Skip to content
SkillScript-led1,554 tokens in use

stockbee-20pct-study

Scans US stocks for +20% and -20% movers, classifies catalyst and chart context, tracks forward outcomes and summarizes recurring patterns.

7,430 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/stockbee-20pct-study

Skill label

measured from its files

What installing stockbee-20pct-study costs

91tokens idle
1,554tokens in use
4,940tokens, 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_client.py, scripts/run_20pct_study.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
  • Structure15/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources10/15

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 36
  • Reaches the network−10

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

    scripts/fmp_client.py, line 32
  • Reads credentials−15

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

    scripts/fmp_client.py, line 162
  • Writes files−8

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

    scripts/run_20pct_study.py, line 386

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

Stockbee 20% Study builds a durable event record of large US stock moves. A scan finds stocks that moved 20 percent up or down over a lookback window, with price and dollar-volume filters, using either the FMP API or an offline OHLCV JSON file.

Further commands enrich each event with a catalyst label and chart context, update 1, 3, 5, 10 and 20 day outcomes with MFE and MAE, summarize cohorts and back-fill history. It is a research and model-book workflow and does not produce buy or sell signals.

What You Get

  • A JSON and Markdown daily report of 20 percent movers
  • Enriched event records with catalyst and technical context labels
  • Forward outcome updates with close return, MFE, MAE and continuation return
  • Cohort summaries with rule candidates and an edge-hint YAML export
  • A durable state/stockbee/20pct_study_events.jsonl file

Common Use Cases

  • Running a daily study after the US close
  • Back-filling years of movers from an OHLCV file to study what happened next
  • Exporting edge hints to downstream strategy research skills

What Makes It Unique

It marks back-filled records for survivorship bias unless the data includes delisted symbols, and attaches overfitting controls and minimum sample sizes to its cohort rules. Offline mode works without any API key.

Under The Hood

A Python CLI reads offline OHLCV and catalyst JSON files, or calls the FMP stable API over the network using a key from the environment or a command-line option, through a bundled client loaded only for live runs. It writes JSON, Markdown and YAML reports and appends to a local JSONL state file. The SKILL.md has the model run these commands from the shell.

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