AB prompt-benchmark
Evaluate one or more prompts with an evidence-based static benchmark covering general quality, structure and format, few-shot examples, safety and robustness, target-model compatibility, and cross-model portability. Use when Codex needs to score, audit, lint, compare, or diagnose prompts; assess whether a prompt is production-ready; check examples or output schemas; identify model-specific assumptions; or recommend high-priority improvements without actually running the prompt against external models.
Evaluate one or more prompts with an evidence-based static benchmark covering general quality, structure and format, few-shot examples, safety and robustness…
As a process B 70/100 · Nearly there — weak spots: result and completion, when it triggers, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityreferences/scoring-rubric.md:104Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Authority boundaries:** the prompt does not request privilege escalation or secret disclosure.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 70/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 40 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1434 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 506: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.