◈

validate_sr_with_claude

Claude AIClaude APIS&R

INSTALLATION

$python -c "exec(open('validate_sr_with_claude.py').read())"

#or paste directly into your Claude Code terminal

[ ABOUT ]

Sends the raw list of computed support and resistance levels to Claude along with the coin name and requests that they be ranked by structural significance — highest-tested levels, clearest reaction zones, and proximity to current price all factor into the ranking. The result is returned as a JSON array sorted by significance.

Algorithmic S/R detection produces many candidate levels, not all of which are equally significant. Claude's ranking step filters the list to the most actionable levels by applying pattern recognition that is difficult to encode as rules — for example, levels that have been tested four or more times and held are ranked higher than levels that were touched once and briefly. Parse the JSON output and take the top 2-3 for drawing.

[ USAGE EXAMPLE ]

example.py

raw = [95000, 93500, 91200, 98000, 101500]
ranked = validate_sr("Bitcoin", raw, price_history)
# → '[98000, 95000, 91200]'  — sorted by significance

[ FULL CODE ]

validate_sr_with_claude.py

def validate_sr(coin, raw_levels, price_history): msg = client.messages.create(model="claude-sonnet-4-5", max_tokens=300, messages=[{"role":"user","content":f"For {coin}, rank these levels by strength: {raw_levels}. Return sorted JSON array."}]) return msg.content[0].text

[ METADATA ]

CategoryClaude AI

ComplexityBeginner

LanguagePython 3.10+

TagsClaude API, S&R

[ ASK CLAUDE ]

Ask AI about this skill before installing it.

[ RELATED SKILLS ]

generate_market_narrative

Use Claude to write a natural language market analysis narrative

rate_signal_quality

Ask Claude to rate the quality of a trading signal from 0-100

analyze_chart_screenshot

Pass TradingView chart screenshot to Claude vision for S&R detection