Skip to content
SkillScript-led2,037 tokens in use

stockbee-setup-fluency-trainer

Turns momentum burst screener output into a model book with 3-day and 5-day outcomes, and runs blind replays of your own VCP decisions.

7,430 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/stockbee-setup-fluency-trainer

Skill label

measured from its files

What installing stockbee-setup-fluency-trainer costs

125tokens idle
2,037tokens in use
7,967tokens, 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/build_model_book.py, scripts/decision_replay.py, scripts/fmp_client.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
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources11/15

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 35
  • Reaches the network−10

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

    scripts/build_model_book.py, line 47
  • Reads credentials−15

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

    scripts/build_model_book.py, line 109
  • Writes files−8

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

    scripts/build_model_book.py, line 296

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 Setup Fluency Trainer keeps a JSONL model book of Stockbee-style Momentum Burst setups. It ingests candidates from the momentum burst screener, then updates 3-day and 5-day forward results with close return, MFE, MAE, stop-hit status and an outcome tag such as STRONG_WINNER or FAILED_STOP, and summarizes cohorts by rating, trigger and setup tags.

A second script, decision_replay.py, captures your enter, wait or pass decisions on vcp-screener candidates, then replays a blind sample later and reveals the price path. It scores rule adherence separately from the outcome. It is a study tool and does not give investment advice.

What You Get

  • A durable state/stockbee/model_book.jsonl with setup fields, human labels and outcomes
  • Ingest, update and summary reports in JSON and Markdown
  • Outcome tags and cohort statistics with rule candidates to review as evidence prompts
  • Write-once decision capture records, blind replay views and reveal reports with four quadrants of adherence and outcome

Common Use Cases

  • Reviewing failed and missed momentum burst candidates
  • Deciding which setup tags to promote, downgrade or filter
  • A weekend blind replay of your own VCP enter, wait or pass decisions

What Makes It Unique

The blind replay keeps what you decided separate from what the price did afterwards, so a rule-compliant decision with a bad outcome is shown as exactly that. Cases captured late or with unverified prices are excluded and counted.

Under The Hood

Python scripts read screener JSON reports and offline OHLCV files and write JSONL, JSON and Markdown files into local state and reports folders. Outcome updates can instead call the FMP API over the network with a key from the environment, through a bundled client loaded only for live runs; blind replay uses the standard library only and needs no key. The SKILL.md has the model run the scripts 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