AA evidence-gate
Generates evidence obligations for a claim or action, evaluates existing evidence against them, and returns a structured verdict (PASS / SOFT_PASS / BLOCK / CONFLICT) with safe downgrade guidance. TRIGGER when the agent is about to present a root-cause diagnosis, claim 'the cause is X', say 'this is safe', recommend a destructive or irreversible action, recommend a rollback, make a safety assertion, or state a strong conclusion based on limited evidence. DO NOT TRIGGER when summarizing, formatting, brainstorming possibilities, performing low-risk reversible operations, or when the caller already has its own evidence-validation step.
As a process A 94/100 · Runs to the end — no weak spots found
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 · 0
✓ No critical or high findings
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 94/100
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 134 steps
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2690 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 17 top-level sections: this looks like several domains in one skill
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 640: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 134 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.