oma-debug Eval
==============

Status: review
Score: 74/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add first-fluke/oh-my-agent --skill oma-debug

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Good trust signals with a few areas worth checking before rollout.
- WARN Audit score: Needs review
- WARN Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- PASS License clarity: MIT
- WARN Permission surface: shell or command execution, filesystem or document access

Warnings:
- Trust score: Good trust signals with a few areas worth checking before rollout.
- Audit score: Needs review
- Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- Permission surface: shell or command execution, filesystem or document access
- High-risk permission hints: Shell or command execution
- SKILL.md references resources/execution-protocol.md and examples, but those files are not present in the submitted skill directory. Either include them or remove the references.
- The skill lacks a concrete end-to-end example showing the full debug workflow from symptom to root cause to regression test.
- The bundled resources are heavily frontend/React-focused. Since the skill claims general bug debugging, backend, API, database, and concurrency bug patterns should be added or clearly scoped.
- The skill does not explicitly define safe execution boundaries beyond general guardrails, such as only running project-sanctioned test/lint/typecheck commands and avoiding secret access or deployment actions.
- Quality score needs review

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- SKILL.md references resources/execution-protocol.md and examples, but those files are not present in the submitted skill directory. Either include them or remove the references.
- High-risk permission hints: Shell or command execution
- The skill lacks a concrete end-to-end example showing the full debug workflow from symptom to root cause to regression test.
- The bundled resources are heavily frontend/React-focused. Since the skill claims general bug debugging, backend, API, database, and concurrency bug patterns should be added or clearly scoped.
- The skill does not explicitly define safe execution boundaries beyond general guardrails, such as only running project-sanctioned test/lint/typecheck commands and avoiding secret access or deployment actions.
- Quality score needs review

URLs:
- Skill: https://www.openagentskill.com/skills/first-fluke-oma-debug
- Audit: https://www.openagentskill.com/skills/first-fluke-oma-debug/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=first-fluke-oma-debug