AF interview-synthesis
Turn a pile of interview notes into findings that survive scrutiny — the code-then-theme pass, the counting discipline (how many actually said it), the quote selection that illustrates instead of cherry-picks, and the confidence lines a small sample earns. Use when asked synthesize these user/customer/exit interviews, what did we actually learn from the calls, turn 12 transcripts into insights, or are these themes real. Produces the coded themes with counts, the divergences preserved, the illustrative quotes, and the claims sized to the sample.
Turn a pile of interview notes into findings that survive scrutiny — the code-then-theme pass, the counting discipline (how many actually said it), the quote…
As a process F 52/100 · Will not run — References files that are not bundled: ../survey-design-basics/SKILL.md
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 · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../survey-design-basics/SKILL.md
Process rating: all ten parameters 52/100
- 0Tools and files. 1 referenced file(s) missing: ../survey-design-basics/SKILL.md
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1187 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
- 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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 550: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.