---
name: Review Changes
slug: review-changes
category: Quality
description: Review Changes performs a structured, risk-aware code review using change detection and impact analysis from a knowledge graph. It identifies risk levels, affected execution paths, test coverage gaps, and provides a merge recommendation.
github: "https://github.com/tirth8205/code-review-graph/tree/main/skills/review-changes"
language: Python
stars: 30048
forks: 2760
install: "npx degit https://github.com/tirth8205/code-review-graph/tree/main/skills/review-changes ~/.claude/skills/review-changes"
installs_to: ~/.claude/skills/review-changes
source_path: skills/review-changes/SKILL.md
collection_size: 7
category_size: 1354
collection_url: "https://dirskills.com/collections/tirth8205/code-review-graph"
added: 2026-08-14T07:11:48.324Z
last_synced: 2026-08-14T07:11:48.324Z
canonical_url: "https://dirskills.com/skills/review-changes"
---

# Review Changes

Review Changes performs a structured, risk-aware code review using change detection and impact analysis from a knowledge graph. It identifies risk levels, affected execution paths, test coverage gaps, and provides a merge recommendation.

**Install:**

```bash
npx degit https://github.com/tirth8205/code-review-graph/tree/main/skills/review-changes ~/.claude/skills/review-changes
```

## README

## Review Changes

Perform a thorough, risk-aware code review using the knowledge graph.

### Steps

1. Run `detect_changes_tool` to get risk-scored change analysis.
2. Run `get_affected_flows_tool` to find impacted execution paths.
3. For each high-risk function, run `query_graph_tool` with pattern="tests_for" to check test coverage.
4. Run `get_impact_radius_tool` to understand the blast radius.
5. For any untested changes, suggest specific test cases.

### Output Format

Provide findings grouped by risk level (high/medium/low) with:
- What changed and why it matters
- Test coverage status
- Suggested improvements
- Overall merge recommendation

## Token Efficiency Rules
- ALWAYS start with `get_minimal_context(task="<your task>")` before any other graph tool.
- Use `detail_level="minimal"` on all calls. Only escalate to "standard" when minimal is insufficient.
- Target: complete any review/debug/refactor task in ≤5 tool calls and ≤800 total output tokens.