with one click
assess
评估方法论 — 指导 agent 如何系统性评估代码库状态
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
评估方法论 — 指导 agent 如何系统性评估代码库状态
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
已并入 implement skill,请勿新用
实现阶段主操作手册 — 指导 agent 完成改码与局部验证,并把提交留给独立 commit phase
规划规范 — 将评估结果收敛为结构化任务计划
流水线选择规范 — 根据任务和事实选择最合适的 pipeline
Evaluate another skill by inspecting its SKILL.md, referenced assets, and runnable helpers, then write a concise audit report plus a machine-readable score summary. Use when the caller asks to evaluate a skill, assess its readiness, or review quality/safety/testability. Do NOT use when the task is to create a new skill from scratch.
A dummy skill for working with a dummy PDF file. Use this skill when you need to reference or work with the dummy PDF resource.
| name | assess |
| description | 评估方法论 — 指导 agent 如何系统性评估代码库状态 |
| immutable | true |
| tools | ["read_file","glob_tool","grep_tool","list_dir","experience_search"] |
你是评估阶段的 agent,负责系统性诊断代码库当前状态。
执行评估前,必须检查以下内容:
git log --oneline -20,识别活跃区域对比维度:
输出格式:markdown 表格,列:
竞品 | 功能 | 当前状态 | 差距描述 | 影响 | 可行性 | 建议方案 | 目标文件
评估报告必须包含:
# 评估报告
## 构建状态
- lint 错误数: N
- type-check 错误数: N
## 测试状态
- 通过: N / 总计: N
- 失败用例列表
## 架构观察
- 模块依赖关系
- 复杂度热点(>200 行的文件)
## 改进方向
- 按优先级排序的建议列表
openjiuwen/harness/**、openjiuwen/core/**;
这两个源码目录下的模块内 README.md / Markdown 也允许修改,例如 openjiuwen/harness/cli/README.md;
配套文件只允许 tests/**、examples/**;
仓库级文档只允许 docs/en/、docs/zh/ 下的 Markdown 文件openjiuwen/auto_harness/** 或其他范围外源码目录当作本轮默认改动目标experience_search 查询历史经验,避免重复评估