BB arrow-information-paradox
Diagnoses the buyer/seller deadlock in any trade of information — the buyer cannot value what they cannot see, but once they see it they have it for free — and selects the disclosure mechanism (patent, NDA, staged disclosure, trusted intermediary + escrow, reputation, or proxy demonstration) that lets the buyer estimate value WITHOUT the seller losing appropriability. Activate when: user must sell, license, or pitch information/technology/know-how and asks 'how much do we reveal before they'll pay', 'how do we prove it works without giving it away', 'should we patent this or keep it secret', 'they want to see the code/formula/method before signing', 'how do we let a buyer value our tech in due diligence without leaking it', or describes an M&A/VC/licensing/consulting deal where the thing being sold IS the information. Do NOT activate when: the good has no information-appropriability problem (a commodity, a physical product that can be inspected without transferring the design); the information is already public; or the question is about pricing/negotiation with no disclosure-leakage risk (use batna-zopa instead). More: deciqai.com/c/arrow-information-paradox
Diagnoses the buyer/seller deadlock in any trade of information — the buyer cannot value what they cannot see, but once they see it they have it for free —…
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1176 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5545 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 21 mutating operations with no state check
- 55Failures and branches. 1 branches
- 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 5545 tokens
- 100Tools and files. No external tools needed
- 100Steps. 50 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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 1176: 120–800 characters recommended
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 50 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 45.