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

economic-calendar-trading

Skill17 starsChanged 4 months agoApache-2.0View on GitHub

Plan scheduled macro-event risk from official calendars and point-in-time expectations. Use for FOMC, employment, inflation, GDP, or other releases requiring standardized surprise, component, revision, scenario, and execution analysis.

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, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use a point-in-time consensus and same-definition historical series.

    line 29
  2. Distinctive:

    Use a pretested bar-based delay or price-structure trigger.

    line 55
  3. Very specific:

    Use get_financial_news to analyze FOMC statements and press conferences for hawk/dove tone shifts.

    line 64
  4. Distinctive:

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

    line 70
  5. Distinctive:

    Verify actuals and revisions from the primary source before interpretation.

    line 78
  6. Distinctive:

    Use the predeclared execution gate.

    line 79
  7. Very specific:

    Treat clustered or conflicting components as lower confidence or no trade.

    line 82

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Economic Calendar Trading

Plan macro-event risk from live official calendars, time-stamped consensus, release vintages, and observable price triggers. Surprise matters, but revisions, components, positioning, uncertainty, and regime affect the response.

Event Map

Event familyComponents to recordPrimary source
FOMCDecision, statement changes, SEP, press conferenceFederal Reserve
EmploymentPayrolls, unemployment, participation, wages, revisionsBLS
InflationHeadline/core, monthly/annual, category breadth, revisionsBLS/BEA
Growth/activityReal/nominal detail, inventories, revisions, survey componentsSource agency

Standardized Surprise

Standardized surprise = (Actual - consensus) / historical standard deviation of surprises

Use a point-in-time consensus and same-definition historical series. State source, sample, standard deviation, revisions, and transformation. If history is insufficient, report raw surprise and forecast range without a synthetic score.

Workflow

1. Check Calendar

get_economics_calendar(from_date=<start>, to_date=<end>, impact="high")

Refresh before each session and verify date, time, timezone, and revision policy against the official agency calendar; third-party impact labels are screening aids only.

2. Research Consensus

get_financial_news(topic="<event> forecast consensus <month> <year>", max_results=10)

Extract: consensus forecast, range of estimates, leading indicators, and current market positioning.

3. Build Scenario Matrix

Map component combinations, revisions, and price triggers. Include no trade for mixed releases or failed liquidity conditions; do not assign probabilities without a calibrated model.

4. Post-Release Execution Gate

Use a pretested bar-based delay or price-structure trigger. Require verified actuals, acceptable spread/depth, stable timestamps, and a calculable stop; event labels do not determine a universal waiting period.

5. Trade the Reaction

  • Continuation candidate: enter only on the specified closed-bar or retest trigger.
  • Fade candidate: define overreaction in normalized returns and test separately; VWAP is a benchmark, not a guaranteed destination.

6. FOMC Analysis

Use get_financial_news to analyze FOMC statements and press conferences for hawk/dove tone shifts.

Analyze the decision, statement redlines, projections, and press conference separately. Measure the response in policy-rate futures/yields and the traded asset; do not infer fixed direction or duration from a hawkish/dovish label.

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: Use the official Federal Reserve calendar and BLS release calendar because dates can change; Federal Reserve research shows reaction depends on surprise, disagreement, and regime.

Key Rules

  • Verify actuals and revisions from the primary source before interpretation.
  • Use the predeclared execution gate; neither immediate trading nor a fixed wait is universally safe.
  • Choose order type from the fill-versus-price-risk tradeoff; limits may not fill and markets may slip.
  • Aggregate direct, correlated, and factor exposures in the event stress test.
  • Treat clustered or conflicting components as lower confidence or no trade.
  • Size from stress loss, not a vendor impact score.

Related Skills

  • sentiment-analysis -- Pre-event sentiment gauges positioning
  • sector-rotation -- Macro data drives sector rotation shifts

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.