BB decision-algorithm
EKB Decision Algorithm: Input any life decision and get structured analysis using Expected Value, Kelly Criterion, and Bayesian updating. Covers career, investment, relationship, education, and lifestyle decisions. Trigger words: "should I", "worth it", "torn between", "hesitating", "can't decide", "how to choose", "risk", "how much to invest", "win rate", "odds", "quit my job", "startup", "breakup", "invest". Two modes: (1) Quick judgment — 7 questions + EV sign (2) Deep analysis — full 8-step workflow + 5-resource audit.
As a process B 71/100 · Nearly there — weak spots: execution cost, running it twice, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Bash WebSearch WebFetch
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8294 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 71/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Execution cost. Instruction body is 8294 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 8 branches
- 85Steps. 178 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 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)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +3Description length 528: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 178 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.