competitive-teardown Eval
=========================

Status: review
Score: 81/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add nexu-io/html-anything --skill competitive-teardown

Required checks:
- WARN Task fit: Task fit is weak; compare alternatives before selecting.
- 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: 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:
- Task fit: Task fit is weak; compare alternatives before selecting.
- Trust score: Good trust signals with a few areas worth checking before rollout.
- 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
- Financial research output is not financial advice; require human review before any live investment decision
- The SKILL.md references three asset templates (war-room-grid.html, radar-map.html, analyst-dossier.html) but the submitted excerpt does not include these files. If they are missing from the repository, the skill's design guidance cannot be fully applied.
- The skill does not explicitly define how to handle user input that is not in the expected format (e.g., unstructured notes). It assumes the user provides competitive data, but does not specify a fallback or parsing strategy.
- Financial research output is not financial advice; require human review before any live investment decision.

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.md references three asset templates (war-room-grid.html, radar-map.html, analyst-dossier.html) but the submitted excerpt does not include these files. If they are missing from the repository, the skill's design guidance cannot be fully applied.
- Financial research output is not financial advice; require human review before any live investment decision
- The skill does not explicitly define how to handle user input that is not in the expected format (e.g., unstructured notes). It assumes the user provides competitive data, but does not specify a fallback or parsing strategy.
- Financial research output is not financial advice; require human review before any live investment decision.
- Production credentials, payments, or irreversible account changes without explicit human review
- Sensitive private data before reviewing repository code, license, and permission surface

URLs:
- Skill: https://www.openagentskill.com/skills/nexu-io-competitive-teardown
- Audit: https://www.openagentskill.com/skills/nexu-io-competitive-teardown/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=nexu-io-competitive-teardown