_old-earnings-orchestrator
Master orchestrator for batch earnings analysis. Processes all 8-Ks for a company chronologically, running prediction→attribution loop with accuracy tracking.
npx skills add majiayu000/claude-skill-registry --skill old-earnings-orchestrator-faisalanjum-eventtrader --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Earnings Orchestrator **Goal**: Process all 8-K earnings filings for a company chronologically, building a closed-loop prediction→attribution system with accuracy feedback. **Thinking**: ALWAYS use `ultrathink` for maximum reasoning depth. **Input**: Company ticker (e.g., "GBX", "AAPL") --- ## Architecture ``` Master Orchestrator (this skill) │ ├─→ Query Neo4j for all 8-Ks with Item 2.02 │ └─→ For each filing chronologically: │ ├─→ First filing: /earnings-attribution only │ └─→ Subsequent filings: │ ├─→ /earnings-prediction (predict before seeing outcome) │ └─→ /earnings-attribution (verify & learn) ``` --- ## Workflow Use TodoWrite to track progress through all filings. ### Step 1: Query 8-K Universe Query Neo4j for all 8-Ks with Item 2.02 (earnings) for the ticker: ```cypher MATCH (r:Report)-[pf:PRIMARY_FILER]->(c:Company) WHERE c.ticker = $ticker AND r.formType = '8-K' AND any(item IN r.items WHERE item CONTAINS 'Item 2.02') AND pf.daily_stock IS NOT NULL RETURN r.accessionNo AS accession_no, c.ticker AS ticker, c.name AS company_name, r.created AS filing_datetime, pf.daily_stock AS daily_return, pf.daily_macro AS macro_adj_return, r.items AS items ORDER BY r.created ASC ``` E
- Architecture
- Workflow
- Step 1: Query 8-K Universe
- Step 2: Check Processing State
- Step 3: Process Each Filing
- Step 4: Update Tracking
- Accuracy Tracking
- Direction Accuracy
- Magnitude Accuracy
- Running Metrics
- Resume Logic
- Output Files
- Run Summary Format
- Invocation Examples
What does the _old-earnings-orchestrator skill do?
Master orchestrator for batch earnings analysis. Processes all 8-Ks for a company chronologically, running prediction→attribution loop with accuracy tracking.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill old-earnings-orchestrator-faisalanjum-eventtrader --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.