Methodology for categorizing changes, assessing risks, and creating summaries from any changeset. Triggers: diff analysis, changeset review, risk assessment, change categorization, semantic analysis, release preparation, change summary, git diff Use when: analyzing specific changesets, assessing risk of changes, preparing release notes, categorizing changes by type and impact DO NOT use when: quick context catchup - use catchup instead. DO NOT use when: full PR review - use review-core with pensive skills. Use this skill for systematic change analysis with risk scoring.
Install with Tessl CLI
npx tessl i github:majiayu000/claude-skill-registry-data --skill diff-analysis93
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 98%
↑ 1.05xAgent success when using this skill
Validation for skill structure
4-step methodology and structured summary
Summary theme
100%
100%
Scope with counts
40%
100%
Risk level present
100%
100%
Review focus
100%
100%
Dependencies noted
100%
100%
Semantic type grouping
100%
100%
Baseline established
100%
100%
Risk indicators identified
100%
100%
Risk assessment step
100%
100%
Downstream format
100%
100%
Without context: $0.2246 · 1m 7s · 12 turns · 19 in / 3,250 out tokens
With context: $0.4862 · 1m 57s · 24 turns · 153 in / 6,800 out tokens
Semantic change categorization and risk scoring
Semantic categories used
100%
100%
Risk indicators identified
100%
100%
Risk level assigned
100%
100%
Scope with counts
100%
100%
Review focus specified
100%
100%
Dependencies section
60%
100%
Baseline defined
100%
100%
Theme stated
50%
70%
Risk reasoning present
100%
100%
Downstream format
100%
100%
Without context: $0.1794 · 1m 11s · 8 turns · 13 in / 3,862 out tokens
With context: $0.5940 · 2m 28s · 29 turns · 33 in / 8,462 out tokens
Baseline establishment and risk level assessment
Comparison states named
100%
100%
Analysis boundary defined
80%
80%
Scale metrics included
100%
100%
Semantic type grouping
100%
100%
Risk level assigned
100%
100%
Risk scoring reasoning
80%
100%
Summary theme
100%
100%
Review focus named
100%
100%
Dependencies noted
100%
100%
Downstream format
100%
100%
Without context: $0.2060 · 1m 20s · 8 turns · 13 in / 4,226 out tokens
With context: $0.4809 · 2m · 21 turns · 26 in / 6,593 out tokens
Table of Contents
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.