evo-stl-mass Eval
=================

Status: review
Score: 70/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add Zhang-Henry/CoEvoSkills --skill evo-stl-mass

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: Usable candidate, but the agent should surface permission and audit notes before installation.
- PASS License clarity: Apache-2.0
- PASS Permission surface: no high-risk permission surface in public metadata

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- The skill assumes STL coordinates are in millimeters without a configurable unit option, which could lead to incorrect mass calculations if the STL uses other units.
- The density table parser is brittle: it relies on a specific markdown table format with '**' markers and may fail on variations.
- The tolerance calculation for vertex matching is heuristic and may not be robust for all STL files, potentially causing incorrect component detection.
- Quality score needs review
- GitHub adoption: 65 GitHub stars
- Stars/forks activity: 65 stars, 5 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
- The skill assumes STL coordinates are in millimeters without a configurable unit option, which could lead to incorrect mass calculations if the STL uses other units.
- No OpenAgentSkill engagement data yet
- The density table parser is brittle: it relies on a specific markdown table format with '**' markers and may fail on variations.
- The tolerance calculation for vertex matching is heuristic and may not be robust for all STL files, potentially causing incorrect component detection.
- Quality score needs review
- GitHub adoption: 65 GitHub stars

URLs:
- Skill: https://www.openagentskill.com/skills/zhang-henry-evo-stl-mass
- Audit: https://www.openagentskill.com/skills/zhang-henry-evo-stl-mass/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=zhang-henry-evo-stl-mass