← ClaudeAtlas

equity-research-reportlisted

Produce comprehensive, evidence-backed public-equity research reports with market, filing, fundamental, valuation, technical, risk, catalyst, scenario, and source analysis. Use when the user asks for "全面分析报告", "股票研报", "深度分析公司", "完整个股分析", "comprehensive equity report", or requests analysis of a stock, company, or equity thesis with current auditable data.
artherahq/skills · ★ 2 · Data & Documents · score 66
Install: claude install-skill artherahq/skills
# Equity Research Report Build a report through an explicit research workflow. Treat an attractive narrative as insufficient unless the evidence and completion gates pass. ## Workflow 1. Resolve the instrument, exchange, currency, locale, and report `as_of` timestamp. Stop if the identity is ambiguous. 2. Publish a concise execution plan containing data collection, specialist analyses, synthesis, critique, and validation. Do not expose private chain-of-thought. 3. Collect one normalized market-data bundle first. Reuse it across specialists instead of fetching the same quote independently. 4. Collect point-in-time evidence for market data, financial statements or filings, valuation inputs, risk history, and current catalysts. Record source, timestamp, and limitations for every item. 5. Run independent technical, fundamental, valuation, risk, and catalyst analyses. Use deterministic calculations for indicators, multiples, returns, volatility, drawdown, and scenarios. 6. Retry only missing or failed evidence, at most twice per gap. Fall back to deterministic analysis when an LLM fails but verified inputs remain available. Mark fallback output `degraded` and cap its confidence. 7. Run a critic pass. Check unit scale, stale data, contradictory prices, unsupported targets, missing filings, circular citations, undeclared primary-source substitution, unreconciled cross-source contradictions, and conclusions that exceed the evidence. 8. Build the report and its machine-readable man