CtrlK
BlogDocsLog inGet started
Tessl Logo

git-forensics

分析 Git 历史,发现"逻辑耦合"(总一起改的文件)和"热点"(高频修改的复杂模块)。基于 Adam Tornhill 的《Your Code as a Crime Scene》方法论。

70

1.45x
Quality

56%

Does it follow best practices?

Impact

90%

1.45x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.trae/skills/git-forensics/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

84%

35%

Finding Hidden Dependencies in an Open Source Service

Temporal coupling analysis

Criteria
Without context
With context

Script output format

0%

30%

Noise files excluded

100%

100%

HIGH_COUPLING label

0%

100%

MEDIUM_COUPLING label

0%

100%

File type classification

20%

70%

Build root annotation

100%

100%

History completeness check

0%

100%

Initial activity survey

100%

100%

Actionable recommendations

100%

100%

Architectural decay identification

50%

40%

100%

40%

Technical Debt Prioritization for an Engineering Refactoring Sprint

Hotspot detection and debt scoring

Criteria
Without context
With context

Hotspot script output fields

100%

100%

debt_score field present

90%

100%

debt_score = churn × max_ccn

0%

100%

max_ccn used

0%

100%

nloc field present

0%

100%

Sorted by debt_score descending

100%

100%

High churn + high complexity = top priority

86%

100%

High churn + low complexity = deprioritize

91%

100%

Analysis period defined

40%

100%

Concrete file example

100%

100%

88%

9%

Pre-Decomposition Architectural Risk Assessment

Full forensic report with cross-root coupling

Criteria
Without context
With context

Both analyses present

100%

100%

Cross-subsystem section

100%

100%

Cross-subsystem pairs flagged

100%

100%

Build root annotation

100%

100%

Orphan files listed

100%

100%

One-year orphan threshold

0%

100%

Refactoring priority section

100%

100%

Priority matrix applied

60%

100%

Coupling threshold 0.7

37%

37%

Actionable recommendations

100%

100%

Rename distortion awareness

0%

0%

Repository
Lingjie-chen/MT5
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.