Diff Analysis Skill for Claude
Analyzes changesets with risk scoring, categorization by type and impact, and release note preparation. Use when extracting insights from raw change data.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/athola/claude-night-market --skill diff-analysisThe instruction itself
17 sections, as written by the authorTable of Contents
- Overview
- When to Use
- Activation Patterns
- 4-Step Methodology
- Exit Criteria
Diff Analysis Methodology
Overview
Structured method for analyzing changesets: categorize changes, assess risks, generate insights. Works for git diffs, configuration changes, API migrations, schema updates, or document revisions.
When To Use
- Extracting insights from raw change data
- Categorizing and prioritizing changes before code reviews
- Preparing release notes or changelogs
- Assessing migration scope and risk
When NOT To Use
- Quick context catchup - use catchup instead
- Full PR review - use review-core with pensive skills
Activation Patterns
Trigger Keywords: diff, changes, release notes, changelog, migration, impact, risk assessment
Auto-Load When: Git diffs present, change analysis requested, impact assessment needed.
Progressive Loading
Load modules based on workflow stage:
Always Load
modules/semantic-categorization.mdfor change categorization workflow
Conditional Loading
modules/risk-assessment-framework.mdwhen risk assessment is neededmodules/git-diff-patterns.mdwhen working with git repositories
Integration
- Use
sanctum:git-workspace-reviewfor git data gathering - Use
imbue:proof-of-workfor capturing analysis evidence - Use
imbue:structured-outputfor formatting final deliverables
Required TodoWrite Items
diff-analysis:baseline-establisheddiff-analysis:changes-categorizeddiff-analysis:risks-assesseddiff-analysis:summary-prepared
Mark each item complete as you finish the corresponding step.
4-Step Methodology
Step 1: Establish Baseline (diff-analysis:baseline-established)
Define comparison scope: what states are being compared, boundary of analysis, and scale metrics.
For git contexts, load modules/git-diff-patterns.md. For other contexts, compare relevant artifacts.
Step 2: Categorize Changes (diff-analysis:changes-categorized)
Group changes by semantic type. Load modules/semantic-categorization.md for change categories, semantic categories, and prioritization.
Step 3: Assess Risks (diff-analysis:risks-assessed)
Evaluate impact. Load modules/risk-assessment-framework.md for risk indicators, levels, and scoring methodology.
Step 4: Prepare Summary (diff-analysis:summary-prepared)
Synthesize findings: theme, scope with counts, risk level, review focus, dependencies. Format for downstream consumption (PR descriptions, release notes, reviews).
Exit Criteria
- All TodoWrite items completed with categorized changes and risk assessment
- Downstream workflows have semantic understanding of the changeset
- Summary ready for appropriate consumption (review, release notes, planning)
Other skills for the same job
different authors, same section of the catalogue
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
How to use it
Take athola/diff-analysis from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.