skills.rest
arnonmoscona
arnonmosconaCOMMUNITY
Explore all skills by this author →
GitHub

Review Changes

Reviews code changes using risk-scored change detection and knowledge graph impact analysis.

Updated May 3, 2017
Search Tags:#code review#knowledge graph#impact analysis#test coverage#risk assessment#change detection#merge recommendation
One-click install
npx skills add https://github.com/arnonmoscona/dot_files --skill review-changes-arnonmoscona
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Review Changes
Source: https://github.com/arnonmoscona/dot_files/tree/main/claude/projects/toolguard/.claude/skills/review-changes
Command: npx skills add https://github.com/arnonmoscona/dot_files --skill review-changes-arnonmoscona

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often miss hidden ripple effects of a change, such as impacted execution flows and untested functions. This Skill performs a structured, risk-aware review by querying a knowledge graph to detect changes, trace affected flows, and check test coverage before merge. ## Core Features & Use Cases - Risk-Scored Change Detection: Runs detect_changes to identify what changed and rank findings by risk level. - Impact Analysis: Uses get_affected_flows and get_impact_radius to map the blast radius of each change across execution paths. - Test Coverage Checks: Queries the graph for tests covering high-risk functions and suggests specific test cases for untested changes. - Use Case: Before merging a pull request that modifies a core authentication function, run this review to see which flows are impacted, whether tests exist for the changed code, and receive a merge recommendation grouped by risk level. ## Quick Start Review my current code changes and tell me the risk level, impacted flows, test coverage gaps, and whether it is safe to merge.

Frequently Asked Questions about Review Changes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review code changes for hidden impact before merging?▼

Run detect_changes to get a risk-scored list of modifications, then use get_affected_flows and get_impact_radius to trace which execution paths and functions are impacted. The review output groups findings by risk level with a merge recommendation.

How to check test coverage for changed functions in a code review?▼

For each high-risk function identified in the change analysis, run query_graph with pattern="tests_for" to find existing tests. If coverage is missing, the review suggests specific test cases for the untested changes.

What is a knowledge graph based code review?▼

It is a review approach that queries a graph representation of the codebase to detect changes, map impacted execution flows, and measure blast radius. This goes beyond line-by-line diff reading by surfacing downstream effects of each modification.

How many tool calls does a graph-based review require?▼

The workflow targets completing any review in five or fewer tool calls and under 800 output tokens. It starts with get_minimal_context and uses detail_level="minimal", escalating to "standard" only when minimal detail is insufficient.

When should I escalate from minimal to standard detail level?▼

Escalate to detail_level="standard" only when the minimal output lacks enough information to assess a change's risk or impact. Always begin with get_minimal_context and minimal detail to keep token usage low.

Related Skills

Explore More Software Engineering Skills→
bmiit145bmiit145

review-changes

Reviews code changes using risk-scored change detection and knowledge graph impact analysis.

Community
Intermediate
aget-frameworkaget-framework
11

aget-review-pr

Review pull requests for code quality, test coverage, and standards compliance.

Official
Intermediate
Intense-VisionsIntense-Visions
18

harness-test-advisor

Identify minimal test sets from changed files with graph-aware discovery and static fallbacks.

Official
Advanced
89jobrien89jobrien
1

using-gkg

Index repositories into a queryable knowledge graph using gkg.

Community
Intermediate