evoflow-debugging SKILL.md skillA
evoflow-debugging from evovexai/evoflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add evovexai/evoflow/evoflow-debugging@git:20260912.6c490fdPins git:20260912.6c490fd in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- evovexai/evoflow
- Path
skills/public/evoflow-debugging/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260912.6c490fd, committed Sep 12, 2026
- Size
- 2,776 bytes
- Repository stars
- 611
- License
- a license file GitHub does not identify
EvoFlow 项目内 Bug / 行为不符 / 数据展示错误排查。先定验收与 ground truth，沿数据流找第一个错层，三条 Gate（真实证据、生产消费函数、最小复现）后再改代码。用户报功能异常、UI 与 API 不一致、测试失败、运维页数据不对时使用；深度方法论可读 superpowers-systematic-debugging。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# EvoFlow 问题排查
适用：功能异常、UI 与预期不符、API 字段不对、测试失败、性能/回归等**需要找根因并修复**的任务。
通用调试心法（四阶段、根因追踪等）可读 **superpowers-systematic-debugging**；本文聚焦 **EvoFlow 仓库 + 工具链**。
## 0. 先定验收（动手改代码前必做）
用一句话写清：
- **怎样算对**
- **ground truth** 是哪条数据（API 响应字段 / DB 行 / 日志 / 测试断言）
- **明确不做什么**（范围外的不顺手改）
## 1. 沿数据流定层（禁止盲改 UI）
沿链路找**第一个错的数据**：
`用户所见 → 前端渲染 → API 字段 → 后端聚合/摘要 → 存储/上游写入`
**API/存储已错 → 先修后端，不要先改前端映射。**
## 2. 三条 Gate（违反则禁止提交代码改动）
1. **一条真实证据**：贴出或读取错误态原始数据（curl/API JSON、日志、DB 字段、失败测试输出）。
2. **责任边界**：指出**谁生产、谁消费**该字段/行为（函数名或文件路径）。
3. **可复现**：最小输入复现「输入 A → 输出 B（错的）」——单元测试 mock、短脚本、或直接调责任函数。**读代码觉得对 ≠ 验证通过。**
## 3. 验证顺序
1. **标准路径**：文档/最常见格式 → 应通过
2. **真实路径**：生产或用户提供的 payload
3. **边界路径**：空值、旧格式、流式落库、fallback 字段（如 `additional_kwargs`、`{type, data}` wire format）
标准路径过、真实/边界挂 → 补解析/兼容，勿推翻整条链路。
## 4. 修复纪律
- **一次只动一层**；改完立刻跑验证（测试 / API / 复现脚本）
- **最小 diff**：只修根因，不顺手重构
- **禁止无证据回退**：未证明改错时，不要整片 revert
- **防再犯**：wire format / 摘要 / 序列化类问题加测**真实结构**的回归测试
## 5. 与本项目工具的配合
- **先** `scenario(activate, agent)`，再 `rg` / `search_code_index` / `read` / `worker`
- 跑验证：`terminal`（pytest、curl、短脚本）
- 可并行、边界清晰的子问题：`subagent` 委派，主会话汇总后再改
## 6. 交付说明
回复用户时：**根因（一句）· 改了哪一层 · 如何验证**（重启谁 / 看哪个字段 / 跑哪条测试）。Read the whole file at its exact version.
How to install
mdr add evovexai/evoflow/evoflow-debugging@sha256:838e16a85f355d8bThe line at the top of this page pins the label git:20260912.6c490fd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_w2gwmgpdlx7vxxqv)
6 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 12, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2776 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
evovexai/evoflow · 611 stars · license a license file GitHub does not identify · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_w2gwmgpdlx7vxxqv GET https://markdownregistry.com/api/v1/resolve?ref=evovexai/evoflow/evoflow-debugging GET https://markdownregistry.com/api/v1/blob/838e16a85f355d8bb261024838dd9182f975c14e6f03c43d48f4b0ec7bce03b2
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.