BB intent-router
Converges an underspecified request into an IntentSpec: looks up what sources answer, asks only what they cannot, halts instead of guessing, checks delivery against the spec. Use when a request to implement, add, change, fix or configure leaves a decision open — scope, approach, failure behaviour, what done means — contradicts itself, reads two ways, or rests on a premise sources rule out. Silent on a fully stated request its sources do not contradict; not for explaining existing state.
Converges an underspecified request into an IntentSpec: looks up what sources answer, asks only what they cannot, halts instead of guessing, checks delivery…
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7525 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 12 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 7525 tokens
- 100Steps. 63 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (9 tags): a typed call is more reliable
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
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 491: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 63 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.