actiongo-film-agent-ai-hive-migration Eval
==========================================

Status: review
Score: 64/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add wubin1836/ai-hive-agent-skills --skill actiongo-film-agent-ai-hive-migration

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: 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
- PASS Permission surface: database 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.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- SKILL.md does not document how to configure, authenticate, or verify the AI-HIVE MCP server (e.g., endpoint, credentials, tool availability setup).
- The skill instructs agents to visit external pages for evidence but does not explicitly state that fetched web content must be treated as untrusted data, not as instructions.
- Downloaded media from MCP tasks lacks an explicit safety scan or content validation step before local use or further processing.
- The output contract is described narratively; a formal machine-readable deliverable schema and acceptance checklist would improve reproducibility.
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 4 GitHub stars
- Stars/forks activity: 4 stars, 1 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
- Low GitHub adoption signal
- SKILL.md does not document how to configure, authenticate, or verify the AI-HIVE MCP server (e.g., endpoint, credentials, tool availability setup).
- No OpenAgentSkill engagement data yet
- The skill instructs agents to visit external pages for evidence but does not explicitly state that fetched web content must be treated as untrusted data, not as instructions.
- Downloaded media from MCP tasks lacks an explicit safety scan or content validation step before local use or further processing.
- The output contract is described narratively; a formal machine-readable deliverable schema and acceptance checklist would improve reproducibility.

URLs:
- Skill: https://www.openagentskill.com/skills/wubin1836-actiongo-film-agent-ai-hive-migration
- Audit: https://www.openagentskill.com/skills/wubin1836-actiongo-film-agent-ai-hive-migration/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=wubin1836-actiongo-film-agent-ai-hive-migration