Skip to content
SkillScript-led969 tokens in use

PEAD Screener

A Python screener for post-earnings announcement drift that tracks earnings gap-ups on weekly candles and sorts them into monitoring, signal-ready, breakout and expired stages.

7,428 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/pead-screener

Skill label

measured from its files

What installing PEAD Screener costs

97tokens idle
969tokens in use
3,036tokens, 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/calculators/__init__.py, scripts/calculators/breakout_calculator.py, scripts/calculators/liquidity_calculator.py, scripts/calculators/risk_reward_calculator.py, scripts/calculators/weekly_candle_calculator.py, scripts/fmp_client.py, scripts/report_generator.py, scripts/scorer.py, scripts/screen_pead.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
  • Structure22/25
  • Examples9/15
  • Output7/15
  • Size15/15
  • Resources2/15

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 22
  • 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 169
  • Writes files−8

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

    scripts/report_generator.py, line 50

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

PEAD Screener looks for stocks that gapped up on earnings and checks how their weekly candles develop afterwards. A red candle pullback marks a signal-ready setup, and a move above that candle’s high marks a breakout. Each candidate gets a stage, a composite score and rating, liquidity figures and a worked entry, stop and target.

It runs in two modes: from the Financial Modeling Prep earnings calendar, or from the JSON report of the earnings-trade-analyzer skill. It describes screening results and does not give investment advice.

What You Get

  • A JSON report pead_screener_DATE_TIME with stage classification
  • A Markdown report grouped by stage
  • Stages of MONITORING, SIGNAL_READY, BREAKOUT and EXPIRED for each candidate
  • Entry, stop, target and risk and reward for each setup
  • A visible count of earnings rows whose timing was unconfirmed

Common Use Cases

  • Finding recent earnings gap-up stocks that are pulling back in a red weekly candle
  • Moving from an earnings analyzer report to a weekly-candle follow-up screen
  • Keeping a watchlist and removing names that left the monitoring window
  • Reviewing PEAD theory and entry and exit rules from the reference files

What Makes It Unique

It focuses on weekly candle structure after the gap and turns it into explicit stages. The two input modes let it work from the broad earnings calendar or from a graded list, and the skill advises Mode B for scheduled US-equity routines because the global calendar can spend the API budget on non-US listings. It also shows how many earnings rows had unconfirmed timing so the fallback assumption stays visible.

Under The Hood

Claude runs a Python script from the shell. The script calls the Financial Modeling Prep API with your key from the FMP_API_KEY variable, and the free tier of 250 calls a day covers default screening. In Mode B it reads an earnings-trade-analyzer JSON file from disk. It writes a JSON and a Markdown report into the output folder. Reference files on PEAD strategy and entry and exit rules are loaded when Claude presents results.

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