architecture-designer Eval
==========================

Status: review
Score: 76/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add Jeffallan/claude-skills --skill architecture-designer

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: filesystem or document access, network or browser 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: filesystem or document access, network or browser access
- High-risk permission hints: Secrets or environment access
- Permission surface may require sandboxing
- No explicit 'Limitations' or 'When not to use' section in SKILL.md; the frontmatter mentions it is distinct from code-level design patterns and database-only tasks, but the body does not elaborate on boundaries.
- No setup/installation notes, although this is acceptable for a pure prompt/reference skill with no executable components.
- Quality score needs review
- Permission surface needs review: filesystem or document access, network or browser access

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
- No explicit 'Limitations' or 'When not to use' section in SKILL.md; the frontmatter mentions it is distinct from code-level design patterns and database-only tasks, but the body does not elaborate on boundaries.
- High-risk permission hints: Secrets or environment access
- Permission surface may require sandboxing
- No setup/installation notes, although this is acceptable for a pure prompt/reference skill with no executable components.
- Quality score needs review
- Permission surface needs review: filesystem or document access, network or browser access

URLs:
- Skill: https://www.openagentskill.com/skills/jeffallan-architecture-designer
- Audit: https://www.openagentskill.com/skills/jeffallan-architecture-designer/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=jeffallan-architecture-designer