AB second-level-thinking
Apply Howard Marks' Second Level Thinking framework to investment decisions. Use this skill whenever the user is analyzing an investment opportunity, evaluating a trade thesis, stress-testing a conviction, or asking whether a stock/asset/market is actually as attractive as it looks. Also trigger when the user wants to challenge their own reasoning ("am I just following the crowd?"), wants to identify what the market is mispricing, is debating whether a consensus view is already fully reflected in price, or asks about risk/reward asymmetry, market cycles, or contrarian positioning. The skill channels Marks' philosophy: superior returns require being different AND right — and that starts with understanding what everyone already believes.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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: 2. 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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash) 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
- 100Steps. 30 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1589 tokens
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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 745: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 30 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.