Skip to content
SkillScript-led1,594 tokens in use

Crypto Regime Analyzer

Scores crypto market regime from 0 to 100 across six components using free CoinGecko and Binance public data, or from an offline snapshot file.

7,426 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/crypto-regime-analyzer

Skill label

measured from its files

What installing Crypto Regime Analyzer costs

94tokens idle
1,594tokens in use
3,726tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/calculators/__init__.py, scripts/calculators/alt_breadth_calculator.py, scripts/calculators/btc_trend_calculator.py, scripts/calculators/dominance_calculator.py, scripts/calculators/drawdown_vol_calculator.py, scripts/calculators/funding_calculator.py, scripts/calculators/momentum_thrust_calculator.py, scripts/crypto_regime_analyzer.py, scripts/data_client.py, scripts/numeric_utils.py, scripts/report_generator.py, scripts/scorer.py, scripts/tests/conftest.py, scripts/tests/test_alt_breadth_calculator.py, scripts/tests/test_btc_trend_calculator.py, scripts/tests/test_data_client.py, scripts/tests/test_dominance_calculator.py, scripts/tests/test_drawdown_vol_calculator.py, scripts/tests/test_funding_calculator.py, scripts/tests/test_missing_dependency_exit.py, scripts/tests/test_momentum_thrust_calculator.py, scripts/tests/test_scorer_and_pipeline.py.

Touches

shelldetectednetworkdetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure17/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources13/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 70
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 70
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/data_client.py, line 57

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity36
  • Momentum40

Crypto Regime Analyzer describes what the crypto market currently looks like before any coin-level work begins. A Python script combines six weighted components (BTC trend structure, altcoin breadth, BTC dominance, perpetual funding, drawdown and volatility, and momentum) into a composite score, where 100 is the healthiest risk-on reading, and assigns a zone of RISK_ON, NEUTRAL or RISK_OFF.

It needs no API key. It does not pick coins, give buy or sell signals or set price targets. The zones are descriptive heuristics that have not been validated as allocation rules.

What You Get

  • A 0 to 100 composite score and a zone (RISK_ON, NEUTRAL or RISK_OFF)
  • A per-component table with weight, score and a signal string
  • Flags for components that had no data, with the effect on confidence
  • crypto_regime.json for chaining into other skills and crypto_regime.md as a one-page report

Common Use Cases

  • A daily check of whether crypto conditions look risk-on or risk-off
  • Asking whether altcoins are participating broadly or only a few are leading
  • Checking whether perpetual funding rates look crowded
  • Feeding a descriptive crypto input into an exposure summary

What Makes It Unique

It works with free, keyless public data and has an offline mode, so the same score can be reproduced from a snapshot. Missing components are handled by redistributing weights and reporting the gap. A validation reference states the evidence boundary, so the bands are not presented as tested allocation rules. Dominance history builds up locally one observation per day, and the component reports as unavailable until enough days exist.

Under The Hood

In live mode the agent runs a Python script that calls the public CoinGecko API and the Binance futures endpoint over the network, with throttling for the free tier; the first run of a day can take a few minutes. It caches fetched data and a daily dominance record in a local cache folder (.crypto_regime_cache by default), and writes the JSON and Markdown reports into the chosen output folder, so it creates files and folders on disk. Offline mode makes no network calls. No API key is used. The agent also creates the output folder with a shell command.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers