Skip to content
SkillScript-led1,203 tokens in use

stockbee-episodic-pivot-analyzer

Scores Day 1 Episodic Pivot candidates on catalyst quality plus gap, range and volume confirmation, and sorts them into watch and handoff states.

7,430 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/stockbee-episodic-pivot-analyzer

Skill label

measured from its files

What installing stockbee-episodic-pivot-analyzer costs

124tokens idle
1,203tokens in use
2,586tokens, 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/analyze_ep.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
  • 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 62
  • Reaches the network−10

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

    scripts/analyze_ep.py, line 46
  • Reads credentials−15

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

    scripts/analyze_ep.py, line 197
  • Writes files−8

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

    scripts/analyze_ep.py, line 1050

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 Episodic Pivot Analyzer classifies candidates after a catalyst such as earnings, a guidance raise, M&A, an FDA decision, an analyst action, a contract or a product launch. It scores catalyst quality together with gap and range expansion, volume shock, neglect context, liquidity and the risk distance to the EP-day low.

Each candidate gets a state (actionable Day 1, Day 1 watch, delayed EP watch, catalyst watch or reject), an EP type and flags for handoff to pead-screener. It does not find news itself and does not give investment advice.

What You Get

  • A stockbee_episodic_pivot JSON report with scores and reasons
  • A Markdown candidate report
  • State and EP type for each candidate, such as EARNINGS_EP or FDA_EP
  • Risk to the EP-day low and PEAD handoff and delayed-EP flags

Common Use Cases

  • Sorting a list of earnings and guidance events into Day 1 and delayed watchlists
  • Combining catalyst context with momentum burst price and volume output
  • Passing strong earnings candidates on to a post-earnings drift screener

What Makes It Unique

It scores the news and the price reaction together, and separates names to act on at once from delayed EP names not to chase on Day 1. The catalyst must be supplied, because the skill does not search for news.

Under The Hood

A Python script reads JSON inputs you provide and writes JSON and Markdown reports to a reports folder. Optional price enrichment calls the FMP API over the network with a key from the environment, through a bundled client loaded only for live runs, with a cap on API calls. The SKILL.md has the model run the script 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