agentleFS
SKE-LabsSKE-Labs/agent-trading-skills/skills/fundamental-analysis/earnings-trading/SKILL.md

earnings-trading

Skill17 starsChanged 4 months agoApache-2.0View on GitHub

Trade around earnings announcements for stocks. Use when positioning for earnings, trading post-earnings moves, or analyzing earnings-driven volatility.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not invent a numeric "whisper" from price direction.

    line 26
  2. Distinctive:

    Look for dated estimate revisions, price-target changes, and positioning proxies.

    line 50
  3. Distinctive:

    Treat the setup as a testable hypothesis, not a prediction.

    line 66
  4. Distinctive:

    Do not hold through earnings unless the mandate explicitly permits gap and halt risk.

    line 74
  5. Distinctive:

    Never infer a hidden expectation as fact.

    line 75
  6. Distinctive:

    Verify adjusted metrics against GAAP reconciliation and use point-in-time consensus.

    line 77
  7. Distinctive:

    Treat transcript tone and analyst questioning as contextual evidence, not standalone signals.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Earnings Trading

Analyze and trade earnings only from time-stamped expectations, primary filings, and an explicit event-risk plan. Surprise is important, but price also reflects guidance, revisions, positioning, valuation, liquidity, and regime.

Earnings Evidence Matrix

DimensionRecord
EarningsGAAP and adjusted EPS, reconciliation, point-in-time consensus, surprise
RevenueReported revenue, organic/segment mix, consensus, FX effects
OutlookPrior versus new ranges and assumptions; do not reduce guidance to one word
QualityCash flow, margins, working capital, one-offs, share count
ContextPre-event move, options-implied move if available, valuation, liquidity

Priced Expectations

Do not invent a numeric "whisper" from price direction. Report observable proxies separately: estimate revisions and dispersion, pre-event abnormal return, short interest, options-implied move/skew, and source-dated analyst commentary. Label any inference about positioning as uncertain.

Post-Earnings Drift

Stocks that surprise on earnings tend to continue drifting in the same direction -- one of the most documented market anomalies.

Post-earnings-announcement drift is an empirical research finding, not a fixed probability or holding period. Define standardized unexpected earnings using point-in-time estimates, form size/liquidity buckets, and test horizons without overlapping-sample leakage. Compare closed-bar entry times and fixed, time, and trailing exits after spread and slippage.

Workflow

1. Get Consensus Estimates

get_fundamentals(ticker="AAPL")

Pull point-in-time EPS/revenue estimates, estimate dispersion, earnings timestamp, and historical surprises. Verify event time and results in the issuer's 8-K/earnings release and 10-Q.

2. Research Expectations and Sentiment

get_financial_news(topic="AAPL earnings <quarter> <current year> expectations analyst", max_results=15)

Look for dated estimate revisions, price-target changes, and positioning proxies. Separate facts from commentary and deduplicate syndicated stories.

3. Analyze Call Transcript (Post-Release)

get_financial_news(topic="AAPL earnings call transcript summary management tone", max_results=10)

Compare the transcript with the prior quarter using reproducible features: quantified outlook changes, topics raised by analysts, answer specificity, and risk-language changes. Quote minimally with timestamps and treat tone as interpretation, not a deterministic label.

4. Score and Decide

Report each dimension separately, price reaction versus any implied move, liquidity, and valid, watch, or no trade. If trading, state entry trigger, gap-aware invalidation, time exit, maximum event loss, and source timestamps.

Evidence and Validation

  • Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
  • Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
  • Include spread, fees, slippage, borrow or funding, partial fills, and latency. Reject the setup when net expectancy is not positive or depends on one narrow parameter.
  • Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
  • Research basis: Livnat & Mendenhall documents post-earnings-announcement drift, but its magnitude depends on how surprise is measured and does not justify a fixed continuation probability.

Key Rules

  • Do not hold through earnings unless the mandate explicitly permits gap and halt risk.
  • Never infer a hidden expectation as fact; show the observable positioning proxies.
  • Calibrate entry delay in closed bars for the instrument and session rather than imposing a universal clock time.
  • Verify adjusted metrics against GAAP reconciliation and use point-in-time consensus.
  • Treat transcript tone and analyst questioning as contextual evidence, not standalone signals.
  • Size from the stress gap loss and portfolio risk limit, not a fixed percentage reduction.

Related Skills

  • sentiment-analysis -- source-dated expectations and positioning evidence
  • economic-calendar-trading -- Macro events near earnings amplify volatility

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.