AgentStack
SKILL verified Apache-2.0 Self-run

News Trading

skill-ske-labs-agent-trading-skills-news-trading · by SKE-Labs

Trade volatility around economic news and corporate events. Use deviation-from-consensus scoring to gauge expected move magnitude. Use when capitalizing on market-moving news, trading earnings, or positioning for scheduled events.

No reviews yet
0 installs
15 views
0.0% view→install

Install

$ agentstack add skill-ske-labs-agent-trading-skills-news-trading

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of News Trading? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

News Trading Strategy

Trade volatility from scheduled economic events using deviation-from-consensus scoring.

Setup Conditions

High-Impact Events

| Event | Impact | Typical Move | | --- | --- | --- | | FOMC/Fed Rate | Very High | 100+ pips | | NFP (Jobs) | Very High | 50-100 pips | | CPI (Inflation) | High | 50-80 pips | | GDP | High | 30-50 pips |

Deviation-from-Consensus Scoring

Deviation Score = (Actual - Forecast) / Forecast x 100

| Event | Small (skip/minimal) | Moderate (tradeable) | Large (high conviction) | | --- | --- | --- | --- | | NFP | +/-25K | +/-50K | +/-100K+ | | CPI | +/-0.1% | +/-0.2% | +/-0.3%+ | | GDP | +/-0.2% | +/-0.5% | +/-1.0%+ |

Meeting consensus rarely produces tradeable moves -- the deviation drives the trade.

Post-Event Wait Periods

| Event Impact | Wait Time | | --- | --- | | Very High (FOMC, NFP) | 30-45 min | | High (CPI, GDP) | 15-30 min | | Medium (Retail Sales, PMI) | 5-15 min |

Workflow

1. Check Economic Calendar

get_economics_calendar(from_date=, to_date=, impact="high")

Identify upcoming high-impact events. Note dates, times, affected markets.

2. Research Consensus

get_financial_news(topic=" forecast consensus  ", max_results=15)

Find current consensus forecast and range of analyst estimates for each event.

3. Plan Scenarios

For each event, pre-plan: Beat (direction + entry trigger), Miss (opposite direction), Meet (no trade).

4. Post-Release Entry

After the event, apply the wait period above. Then:

  • Observe initial reaction (1-5 min)
  • Wait for consolidation (per wait table)
  • Enter breakout of post-news consolidation
  • Use wider stops (volatility is elevated)
  • Target next key level

5. Event Clustering

When multiple events release in the same window: increase wait time by 50%, wait for ALL numbers before entering. If data points conflict, skip the trade.

6. Report to Orchestrator

Event details, consensus vs actual, deviation score, recommended action, conviction level.

Key Rules

  • NEVER enter during the first 60 seconds after release -- whipsaws dominate
  • NEVER hold positions through a high-impact event without a deliberate pre-news plan
  • NEVER trade full size on news -- reduce position size by 50-75% to account for volatility
  • When clustered events produce conflicting signals, skip the trade entirely
  • Always account for widened spreads around news releases

Related Skills

  • breakout-trading -- post-news consolidation breakouts follow breakout principles
  • gap-trading -- news events often produce gap opens

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.