Review changes
Skill cristianorj22/arthus-harness/plugins/mcp-code-review-graph/claude/skills/review-changes
Perform a structured code review using change detection and impact analysis from the code-review-graph MCP. Use when reviewing a PR or local diff that touches multiple files and you need to understand blast radius before judging risk.From its SKILL.md
npx -y skills add cristianorj22/arthus-harness --skill review-changesAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, 268 tokens by cl100k_base, as published. Nobody here has run it
Review Changes
Perform a thorough, risk-aware code review using the knowledge graph.
Steps
- Run
detect_changesto get risk-scored change analysis. - Run
get_affected_flowsto find impacted execution paths. - For each high-risk function, run
query_graphwithpattern="tests_for"to check test coverage. - Run
get_impact_radiusto understand the blast radius. - 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.
Cross-link
- Pairs with
code-revieweragent — reviewer reads code-level patterns; this skill provides structural impact data. - For tiny diffs (< 5 files), prefer the
code-revieweragent without invoking the graph.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.