skills/market-news-analyst/SKILL.md
This skill should be used when analyzing recent market-moving news events and their impact on equity markets and commodities. Use this skill when the user requests analysis of major financial news from the past 10 days, wants to understand market reactions to monetary policy decisions (FOMC, ECB, BOJ), needs assessment of geopolitical events' impact on commodities, or requires comprehensive review of earnings announcements from mega-cap stocks. The skill automatically collects news using WebSearch/WebFetch tools and produces impact-ranked analysis reports. All analysis thinking and output are conducted in English.
npx skillsauth add kavi-lin/stock market-news-analystInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Analyse 10-day market-moving news → impact-ranked English Markdown report. All thinking + output in English. See README.md for principles, pitfalls, and pedagogy.
WebSearch + WebFetch available. No API keys.
User asks for: recent market news analysis, FOMC / ECB / BOJ decision impact, mega-cap earnings review, geopolitical → commodity reactions, or "past 10 days of market-moving events".
Execute parallel searches across these categories:
| Category | Query examples | |---|---| | Monetary policy | "FOMC meeting past 10 days", "Federal Reserve interest rate", "ECB policy decision", "Bank of Japan" | | Inflation / econ data | "CPI inflation [month]", "NFP jobs report", "GDP data", "PPI producer prices" | | Mega-cap earnings | "Apple earnings [quarter]", "MSFT earnings", "NVDA earnings", "AMZN", "TSLA", "META", "GOOGL" | | Geopolitics | "Middle East conflict oil", "Ukraine war", "US China tensions", "tariffs" | | Commodities | "oil prices past week", "gold prices", "OPEC meeting", "natural gas", "copper" | | Corporate | "major M&A", "bank earnings", "bankruptcy", "credit rating downgrade" |
Source priority (highest → lowest):
Full tier list: references/trusted_news_sources.md.
Filter: drop stock-specific small-caps, minor product updates, routine filings. Only keep news with clear market impact (price move, volume spike).
Capture per item: date+time, event type, source tier, initial reaction.
Always load:
references/market_event_patterns.mdreferences/trusted_news_sources.mdConditionally load (based on news types collected):
| News type | Load | Focus sections | |---|---|---| | Monetary policy | market_event_patterns.md | Central Bank Monetary Policy Events | | Geopolitical | geopolitical_commodity_correlations.md | Energy, Precious Metals, matching region | | Mega-cap earnings | corporate_news_impact.md | Specific company sections, sector contagion | | Commodity news | geopolitical_commodity_correlations.md | Oil / Gold / Copper / etc. |
Use references to: predict expected reaction, identify anomalies (reaction differed from historical pattern), assess typical vs outsized magnitude, check if contagion spread as expected.
Score each news item across 3 dimensions.
1. Asset Price Impact (primary, 1-10 points):
Equity — index level (S&P 500 / Nasdaq / Dow):
Equity — sector ETF: Severe ±5%+ / Major ±3-5% / Moderate ±1-3% Equity — mega-cap stock: Severe ±10%+ / Major ±5-10% / Moderate ±2-5%
Commodities:
Bonds — 10Y Treasury yield: Severe ±20bps+ / Major ±10-20bps / Moderate ±5-10bps FX — DXY: Severe ±1.5%+ / Major ±0.75-1.5% / Moderate ±0.3-0.75%
2. Breadth Multiplier:
3. Forward-Looking Modifier:
Formula: Impact Score = (Price Impact × Breadth Multiplier) × (1 + Forward Modifier)
Examples:
Rank all items by score desc → determines report ordering.
For each item with score > 5, track reaction across assets:
Equities: index perf (S&P / Nasdaq / Dow / Russell 2000), sector rotation, mega-cap moves, Growth vs Value, Large vs Small. Fixed income: 2Y / 10Y / 30Y yields, curve shape, credit spreads (IG, HY), TIPS breakevens. Commodities: energy (WTI/Brent/NG), precious metals, base metals, ags (if relevant). FX: DXY, EUR/USD, USD/JPY, GBP/USD, EM currencies, safe havens (JPY, CHF). Derivatives: VIX, put/call ratio, unusual options volume, futures positioning.
Pattern comparison vs knowledge base:
Anomaly flags: market shrugged off market-moving news / overreaction to minor news / contagion failed to spread / safe havens broke correlations.
Sentiment indicators: risk-on vs risk-off regime, crowded-trade unwinds, follow-through vs reversal.
