ai-research-explore Eval
========================

Status: failed
Score: 70/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Install path: No install command or repository handoff is available.

Install:


Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- FAIL Install path: No install command or repository handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Potentially useful, but at least one trust signal needs human inspection.
- 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
- FAIL Permission surface: shell or command execution, filesystem or document access

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- High-risk permission hints: Shell or command execution
- Permission surface may require sandboxing
- The tracked source changed or could not be synchronized. Review the current source before installing.
- SKILL.md references shared references under ../ai-research-reproduction/ which are not included in this submitted skill directory; if those files are not bundled or guaranteed present, the skill may not be fully operational.
- The skill delegates to other skills such as explore-code, explore-run, run-train, and analyze-project but does not clarify whether they are bundled, optional, or must be installed separately.
- No explicit setup or environment requirements are documented, such as where the isolated worktree should be created or what permissions are needed for executing runs and network lookups.
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- Stars/forks activity: 484 stars, 16 forks; issue activity unavailable in current metadata

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 shared references under ../ai-research-reproduction/ which are not included in this submitted skill directory; if those files are not bundled or guaranteed present, the skill may not be fully operational.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution
- Permission surface may require sandboxing
- The tracked source changed or could not be synchronized. Review the current source before installing.
- The skill delegates to other skills such as explore-code, explore-run, run-train, and analyze-project but does not clarify whether they are bundled, optional, or must be installed separately.

URLs:
- Skill: https://www.openagentskill.com/skills/lllllllama-ai-research-explore
- Audit: https://www.openagentskill.com/skills/lllllllama-ai-research-explore/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=lllllllama-ai-research-explore