AD contrarian-question
Activate when: user says 'contrarian question,' 'the Thiel question,' 'what important truth do very few people agree with you on,' 'is this actually contrarian,' or 'what valuable company is nobody building'; user is drafting or stress-testing a startup thesis, pitch 'secret,' or investment view that claims to be non-consensus; user is preparing for an interview or pitch where they must defend an unpopular claim; user suspects their bold-sounding claim is really consensus in edgy clothing. Do NOT activate when: the user needs the broader portfolio-level discipline of hunting for edges across many bets (use non-consensus-thinking instead); the claim is a matter of taste or values with no evidence path to being right or wrong; the user wants validation or applause for a provocative take rather than a gate that might fail it. More: deciqai.com/c/contrarian-question
Activate when: user says 'contrarian question,' 'the Thiel question,' 'what important truth do very few people agree with you on,' 'is this actually…
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 2. 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 49/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 70Execution cost. Instruction body is 4992 tokens
- 100Tools and files. No external tools needed
- 100Steps. 53 steps
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 874: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 53 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.