AC representativeness-heuristic
Activate when: user says 'this person/startup looks like a winner', 'I know one when I see it', 'they have the profile of a great hire', 'this reminds me of [famous success]', or any judgment where a vivid profile drives a probability estimate without an explicit base rate. Also activate when auditing for the conjunction fallacy or when pattern-matching is cited as the basis for a high-stakes decision. Do NOT activate when: probability is computed directly from data with no narrative element; base rate and profile have already been reconciled via explicit Bayesian reasoning. More: deciqai.com/c/representativeness-heuristic
Activate when: user says 'this person/startup looks like a winner', 'I know one when I see it', 'they have the profile of a great hire', 'this reminds me of…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 6. 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 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1815 tokens
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 630: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.