AF benchmark-model-provider
Benchmark and rank AI providers/models against a user-specific prompt suite derived from the user's purpose, domain, and usage frequency. Use when users ask which model is smarter, cheaper, deeper, faster, worth using daily, better as local vs service, or when building repeatable benchmark specs, reranking old runs, generating markdown/HTML/PDF benchmark reports.
As a process F 50/100 · Will not run — References files that are not bundled: examples/*.yaml
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- The text references files that are not there: add them or drop the references.
- 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
-
medium Exfiltration
net-redirectable-api-keyscripts/run_benchmark.py:136Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 30. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: examples/*.yaml
Process rating: all ten parameters 50/100
- 0Tools and files. 1 referenced file(s) missing: examples/*.yaml
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 15 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 4 branches
- 100Steps. 68 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1855 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
- high The skill tells the model to perform an irreversible action with no human approval
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)
- +1No license
- +2Single-language instructions
- +3Description length 365: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 68 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (8 of 9)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.