AB founder-wisdom
Surfaces hard-won axioms from experienced startup founders and operators across hiring, fundraising, product, sales, finance, governance, strategy, management, and crisis. Use whenever someone is wrestling with a startup, scale-up, or early-stage company decision — hiring or firing, picking a co-founder, whether to raise at all, bootstrapping and staying independent, non-dilutive capital, selling the company, moats and positioning, how AI changes the way a startup team works, sells, and hires, who stays accountable when an agent does the work, or any "I'm a founder and I'm not sure what to do" moment. Trigger without an explicit ask for "advice" — "should I…", "is it normal that…", "we're thinking about…", and "how do experienced founders handle…" are in scope, as is helping someone else with founder-stage decisions (advisor, coach, mentor, investor). Also trigger on "who said X" questions about the startup canon.
As a process B 73/100 · 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: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7519 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70Execution cost. Instruction body is 7519 tokens
- 100Tools and files. No external tools needed
- 100Steps. 42 steps
- 100When it triggers. States when to use and when not to
- 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
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 927: 120–800 characters recommended
- +4No input/output examples
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (21 of 21)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.