review-edge-case-hunter

Walks every branching path in code, diffs, or specs and reports unhandled edge cases as JSON.

Updated Sep 6, 2026
One-click install
npx skills add https://github.com/JHAMILCALI/Stellar-Build --skill review-edge-case-hunter-jhamilcali
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review-edge-case-hunter
Source: https://github.com/JHAMILCALI/Stellar-Build/tree/main/.claude/skills/review-edge-case-hunter
Command: npx skills add https://github.com/JHAMILCALI/Stellar-Build --skill review-edge-case-hunter-jhamilcali

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often miss boundary conditions and unguarded branches because reviewers rely on intuition rather than systematic path enumeration. This Skill mechanically walks every control-flow branch and domain boundary in a diff, file, or function and reports only the paths that lack explicit handling. ## Core Features & Use Cases - Exhaustive Path Enumeration: Walks conditionals, loops, error handlers, early returns, and domain boundaries such as off-by-one loops, arithmetic overflow, implicit type coercion, race conditions, and timeout gaps. - Diff-Aware Scoping: When a diff is provided, analysis is restricted to boundaries directly reachable from changed lines; full files or functions are treated as the entire scope. - Structured JSON Output: Returns findings as a strict JSON array with location, trigger condition, guard snippet, and potential consequence, silently discarding handled paths. - Use Case: Before merging a pull request that adds input parsing logic, run this review on the diff to surface unguarded null inputs, missing else branches, and overflow risks with minimal fix sketches for each. ## Quick Start Review this diff for unhandled edge cases and list every branching path that lacks an explicit guard.

Frequently Asked Questions about review-edge-case-hunter

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

FAQPage Schema
How do I find unhandled edge cases in a code diff?▼

Provide the diff as the content input and the review scans only the changed hunks, listing boundaries directly reachable from the changed lines that lack an explicit guard. Findings are returned as a JSON array with location, trigger condition, guard snippet, and potential consequence.

What kinds of edge cases does an exhaustive path review catch?▼

It derives edge classes from the content itself rather than a fixed checklist. Typical findings include missing else or default branches, unguarded null or empty inputs, off-by-one loops, arithmetic overflow, implicit type coercion, race conditions, and timeout gaps.

Can I review a full file or function instead of a diff?▼

Yes. When no diff is provided, the entire supplied file or function becomes the analysis scope. The rest of the codebase is ignored unless the provided content explicitly references external functions.

What output format does the edge case review produce?▼

It returns only a valid JSON array where each object has exactly four fields: location, trigger_condition, guard_snippet, and potential_consequence. An empty array is returned when no unhandled paths are found, with no extra text or markdown wrapping.

When should I not use method-driven edge case review?▼

It is not suited for judging code quality, style, or design, since it never comments on whether code is good or bad. For security-focused or attitude-driven critique, use an adversarial review approach instead, which is orthogonal to this method.