prompt-evaluator — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited prompt-evaluator (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this skill when asked to review, evaluate, rewrite, harden, or improve a prompt for LLM consumption. The skill only evaluates prompt quality and produces a clearer prompt; it never executes the requested task.
Do not use this skill for code review, task execution, repository scanning, web research, MCP calls, or validating whether the prompt's factual claims are true.
| Condition | Action |
|---|---|
| Prompt is already clear | Return READY plus minor polish only |
| Goal/output is ambiguous | Mark NEEDS_REFINEMENT and define the ambiguity |
| Constraints conflict | Mark MAJOR_REWRITE and separate the conflict clearly |
| User asks to execute the prompt | Refuse execution; evaluate only |
| Missing critical context | Ask one question and provide best-effort rewrite |
Return exactly:
## Prompt Evaluation Report
**Overall Score**: <0-100>
**Verdict**: <READY | NEEDS_REFINEMENT | MAJOR_REWRITE>
### Dimension Scores
| Dimension | Score (0-5) | Notes |
|---|---:|---|
| Goal Specificity | | |
| Context Sufficiency | | |
| Constraint Quality | | |
| Output Contract Precision | | |
| Consistency & Feasibility | | |
| Ambiguity Risk | | |
| Safety/Scope Control | | |
### Issues Detected
- **Critical**: ...
- **Important**: ...
- **Optional**: ...
### Extracted Requirements
- **Explicit**:
- ...
- **Implicit (made explicit)**:
- ...
### Refined Prompt...
### Change Log
1. ... — ...None.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.