Review Changes
- 779 installs
- 28.5k repo stars
- Updated August 2, 2026
- tirth8205/code-review-graph
review changes is a Claude Code skill that performs structured, risk-aware code reviews using a knowledge graph for developers who need impact radius analysis and test coverage checks before merging.
About
review changes is a Claude Code skill from tirth8205/code-review-graph that performs structured, risk-aware code reviews using a repository knowledge graph. The workflow runs detect_changes_tool for risk-scored diffs, get_affected_flows_tool for impacted execution paths, query_graph_tool with pattern tests_for to verify test coverage on high-risk functions, and get_impact_radius_tool for blast-radius analysis. Output groups findings by high, medium, and low risk with change rationale, coverage gaps, and suggested test cases for untested edits. Developers reach for review changes before merging PRs when they need graph-backed impact analysis beyond line-by-line diff comments.
- 5-step structured review workflow using knowledge graph tools
- Always begins with get_minimal_context for token efficiency
- Groups findings by risk level: high/medium/low
- Combines change detection, affected flows, impact radius, and test coverage analysis
- Delivers overall merge recommendation with specific test suggestions
Review Changes by the numbers
- 779 all-time installs (skills.sh)
- Ranked #182 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/tirth8205/code-review-graph --skill review-changesAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 779 |
|---|---|
| repo stars | ★ 28.5k |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 2, 2026 |
| Repository | tirth8205/code-review-graph ↗ |
How do you review code changes with impact analysis?
Perform structured, risk-aware code reviews that detect impact radius, test coverage gaps, and suggest fixes before merging.
Who is it for?
Developers reviewing PRs in graph-indexed repos who need risk-scored impact analysis and test gap detection.
Skip if: Repositories without the code-review-graph tooling or teams wanting quick stylistic lint feedback only.
When should I use this skill?
User requests a structured code review, merge readiness check, or impact analysis on recent changes.
What you get
Risk-grouped review report with affected flows, blast radius, coverage gaps, and suggested test cases.
- Risk-grouped code review report
- Suggested test cases for coverage gaps
Files
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.
Related skills
Improve Codebase ArchitectureSafely deepen clusters of shallow modules into cohesive, testable units while respecting their external dependencies.566k196k
Caveman ReviewGet ultra-compressed, one-line code review comments that cut noise while keeping every actionable fix.270k94.7kCodebase DesignShared vocabulary for designing deep modules: improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable.266k196kCavecrewDelegate coding tasks to specialized subagents that return compressed output, keeping the main context window usable for much longer sessions.220k94.7kCode ReviewReviews a branch or PR diff on two axes at once: conformance to coding standards plus a code-smell baseline, and whether it actually implements the original spec.201k196k
Requesting Code ReviewDispatch a consistent, high-signal code reviewer subagent that catches plan deviations and quality issues before merging or continuing development.183k264kFAQ
What tools does review changes call?
review changes invokes detect_changes_tool, get_affected_flows_tool, query_graph_tool with pattern tests_for, and get_impact_radius_tool. These graph tools produce risk-scored findings, affected flows, and coverage gaps grouped by severity.
What output format does review changes produce?
review changes delivers findings grouped by high, medium, and low risk. Each item explains what changed, why it matters, test coverage status, and suggested test cases for untested high-risk functions.
Is Review Changes safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.