AC build-protocol-decision
Rigorous workflow for high-stakes decision-making: investments (stocks/crypto/real-estate), major purchases, technology selection, supplier choice. Use when the decision commits >$1000 or >1 day of effort, is hard to reverse, or involves tradeoffs between multiple alternatives. Inherits build-protocol core rules, adds decision-specific: real-time data verification mandate (never trust document prices), methodology transparency (PE/DCF/MA required, no gut calls), position-sizing discipline, stop-loss as first-class rule, daily P/L tracking. Guards against 'Sycophancy of Precision'—writing '+12.85%' looks trustworthy but precision ≠ accuracy. Triggers on: 'should I buy/invest in X', 'compare options', 'pick a vendor', '选哪个', '投资策略', '操盘手册', 'which option', 'buy vs build', '怎么选'.
Rigorous workflow for high-stakes decision-making: investments (stocks/crypto/real-estate), major purchases, technology selection, supplier choice.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 5. 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 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 5 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 85Steps. 65 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2441 tokens
- 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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 787: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 65 items
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.