BC winners-curse
In a common-value auction where all bidders estimate the SAME uncertain value, the winner is systematically the one who most OVER-estimated it — so winning is bad news that you likely overpaid. The discipline is to shade your bid for the adverse selection of winning, condition your estimate on the fact that you won, and pre-commit to a value-conditioned walk-away ceiling. Activate when: user is bidding in an auction, acquisition, or competitive process for something with a shared uncertain value ('what should we bid', 'we won — did we overpay', 'how high do we go', 'auction', 'best-and-final', 'competitive M&A / acquihire', 'ad auction / max CPC', 'bidding war', 'we keep losing deals — should we bid more'), or someone treats winning a contested bid as pure good news. Do NOT activate when: the value is PRIVATE (tastes differ, so 'you' knowing what it's worth to you is not an estimate of a shared truth) and there is no common-value component; there is a single buyer/seller with no competing bidders; the item's value is known with near-certainty. More: deciqai.com/c/winners-curse
In a common-value auction where all bidders estimate the SAME uncertain value, the winner is systematically the one who most OVER-estimated it — so winning is…
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, failures and branches
How to improve
- Shorten the description to 1024 characters.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1093 chars, limit 1024
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4990 tokens
- 100Steps. 44 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 10 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
- +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 1093: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +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: 63.