Multi-event interaction:
Geopolitical ↔ commodity correlation (use geopolitical_commodity_correlations.md):
Transmission channels:
Output English Markdown report. Section skeleton (fill all sections, skip only if N/A):
# Market News Analysis Report — [Date Range]
## Executive Summary
[3-4 sentences: period, event count, dominant theme/regime, top 1-2 highest-impact events]
## Market Impact Rankings
| Rank | Event | Date | Impact Score | Assets Affected | Reaction |
## Detailed Event Analysis
### [Rank]. [Event Name] (Impact Score: [X])
**Event Date** / **Event Type** / **Source**
#### Event Summary
[3-4 sentences: what happened, context (expected vs surprise), forward guidance]
#### Market Reaction
**Immediate (day-of)**:
- Equities: S&P [±%], NDQ [±%], sector rotation
- Bonds: 10Y yield [change], credit spreads
- Commodities: Oil/Gold/Copper [±%] (if relevant)
- FX: USD [±%], relevant pairs
- Volatility: VIX level/change
**Follow-through**: sustained / reversed / consolidated
**Pattern comparison**: expected vs actual (consistent / amplified / dampened / inverse) + explanation
#### Impact Assessment Detail
- Asset Price Impact: [severity] — justification
- Breadth: [systemic/cross-asset/sector/stock-specific] — affected markets
- Forward Significance: [regime change / trend confirm / isolated / contrary]
- **Score**: (Price × Breadth) × (1 + Forward) = [total]
#### Sector-Specific Impacts (if relevant)
[Sector: impact + reason, e.g. Tech −3% rate sensitivity, Energy +5% oil spillover]
#### Geopolitical-Commodity Correlation (geopolitical events only)
Commodity price move / supply-demand mechanism / historical precedent / expected duration
[Repeat per event in rank order]
## Thematic Synthesis
### Dominant Market Narrative
[Overarching theme across 10-day window]
### Interconnected Events
[How events related/compounded, sequential causation]
### Market Regime Assessment
Risk appetite: [Risk-On / Risk-Off / Mixed]
Evidence: sector performance, safe-haven flows, credit spreads, VIX
Sector rotation: Growth vs Value, Cyclicals vs Defensives, out/underperformers
### Anomalies and Surprises
[Unexpected reactions + likely explanation]
## Commodity Market Deep Dive
### Energy: WTI/Brent price level, % change, drivers; Natural Gas if significant
### Precious Metals: Gold/Silver level, drivers (rates, safe haven, central banks)
### Base Metals: Copper/Aluminum if significant
### Agricultural: if relevant
## Forward-Looking Implications
### Market Positioning Insights
[What this analysis suggests for positioning: overweight/underweight, defensive posture]
### Upcoming Catalysts
[Near-term events that may drive markets — next FOMC, CPI, earnings clusters]
### Risk Scenarios
[Downside + upside scenarios with probability-weighted impacts]
## Data Sources and Methodology
- News sources consulted: [list]
- Analysis period: [exact date range]
- Market data: [data sources used]
- Knowledge base references loaded: [which references]
Tone: rigorous, quantified, English. Avoid vague words ("significant", "large") — always use numbers (%, bps).
market_event_patterns.md — central bank decisions, inflation/jobs data, geopolitical events, earnings, credit events, commodity events, recession indicators, historical case studies, pattern-recognition frameworkgeopolitical_commodity_correlations.md — energy/precious metals/base metals/ags correlations with geopolitical conflicts, rare earths, regional frameworks (Middle East / Russia-Europe / Asia-Pacific / LatAm), time-horizon guidancecorporate_news_impact.md — Magnificent 7, financial mega-caps, healthcare mega-caps, energy mega-caps, consumer staples, industrial mega-caps, earnings/product launch/M&A frameworks, sector contagiontrusted_news_sources.md — tier 1-4 source map, search strategies, red-flag sources to avoiddevelopment
# earnings-analyst — 個股財報深度分析 > **Trigger**: `財報 [TICKER]` > **Version**: V1.0 > **Data Source**: FMP HTTP REST(`$FMP_API_KEY`) ## 目的 針對單一個股產出**深度財報分析報告**(逐季趨勢、品質指標、估值、分析師共識),涵蓋 sector V1.4 與 `分析 [TICKER]` 既有 protocol **沒有**的「財報層級」深潛內容。 ## 與既有 skill 的差異 | Skill | 重點 | 觸發 | |---|---|---| | `us-stock-analysis` | 估值/技術/情緒 snapshot(yfinance + FMP partial) | Phase 2 fundamentals lane | | `earnings-valuation-forecaster` | 12M 目標價 3×3 敏感度 | ad-hoc / earnings 前 14 天 | | `earnings-trade-analyzer` |
testing
Daily Top N hot themes × Top M short-term movers per theme. Combines theme-detector heat scoring (medium-term) with short-term-target predictions (1d/5d/15d) into a "Tactical Opportunity Radar" recommendation log. Tags concentration WARNING when ≥2 picks share theme. Records FRED + market regime snapshot at recommendation time for future backtest cross-tabs. Standalone — not auto-wired into investment_protocol. Use for daily watchlist refresh / Dashboard推薦面板feed / batch screening across hot themes.
testing
Short-term (1d / 5d / 15d) directional projection for a US stock — "Tactical Opportunity Radar". Outputs target range + confidence breakdown + benchmark-relative alpha + trading meta (stop / position size hint / exit trigger). Each horizon uses independent weights from config/weights.yaml. Refuses to project when source data is stale (returns insufficient_data with reasons). Hard-clamped to prevent cold-start absurd predictions. Use when caller wants short-term directional bias on a specific ticker, NOT for long-term valuation (use earnings-valuation-forecaster for 12-month). Standalone — not auto-wired into investment_protocol.
tools
Shared Finnhub API client used by other skills. Provides rate-limited (60/min), cached, retry-aware access to 17 Finnhub endpoints covering quotes, OHLCV, fundamentals, earnings calendar, earnings surprises, insider transactions, recommendation history, price targets, upgrades/downgrades, dividends, splits, IPOs, and SEC filings. Also exports adapters that normalize Finnhub raw responses into FMP-compatible shapes so that downstream code can swap providers without changing call sites. Use when another skill needs Finnhub data or when building a unified provider layer.