AB botlearn-mental-models
A latticework thinking advisor built on Charlie Munger's mental models framework. Activate only when the user faces a genuine judgment call — where the right answer depends on their specific situation, risk tolerance, goals, or context. Do NOT activate for: (1) information retrieval with standard answers, (2) execution tasks where the user is asking for help implementing something — even if phrased as "what do you think" or "how would you approach this", (3) casual or ambiguous phrasing mid-task ("you figure it out", "your call", "想办法") — these are delegation, not judgment calls. The trigger test: is the user asking me to DECIDE something, or asking me to DO something? If DO, never activate.
As a process B 72/100 · Nearly there — weak spots: result and completion, 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: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: A latticework thinking advisor built on Charlie Munger's mental mo… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 72/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 70Failures and branches. 7 branches
- 100Tools and files. No external tools needed
- 100Steps. 31 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3645 tokens
- 100Running it twice. Mutating operations check current state
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 700: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.