agentleFS
efaslantasefaslantas/claude-finops/.claude/skills/macro-calendar/SKILL.md

macro-calendar

Skill2 starsChanged 5 months agoMITView on GitHub

Macro event calendar and portfolio impact pre-brief. Fetches upcoming central bank decisions, inflation releases, GDP data, earnings seasons, and geopolitical events. For each event, estimates the likely portfolio impact — which holdings are most exposed, what scenarios are priced in, and what to watch for.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Update this report weekly — stale macro calendars are worse than none.

    line 133

≈ “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

Macro Calendar

Trigger phrases

  • "Bu hafta hangi makro olaylar var?"
  • "Fed toplantısı portföyümü nasıl etkiler?"
  • "TCMB kararı öncesi portföy analizi"
  • "Upcoming macro events this month"
  • "What macro events should I watch for my portfolio?"
  • "ENFLASYON verisi ne zaman açıklanıyor?"

Phases

Phase 1 — Event calendar fetch

WebSearch for the next 4 weeks:

Central bank meetings:

  • TCMB (Türkiye Cumhuriyet Merkez Bankası) — next rate decision date + consensus
  • Federal Reserve (FOMC) — next meeting date + current fed funds futures pricing
  • ECB — next meeting + market expectations
  • Bank of England, Bank of Japan (if portfolio has EUR/GBP/JPY exposure)

Macro data releases:

  • Turkey: CPI (TÜFE), PPI (ÜFE), GDP, current account, unemployment
  • US: CPI, PPI, PCE, non-farm payrolls, GDP, retail sales, ISM
  • Eurozone: CPI flash, GDP, PMI
  • China: PMI, industrial production, retail sales (if EM exposure)

Earnings season:

  • For each equity holding: next earnings date (WebSearch: "[ticker] earnings date")
  • Analyst EPS consensus (WebSearch: "[ticker] earnings estimate")

Geopolitical / regulatory:

  • Upcoming elections (Turkey, US, EU member states)
  • Sanctions announcements
  • Trade policy events
  • BIST-specific: BIST index rebalancing dates, dividend season (April-June in Turkey)

Phase 2 — Event classification

For each event, classify:

EventDateMarket sensitivityPortfolio exposureSurprise potential
FOMC rate decisionHIGHUSD assets, NVDA, GOOGLMedium
Turkey CPIHIGHTRY assets, BISTMedium
NVDA earningsHIGHNVDA (direct)High
...

Sensitivity tiers:

  • 🔴 HIGH: event directly reprices holdings (earnings, rate decisions)
  • 🟡 MEDIUM: indirect macro impact (CPI, GDP on sentiment)
  • 🟢 LOW: background noise (PMI, minor data)

Phase 3 — Per-holding event exposure

Map each holding to its top-3 macro sensitivities:

HoldingTop event 1ImpactTop event 2Impact
NVDAFOMC (+100bps = -8% est.)Fed rate changeUS CPITech sentiment
TUPRSTCMB decisionTRY/USD rateBrent oilInput cost
GRAM ALTINReal ratesInversely correlatedUSD indexInverse
USD CASHTCMBTRY devaluationFOMCUSD strength

Phase 4 — Scenario analysis per event

For the 2-3 highest-impact upcoming events, build a mini scenario table:

Example: TCMB rate decision

ScenarioProbabilityTRY impactBIST impactPortfolio impact
Hold (expected)55%FlatFlat~0%
Cut 25bps (dovish surprise)30%-2%+2%+0.5% (net)
Hike 25bps (hawkish surprise)15%+3%-3%-0.8% (net)

Derive probabilities from: WebSearch (analyst surveys, market pricing) + recent TCMB rhetoric.

Example: NVDA earnings

ScenarioRevenue vs estEPS vs estExpected reaction
Beat & raise+5%+10%+8-12%
In-line0%0%±2%
Miss-5%-8%-10-15%

Phase 5 — Risk calendar heat map (text-based)

Week 1 (Jun 23-27):
  Mon:  🟢 EU PMI Flash
  Tue:  🔴 US Consumer Confidence
  Wed:  🔴 FOMC minutes
  Thu:  🟡 Turkey trade balance
  Fri:  🔴 US PCE inflation ← MOST IMPORTANT THIS WEEK

Week 2 (Jun 30 - Jul 4):
  Mon:  🟡 Turkey CPI (TÜFE)
  Tue:  🔴 NVDA earnings (after close)
  ...

Phase 6 — Pre-event positioning checklist

For each HIGH-sensitivity event, suggest:

  1. What to watch: the exact number/language that moves markets
  2. What's priced in: current market expectation (consensus)
  3. Tail risk: the scenario that's NOT priced in
  4. Portfolio action: hedge / reduce / hold / add on weakness
  5. Post-event plan: what price level confirms the move is real

Phase 7 — Output

Write output/macro-calendar-<YYYYMMDD>.md:

# Macro Calendar — Week of <date>

## High-Impact Events (next 4 weeks)
## Per-Holding Event Exposure
## Key Event Scenarios
## Risk Calendar Heat Map
## Pre-Event Positioning Checklist
## Watch-List: Key Levels to Monitor

Update this report weekly — stale macro calendars are worse than none.

Disclaimer: Market reactions to macro events are unpredictable. Consensus expectations are already priced in; only surprises move markets significantly. Not investment advice.

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.