co2-carbon-footprint Eval
=========================

Status: review
Score: 73/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill co2-carbon-footprint

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: 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: 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
- SKILL.md is incomplete; the provided content cuts off mid-code, lacking the full implementation, usage examples, and API documentation.
- instructions.md is generic and not tailored to this specific skill, missing concrete steps for invoking the carbon calculation workflow.
- No explicit input data schema or expected formats are documented, limiting reproducibility and agent guidance.
- Missing limitations and assumptions (e.g., default uncertainty, scope of EPDs, applicability to non-building structures).
- 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 is incomplete; the provided content cuts off mid-code, lacking the full implementation, usage examples, and API documentation.
- No OpenAgentSkill engagement data yet
- instructions.md is generic and not tailored to this specific skill, missing concrete steps for invoking the carbon calculation workflow.
- No explicit input data schema or expected formats are documented, limiting reproducibility and agent guidance.
- Missing limitations and assumptions (e.g., default uncertainty, scope of EPDs, applicability to non-building structures).
- Quality score needs review

URLs:
- Skill: https://www.openagentskill.com/skills/datadrivenconstruction-co2-carbon-footprint
- Audit: https://www.openagentskill.com/skills/datadrivenconstruction-co2-carbon-footprint/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=datadrivenconstruction-co2-carbon-footprint