Review Changes

tirth8205/code-review-graph/skills/review-changes

by tirth82056b12d11625cbec3b6773e076cb3d136464fa90e5No licenseListed Oct 9, 2026Updated Oct 9, 2026

Perform a structured code review using change detection and impact

Instructions onlySoftware Development
AI-generated overview

Performs a structured code review of a change set using knowledge-graph tools to score risk and find test gaps.

What it does
Guides an agent through a structured code review of a change set. It calls knowledge-graph tools to detect risk-scored changed functions, test gaps and affected flows, and to check test coverage and blast radius. Findings are grouped by high, medium and low risk, each with what changed, why it matters, test coverage and a suggested fix, ending with a merge recommendation.
When to use it
Use when reviewing a set of code changes before merge and you want risk-ranked findings and coverage gaps. It suits reviews where a knowledge graph of the codebase is available to narrow scope.
Requirements
Requires access to the referenced knowledge-graph tools (detect_changes_tool, get_affected_flows_tool, query_graph_tool, get_impact_radius_tool, get_minimal_context_tool). Instructions only; ships no scripts.

Review Changes

Review a change set with risk scores and blast radius from the knowledge graph.

Steps

  1. Call detect_changes_tool for risk-scored changed functions, test gaps and affected flows.
  2. Call get_affected_flows_tool only when you need the steps of an affected flow.
  3. For each high-risk function, call query_graph_tool with pattern="tests_for" to check test coverage.
  4. Call get_impact_radius_tool when the blast radius is not clear from step 1.
  5. Suggest specific test cases for untested changes.

Output Format

Group findings by risk level (high, medium, low). For each finding give what changed and why it matters, its test coverage, and the suggested fix. End with a merge recommendation.

Token Efficiency Rules

  • Call get_minimal_context_tool(task="<your task>") before any other graph tool.
  • Pass detail_level="minimal" wherever a tool accepts it. Use "standard" only when minimal is not enough.
  • Prefer a targeted query_graph_tool call over a broad listing call.
  • Budget: about five tool calls and 800 tokens of graph output per task.
  • Read the implementation and its tests before changing code. The graph narrows scope; it does not replace the source.

Source and attribution

Source:tirth8205/code-review-graphinskills/review-changesat commit6b12d11

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal