AC intelligence
Use when the user asks "what's hot", "what's moving", "any alpha", "show me squeeze setups", "what's the setup on ETH", "is SOL coiled", "should I deploy NEAR" or any market-scan / single-pair-drilldown question. Surfaces Superior Trade's live multi-bucket scoring across Hyperliquid alts + HIP-3 (stocks/indices/commodities/FX) — Squeeze fuel, Stealth accumulation, Coiled spring, Basis flipping. The engine picks the strongest timeframe (15m/1h/4h/24h) per pair per bucket; you don't pick one. Pairs in to the existing strategy → backtest → deployment workflow at api.superior.trade.
Use when the user asks "what's hot", "what's moving", "any alpha", "show me squeeze setups", "what's the setup on ETH", "is SOL coiled", "should I deploy…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "updated"
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 85Steps. 10 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 731 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 585: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 10 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.