Skip to content
SkillScript-led2,282 tokens in use

VCP Screener

Screens S&P 500 stocks for Mark Minervini's Volatility Contraction Pattern, with a Stage 2 trend filter, pivot and stop levels, and a historical scan for one ticker.

7,432 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/vcp-screener

Skill label

measured from its files

What installing VCP Screener costs

142tokens idle
2,282tokens in use
7,000tokens, 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/_fmp_compat.py, scripts/_price_bars.py, scripts/calculators/__init__.py, scripts/calculators/execution_state.py, scripts/calculators/forward_outcome.py, scripts/calculators/pattern_classifier.py, scripts/calculators/pivot_proximity_calculator.py, scripts/calculators/relative_strength_calculator.py, scripts/calculators/trend_template_calculator.py, scripts/calculators/vcp_pattern_calculator.py, scripts/calculators/volume_pattern_calculator.py, scripts/coverage_client.py, scripts/evaluation_coverage.py, scripts/fmp_client.py, scripts/historical_report.py, scripts/historical_scanner.py, scripts/report_generator.py, scripts/scorer.py, scripts/screen_vcp.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

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
  • Structure25/25
  • Examples9/15
  • Output15/15
  • Size15/15
  • Resources1/15

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 33
  • Reaches the network−10

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

    scripts/_fmp_compat.py, line 71
  • Reads credentials−15

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

    scripts/fmp_client.py, line 177
  • Writes files−8

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

    scripts/historical_report.py, line 26

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

VCP Screener looks for Stage 2 uptrend stocks that are forming tight bases with contracting volatility near a breakout pivot. A three-phase pipeline pre-filters on quotes, applies a seven-point trend template using 260-day histories from the Financial Modeling Prep API, then detects and scores contractions.

Each candidate gets a composite score, an execution state from Pre-breakout to Damaged, a pattern type, contraction depths, pivot price, a stop level and a relative strength rank. A historical mode walks one ticker’s multi-year price history and lists every VCP with forward outcome statistics. It is a research tool and not investment advice.

What You Get

  • A scored list of VCP candidates with execution state, pattern type and rating
  • Trade setup fields for each candidate: pivot, stop, risk percent, volume dry-up and relative strength
  • Strict mode that keeps only valid patterns in the Pre-breakout or Breakout state
  • A historical report for one ticker with every detected VCP and its breakout, stop-hit or timeout outcome

Common Use Cases

  • Producing a daily or weekly list of tight-base breakout candidates
  • Studying how past VCPs on one stock played out over several years
  • Tuning pattern parameters such as minimum contractions and contraction ratio for research

What Makes It Unique

It reports the quality of the pattern and its execution state as two separate answers, so a well-formed pattern that has already run is marked extended. Price data is checked bar by bar and invalid data is flagged and never filled in, and a coverage block states how much of the universe was evaluated.

Under The Hood

The agent runs a Python script from the shell. The script calls the Financial Modeling Prep API with a key from an environment variable or flag, using about a hundred calls for the default top-100 run and two for a single-ticker history. It writes timestamped JSON and Markdown reports to the output folder. Reference files explain the pattern theory and scoring system. The free FMP tier covers the default run.

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