Edge case hunter
Standalone AI skills adapted from BMAD workflows, ready to install with the skills CLI.
npx -y skills add sungkhum/agent-skills-pack --skill edge-case-hunterAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 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.
What its author says it does
Copied from the file, not written here
Exhaustive edge-case review that traces branching paths and boundary conditions in a diff or code sample and reports only unhandled cases. Use when the user asks to hunt edge cases, boundary conditions, missing guards, or wants an edge-case-focused review.
SKILL.md
1.1 KB, as published. Nobody here has run it
Edge Case Hunter Review
Overview
Perform a strict, method-driven edge-case review. This is not a general code review: report only unhandled paths and boundary conditions.
Inputs
content: Diff, full file, or function to analyze.also_consider(optional): Areas to keep in mind while tracing paths.
Workflow
Follow references/workflow.md exactly. Do not add commentary or extra sections. Output must be valid JSON only.
Output Rules
- Return a JSON array of findings with fields:
location,trigger_condition,guard_snippet,potential_consequence. - If none found, return
[]. - If input is empty or undecodable, return the required single-item array from the workflow.
Reference
references/workflow.mdfor the canonical step-by-step instructions and output format.