Description
ai-debt-detector is an agent skill from the wshobson/agents collection that audits code an AI has just written. It is built on the observation that AI-generated code often passes the happy path while hiding debt: missing error handling, orphaned resources, ignored failure modes, hallucinated packages and silent architectural drift. Rather than reviewing everything at once, the skill runs a targeted audit for those exact patterns after a code generation session. The skill says when to use it: after an AI session that produced 20 or more lines, before merging AI-generated pull requests, when code works but something feels off, after vibe-coding sprints, and when an agent claims a task is done without showing verification. Its process scans the new code for the AI-specific debt patterns and reports what it finds so a person can fix it before the code ships. It is installed with the skills CLI from the wshobson/agents repository, and its skills.sh page showed about 2.7K installs and passing results from three security audits at the time of the scan.…
Highlights
- Targeted audit of AI-generated code
- Checks for missing error handling and orphaned resources
- Flags hallucinated packages and silent architectural drift
- Run after sessions that produce 20+ lines
- Useful before merging AI-written pull requests
- Installs with the skills CLI
Ratings & Reviews
No ratings yet
Be the first to rate ai-debt-detector.
People also visit
code-review-excellence
Systematic code review practices for constructive feedback, bug detection
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions
code-reviewer
Analyzes code diffs and files to identify bugs, security vulnerabilities
ai-debt-detector FAQ
What does this skill check for?
Missing error handling, orphaned resources, ignored failure modes, hallucinated packages and silent architectural drift in code an AI generated.
When should I run it?
After an AI code generation session that produced 20 or more lines, before merging AI-written pull requests, or when code works but feels brittle.
Does it replace a normal code review?
No. The skill is a targeted audit for the patterns AI agents tend to get wrong. It is meant to sit alongside review, not replace it.
How do I install it?
Run npx skills add https://github.com/wshobson/agents --skill ai-debt-detector.
What security audits does it have?
skills.sh lists three audits: Gen Agent Trust Hub Pass, Socket Pass and Snyk Pass.
What are the best ai-debt-detector alternatives?
Popular alternatives to ai-debt-detector include code-review-excellence, multi-reviewer-patterns and code-reviewer. See all ai-debt-detector alternatives