dual-axis-skill-reviewer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Dual Axis Skill Reviewer

双轴Skill审查工具

Run the dual-axis reviewer script and save reports to

reports/

The script supports:

Random or fixed skill selection
Auto-axis scoring with optional test execution
LLM prompt generation
LLM JSON review merge with weighted final score
Cross-project review via
```
--project-root
```

运行双轴审查脚本并将报告保存至

reports/

目录。

该脚本支持：

随机或固定选择Skill
自动轴评分（可选执行测试）
LLM提示词生成
LLM JSON审查结果合并与加权最终评分
通过
```
--project-root
```
实现跨项目审查

When to Use

适用场景

Need reproducible scoring for one skill in
```
skills/*/SKILL.md
```
.
Need improvement items when final score is below 90.
Need both deterministic checks and qualitative LLM code/content review.
Need to review skills in a different project from the command line.

需要为
```
skills/*/SKILL.md
```
中的单个Skill生成可复现的评分。
当最终评分低于90分时，需要获取改进项建议。
同时需要确定性检查与定性LLM代码/内容审查。
需要通过命令行审查其他项目中的Skill。

Prerequisites

前置条件

Python 3.9+
```
uv
```
(recommended — auto-resolves
```
pyyaml
```
dependency via inline metadata)
For tests:
```
uv sync --extra dev
```
or equivalent in the target project
For LLM-axis merge: JSON file that follows the LLM review schema (see Resources)

Python 3.9+
```
uv
```
（推荐——通过内联元数据自动解析
```
pyyaml
```
依赖）
若需执行测试：在目标项目中运行
```
uv sync --extra dev
```
或等效命令
若需合并LLM轴结果：符合LLM审查 schema 的JSON文件（参见资源部分）

Workflow

工作流程

Determine the correct script path based on your context:

Same project:

skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

Global install:

~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

The examples below use

REVIEWER

as a placeholder. Set it once:

bash

undefined

根据使用场景确定正确的脚本路径：

同一项目内：

skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

全局安装后：

~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

以下示例使用

REVIEWER

作为占位符，只需设置一次：

bash

undefined

If reviewing from the same project:

若在同一项目内审查：

REVIEWER=skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

If reviewing another project (global install):

若使用全局安装审查其他项目：

REVIEWER=~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

undefined

REVIEWER=~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

undefined

Step 1: Run Auto Axis + Generate LLM Prompt

步骤1：运行自动轴检查并生成LLM提示词

bash

uv run "$REVIEWER" \
  --project-root . \
  --emit-llm-prompt \
  --output-dir reports/

When reviewing a different project, point

--project-root

to it:

bash

uv run "$REVIEWER" \
  --project-root /path/to/other/project \
  --emit-llm-prompt \
  --output-dir reports/

bash

uv run "$REVIEWER" \
  --project-root . \
  --emit-llm-prompt \
  --output-dir reports/

若审查其他项目，将

--project-root

指向目标项目路径：

bash

uv run "$REVIEWER" \
  --project-root /path/to/other/project \
  --emit-llm-prompt \
  --output-dir reports/

Step 2: Run LLM Review

步骤2：运行LLM审查

Use the generated prompt file in

reports/skill_review_prompt_<skill>_<timestamp>.md

Ask the LLM to return strict JSON output.
When running inside Claude Code, let Claude act as orchestrator: read the generated prompt, produce the LLM review JSON, and save it for the merge step.

使用

reports/skill_review_prompt_<skill>_<timestamp>.md

中的生成提示词文件。

要求LLM返回严格的JSON格式输出。
若在Claude Code中运行，可让Claude作为协调者：读取生成的提示词，生成LLM审查JSON并保存，用于后续合并步骤。

Step 3: Merge Auto + LLM Axes

步骤3：合并自动轴与LLM轴结果

bash

uv run "$REVIEWER" \
  --project-root . \
  --skill <skill-name> \
  --llm-review-json <path-to-llm-review.json> \
  --auto-weight 0.5 \
  --llm-weight 0.5 \
  --output-dir reports/

bash

uv run "$REVIEWER" \
  --project-root . \
  --skill <skill-name> \
  --llm-review-json <path-to-llm-review.json> \
  --auto-weight 0.5 \
  --llm-weight 0.5 \
  --output-dir reports/

Step 4: Optional Controls

步骤4：可选控制项

Fix selection for reproducibility:
```
--skill <name>
```
or
```
--seed <int>
```
Review all skills at once:
```
--all
```
Skip tests for quick triage:
```
--skip-tests
```
Change report location:
```
--output-dir <dir>
```
Increase
```
--auto-weight
```
for stricter deterministic gating.
Increase
```
--llm-weight
```
when qualitative/code-review depth is prioritized.

固定选择以保证可复现性：
```
--skill <name>
```
或
```
--seed <int>
```
一次性审查所有Skill：
```
--all
```
跳过测试以快速分类：
```
--skip-tests
```
修改报告存储位置：
```
--output-dir <dir>
```
提高
```
--auto-weight
```
以强化确定性管控。
当优先考虑定性/代码审查深度时，提高
```
--llm-weight
```
。

Output

输出结果

reports/skill_review_<skill>_<timestamp>.json

reports/skill_review_<skill>_<timestamp>.md

reports/skill_review_prompt_<skill>_<timestamp>.md

(when

--emit-llm-prompt

is enabled)

reports/skill_review_<skill>_<timestamp>.json

reports/skill_review_<skill>_<timestamp>.md

reports/skill_review_prompt_<skill>_<timestamp>.md

（当启用

--emit-llm-prompt

时生成）

Installation (Global)

全局安装

To use this skill from any project, symlink it into

~/.claude/skills/

bash

ln -sfn /path/to/claude-trading-skills/skills/dual-axis-skill-reviewer \
  ~/.claude/skills/dual-axis-skill-reviewer

After this, Claude Code will discover the skill in all projects, and the script is accessible at

~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

若要在任意项目中使用该Skill，将其符号链接至

~/.claude/skills/

：

bash

ln -sfn /path/to/claude-trading-skills/skills/dual-axis-skill-reviewer \
  ~/.claude/skills/dual-axis-skill-reviewer

完成后，Claude Code将在所有项目中识别该Skill，脚本路径为

~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

。

Resources

资源

Auto axis scores metadata, workflow coverage, execution safety, artifact presence, and test health.
Auto axis detects
```
knowledge_only
```
skills and adjusts script/test expectations to avoid unfair penalties.
LLM axis scores deep content quality (correctness, risk, missing logic, maintainability).
Final score is weighted average.
If final score is below 90, improvement items are required and listed in the markdown report.

Script:

skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

LLM schema:

skills/dual-axis-skill-reviewer/references/llm_review_schema.md

Rubric detail:

skills/dual-axis-skill-reviewer/references/scoring_rubric.md

自动轴评分包含元数据、工作流程覆盖度、执行安全性、工件存在性与测试健康状态。
自动轴可检测
```
knowledge_only
```
类型Skill，并调整脚本/测试预期以避免不公平扣分。
LLM轴评分针对内容深度质量（正确性、风险、缺失逻辑、可维护性）。
最终评分为加权平均值。
若最终评分低于90分，markdown报告中会列出必填的改进项。

脚本路径：

skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py

LLM schema：

skills/dual-axis-skill-reviewer/references/llm_review_schema.md

评分细则：

skills/dual-axis-skill-reviewer/references/scoring_rubric.md