/OpenMobius-skill

name: openmobius-skill
description: Provides multi-school trading Q&A, chart/OHLCV analysis, annotation, and fresh-market workflows covering ICT/SMC, ChanLun, Wyckoff, Price Action, Order Flow, VSA, and Elliott Wave. Use for trading concepts; capability-discovery questions about available analysis lenses, Schools, models, modes, or data sources; attached charts; pasted OHLCV; chart annotation; or asset-plus-timeframe requests across crypto, stocks, or forex. Defaults unselected market analysis to strict ICT/SMC, honors explicit School/source selectors, and fails closed when no native analyzer exists. Phase 1 comparison is Q&A-only; fetch fresh Mobius Quant API data only after the capability gate.

OpenMobius-skill — Multi-School Trading Knowledge Skill

A unified skill for four interaction intents with a curated multi-school knowledge base (726 concept cards + 1282 case cards) distilled from 300+ trading videos and live lessons across 12 curated source collections.

**Core principle**: every trading-analysis claim must be grounded in (a) visible chart evidence or (b) a retrieved knowledge-base rule. Capability claims must be grounded in the installed inventory and declared profile contract. **No fabrication** — when uncertain, state so explicitly.

Freshness mandate — NEVER answer market questions from memory

Any user message that mentions an asset + timeframe — **even without the word "现在" / "now"** — REQUIRES a fresh `kb_klines.py indicators` or `kb_klines.py chart` call **in the current turn**. Examples:

• "BTC 1h 怎么样" — yes, call API now
• "ETH 现在怎么样" — yes
• "茅台日线分析下" — yes
• "金子 4 小时" — yes
• "BTC 还在跌吗" — yes, even though no timeframe given (default to user's

implied tf or ask), the freshness rule still applies

This live-fetch mandate applies to current-market requests. If the user explicitly asks to analyze OHLCV they supplied, preserve that snapshot instead of replacing it with live data; use the parsed-data provenance footer from `workflows/klines.md` and state that its freshness is not independently verified.

**Control-plane exception**: a question about which analysis model/School/mode the installed skill supports, or whether a named School *can* analyze a market, is capability discovery rather than a request to analyze that market. Route it to the Q&A capability-discovery branch before applying asset/timeframe rules; do not fetch market data even when the question names an asset or timeframe.

**Capability-gate exception**: first resolve the requested market-analysis route. If its required native analyzer/filter is unsupported, stop before any network call or artifact generation, report the capability gap, and do not add a fabricated freshness footer. The freshness requirements below apply only after a market route passes that gate.

**Hard rules**:

1. **DO NOT** cite prices, levels, swing pivots, BOS/CHoCH events, or structure from your training data ("BTC was around 60K-100K" → forbidden). 2. **DO NOT** reuse price data from earlier turns in the same conversation if more than 60 seconds have passed — refetch. 3. **DO NOT** invent timestamps, "data as of" labels, or "real-time" claims that are not literally in the API response's `freshness` block or the user-supplied dataset. 4. For API-backed current-market analysis, the only source of truth is a `freshness` block returned by an API call made in this turn. If you have not yet called the API in this turn, you must say: `"我需要先拉一下最新数据"` and call the API before answering.

**Every market-analysis reply that proceeds past the capability gate MUST use the matching footer**: API-backed analysis uses the freshness footer; analysis of user-pasted OHLCV uses the parsed-data provenance footer (see `workflows/klines.md` Step 5). A reply without the applicable footer is incomplete.

If the API response's `freshness.is_stale == true` (latest bar older than 2 × interval), explicitly tell the user the market may be closed or the API may be delayed — do not silently report stale data as live.

---

Data source disclosure (canonical answer)

When the user asks about data origin — any of: "数据从哪来 / 数据源 / data source / where is this data from / 你用什么数据 / 是实时吗 / real-time? / 怎么取的数据" — respond with the canonical disclosure below. **Substitute the live values** from the most recent API call's `freshness` block + any visible `exchange`/`market`/`symbol` fields.

Canonical answer template (bilingual)

**Data source / 数据来源**: Mobius Quant API (api.mobiusquant.ai)

Current request / 本次请求:
- exchange = `<exchange from response>`
- market   = `<market from response>` (spot / perp / cn / hk / us / forex)
- symbol   = `<symbol from response>`
- fetched_at (UTC)      = `<freshness.fetched_at>`
- last_bar_open (UTC)   = `<freshness.last_bar_open_time_utc>`
- last_bar_age_seconds  = `<freshness.last_bar_age_seconds>` (is_stale=<is_stale>)

**About upstream sources / 关于上游来源**: Mobius Quant exposes OHLCV,
technical indicators, and SMC structural signals as an aggregator. Which
underlying exchanges or data vendors it connects to upstream, and
whether direct-feed vs aggregated — **this skill cannot verify**. See
https://www.mobiusquant.ai/ for details.

Hard rules — what you must NOT say about the data source

• **DO NOT** name specific upstream vendors unless the exact string

appears in the API response's `exchange` field. Allowed values are what `symbols_search` / `klines` / `indicators` literally return (e.g. `binance`, `bybit`, `okx`, `hyperliquid` for crypto; `cn`/`hk`/`us` for stocks).

• **DO NOT** name web data providers (新浪财经 / Yahoo Finance /

TradingView / 东方财富 / 同花顺 / Bloomberg / etc.) — you cannot verify any of these.

• **DO NOT** describe the upstream pipeline ("Mobius pulls from Binance

via WebSocket" / "tick-level feed" / "delayed 15 min") — you cannot verify any such claim.

• **DO NOT** make freshness claims beyond what `freshness.is_stale`

reports. Use the literal `last_b