactors to a follow-up task.
4. If the failure cannot be reproduced quickly, escalate with the captured evidence and leave the repo untouched.
## Five-step micro-playbook
1. **Snapshot context**
- Record branch, latest commit hash, and dirty files.
- Paste the failure summary into `templates/debug_report_template.md`.
2. **Reproduce fast**
- Run the narrowest test or script possible.
- Store the exact CLI command and snippet of output.
3. **Isolate scope**
- Identify the component or file set causing the issue.
- Outline suspected root causes without editing yet.
4. **Propose fix plan**
- List concrete actions (edit file X, update test Y, run command Z).
- Mark each action as `must`, `optional`, or `blocked`.
5. **Optional patch**
- If the fix is obvious (<30 lines), apply it and run validation.
- Update the debug report with the diff summary and test status.
## Output checklist
… 作者原文负责流程事实;流狐只索引当前章节、要点、文件与命令。
章节 -> When to use this skill → When not to use this skill → When to load this skill → Guardrails → Five-step micro-playbook → Output checklist
要点 -> Snapshot context · Reproduce fast · Isolate scope · Propose fix plan · Optional patch
文件/命令 -> templates/debugreporttemplate.md · must · optional · blocked · templates/fixchecklist.md · runcommand · readfile · searchcode
内容 SHA-256 -> 370b510a1e68
方法与流程
适用与边界
原文中的明确线索
templates/debugreporttemplate.md、must、optional、blocked、templates/fixchecklist.md、runcommand、readfile、searchcode