AB discovery-call-prep
Turns a stated hypothesis and what you know about a person into a discovery-call question guide where every question asks about something that already happened. Grounded in two books, not paraphrased from either, The Mom Test's rule that a real interview asks about past behavior, never a hypothetical, and Transformed's four product risks (value, usability, feasibility, business viability), which decide what each question is actually testing. Tags every question with the risk it tests, names any hypothesis an interview cannot answer, and ends with an ask that costs the person something real. Use whenever the user says "prep me for a discovery call", "write a discovery guide", "build interview questions for this hypothesis", "/discovery-call-prep", or pastes a hypothesis plus notes on who they're about to talk to.
Turns a stated hypothesis and what you know about a person into a discovery-call question guide where every question asks about something that already happened.
As a process B 79/100 · Nearly there — weak spots: 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7967 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "installType" - note
frontmatter-keyunknown frontmatter key "requiresMCP" - note
frontmatter-keyunknown frontmatter key "mcpDependencies" - note
frontmatter-keyunknown frontmatter key "triggerPhrases" - note
frontmatter-keyunknown frontmatter key "status"
Process rating: all ten parameters 79/100
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7967 tokens
- 100Tools and files. No external tools needed
- 100Steps. 83 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 823: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 21 headings
- +3Step-by-step instructions: 83 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.