BC cross-asset-intelligence
Cross-asset financial analysis API combining crypto and traditional markets. BTC vs S&P500/NASDAQ/Nikkei225/DAX correlation, cross-market risk score (0-100), crypto news impact analysis, macroeconomic environment report, token contract risk evaluation, daily market briefing. Pay-per-request with USDC micropayments via x402 on Base. No API key needed. Use when asked to 'check BTC correlation with stocks', 'what is the market risk level', 'is this token safe', 'crypto market analysis', 'macro outlook', 'morning market briefing', 'cross-asset analysis', 'BTC vs equities', 'risk score', 'token safety check', 'evaluate contract risk for address', 'daily market update', 'market sentiment', 'portfolio risk', 'VIX and crypto', 'correlation between bitcoin and stock market', 'financial analysis for trading', 'hedge fund briefing', 'institutional market report'. Bilingual: English and Japanese. Powered by Claude AI (Haiku/Sonnet/Opus). Data from CoinGecko, FRED, Twelve Data, RSS feeds. 4 pricing tiers: quick ($0.001, no AI, sub-second), insight ($0.03-0.15, Claude Haiku), analysis ($0.08-0.20, Claude Sonnet), pro ($0.80-1.00, Claude Opus institutional-grade).
As a process C 59/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
How to improve
- Shorten the description to 1024 characters.
- 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
- error
description-longdescription is 1167 chars, limit 1024
Process rating: all ten parameters 59/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1043 tokens
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1167: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 29 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.