Divergence scan
Skill blaze10011/market-flow-desk/.claude/skills/divergence-scan
RSI/MACD divergence detector — the early-turn radar. Use when the user asks "is anything about to turn?", "any divergences?", "is this move running out of steam?", "check momentum vs price on <ticker>", or as part of analyzing the daily brief. Flags when price makes a higher high but RSI/MACD makes a lower high (bearish exhaustion) or price makes a lower low but momentum makes a higher low (bullish exhaustion) — often BEFORE the trend line breaks.From its SKILL.md
npx -y skills add blaze10011/market-flow-desk --skill divergence-scanAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.8 KB, 338 tokens by cl100k_base, as published. Nobody here has run it
Divergence Scan — early-turn radar
Divergence is the earliest read on a reversal: price and momentum disagreeing. Bearish = price higher-high but RSI/MACD lower-high (buyers exhausting). Bullish = price lower-low but RSI/MACD higher-low (sellers exhausting). Uses the same Wilder RSI + 12/26/9 MACD as the brief, so it agrees with the other tools.
Steps
- Run from project root:
python3 scripts/divergence.py [TICKERS...](no args = all 10 traded names) - Interpret only what it prints (never invent levels). For each name:
- "no divergence" = momentum confirms the move; nothing to flag.
- BEARISH divergence = the up-move is losing fuel; tighten stops / don't add / consider trimming into strength. Strongest when ⚡FRESH (newest swing within ~2 weeks) and on BOTH RSI and MACD.
- BULLISH divergence = selling is exhausting; a bounce/turn is more likely — but pair with trend before acting (a bullish divergence inside a strong downtrend can still fail).
- Deliver a one-line read per flagged name: kind (bull/bear), which oscillator(s), fresh or not, and what it implies for a 1–3d vs 14–20d lean.
Divergence is a WARNING, not a trigger — always confirm with trend-strength (ADX) and a price level before acting. Decision support, NOT advice. Data ~15-min delayed.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.