bmad-review-edge-case-hunter

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

Updated Mar 20, 2026
One-click install
npx skills add https://github.com/LinCie/bearuang --skill bmad-review-edge-case-hunter-lincie
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-review-edge-case-hunter
Source: https://github.com/LinCie/bearuang/tree/main/.opencode/skills/bmad-review-edge-case-hunter
Command: npx skills add https://github.com/LinCie/bearuang --skill bmad-review-edge-case-hunter-lincie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often miss boundary conditions and unhandled branches, letting subtle bugs like off-by-one errors, null inputs, and race conditions slip into production. This Skill mechanically enumerates every path in a diff, file, or function and reports only the gaps that lack guards. ## Core Features & Use Cases - Exhaustive Path Enumeration: Walks all control flow branches and domain boundaries, deriving edge classes from the content itself rather than a fixed checklist. - Diff-Aware Scoping: When given a diff, analyzes only changed hunks and boundaries directly reachable from changed lines. - Structured JSON Output: Returns findings as a strict JSON array with location, trigger condition, guard snippet, and potential consequence. - Use Case: Paste a pull request diff before merging and receive a list of unhandled edge cases such as missing else branches or unguarded null inputs, each with a minimal fix sketch. ## Quick Start Ask the AI to run an edge case review on your diff or function and list only the unhandled boundary conditions.

Frequently Asked Questions about bmad-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 input and the review walks every branching path reachable from the changed lines. It reports only boundaries lacking an explicit guard, returning each finding with a location, trigger condition, and minimal fix snippet.

How to review a function for missing boundary condition handling?▼

Pass the full function or file as the content input with no diff. The entire provided content becomes the analysis scope, and every conditional, loop, and domain boundary is checked for missing handling.

What output format does the edge case review return?▼

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.

Does edge case analysis work on code outside the provided content?▼

No, the review ignores the rest of the codebase unless the provided content explicitly references external functions. Scope is limited to the diff hunks, file, or function you supply.

What happens when the review input is empty or invalid?▼

A halt condition triggers and the review returns a single JSON object indicating the input was empty or undecodable, with a note that no analysis was performed. It then stops without further processing.