openmobius-skill
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, commodities (gold/silver), 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.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/mobiusquant--openmobius-skill)HTML
<a href="/listings/mobiusquant--openmobius-skill"><img src="/api/listings/mobiusquant--openmobius-skill/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
OPENMOBIUS_SRC="$(mktemp -d "${TMPDIR:-/tmp}/openmobius-src.XXXXXX")"
git clone https://github.com/MobiusQuant/OpenMobius-skill.git "$OPENMOBIUS_SRC"
cd "$OPENMOBIUS_SRC"
python3 install.py --platform claude-code # or codex / agy / openclaw / hermes / cursor
# On Linux/macOS, `all` installs all six local-path hosts. WorkBuddy, Grok Bot, and Muse use compact ZIP packages.
cd "${TMPDIR:-/tmp}"
rm -rf -- "$OPENMOBIUS_SRC" # ✓ exact mktemp directory onlyOn Windows, clone into a writable directory and run `py -3 install.py --platform claude-code` (or use `.\install.ps1`).
The installer copies source files into `~/.claude/skills/openmobius-skill/` (or your chosen platform's skills dir), then in that directory:
1. Creates `.venv/` and installs dependencies 2. Downloads Playwright chromium (~280 MB, into your OS's user-global cache) 3. Downloads the pinned `nomic-embed-text-v1.5` weights (~547 MB / 522 MiB, into your HuggingFace cache) 4. Loads bundled canonical vectors and the verified release seed for independent School/evidence vectors, then builds and verifies all three collections. Only locally changed or missing documents are embedded and cached. 5. Generates the platform-specific `SKILL.md` 6. Runs a health check
Each installer-managed local copy is **self-contained**: it owns its own `.venv` and `_index`. The clone is just a one-shot source bundle.
**First run**: dependency/model downloads plus seed-accelerated index build · **Subsequent runs**: unchanged records use the release seed or local embedding cache
After install, try capability discovery plus the default, scoped, and composed routes directly:
# Default: strict ICT/SMC "What is Liquidity Sweep?" "How is ETH 4h looking?" # Discover the installed capabilities (no market-data request) "What analysis models can I use?" # Select an exact School or source "Explain 中枢 using ChanLun only" "Explain Order Block using Wuyuan's SMC material only" # Compose or compare "Compare ICT and ChanLun definitions of market structure" "Use SMC as primary and Wuyuan as a reference to analyze BTC 1h"
Other Schools can scope knowledge Q&A when attributable material exists. Current-market analysis additionally requires a native analyzer; unsupported routes stop before market-data or chart work. Capability-discovery questions read the installed registry dynamically and report native market profiles, Q&A-only lenses, knowledge categories, and the available composition modes as separate concepts; they do not fetch market data or describe a category as an analysis model.
> **Prerequisites**: Python 3.10+. See [INSTALL.md](./INSTALL.md) for details.
---
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 499 lines
- ---
- 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, commodities (gold/silver), 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 / futures / 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`, `gate`, `coinbase`, `hyperliquid`,
- `composite` for crypto; `stock` for `cn`/`hk`/`us`; `commodity` for
- `XAUUSD`/`XAUF`/`XAGF`; `forex` for FX spot).
- - **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_bar_age_seconds` number.
- ### What you CAN say
- - The API endpoint (`api.mobiusquant.ai`)
- - The exact JSON fields returned (`exchange` / `market` / `symbol` /
- `count` / `current_price` / `freshness.*`)
- - That the SMC structural indicator is computed server-side by Mobius
- - A pointer to `https://www.mobiusquant.ai/` for upstream details
- ---
- ## Host-neutral runtime and artifact paths
- Resolve these placeholders for the current host before running a workflow.
- They are documentation tokens, not literal paths or shell variables:
- - `<SKILL_ROOT>` — the directory containing the loaded `SKILL.md`. Run all
- commands with this directory as the working directory so relative `scripts/`
- paths resolve without depending on the user's current directory.
- - `<PYTHON>` — the Python executable selected for this installed skill. Resolve
- it from the platform/installer-managed runtime; Windows and POSIX executable
- paths differ, and a managed host may expose its own runner. Do not assume
- `python` or `python3` is available on `PATH`.
- - `<TEMP_DIR>` — a writable, task-specific temporary directory created through
- the current host's temporary-directory facility. Do not assume a particular
- POSIX or Windows system path exists.
- - `<USER_OUTPUT_DIR>` — a writable directory selected by the user or exposed by
- the host for durable artifacts that must be returned. Do not use a repository
- checkout or developer-machine path as the implicit output location.
- - `<INPUT_IMAGE>` — the host-resolved path to the user's attached chart.
- Never execute the angle-bracket placeholders literally. Quote each resolved
- path according to the current command runner when it contains spaces. Command
- blocks use logical argument lists and avoid shell-only pipes, heredocs, and
- continuation syntax. Create JSON/text inputs with the host's file-writing tool
- or a JSON serializer, then pass the resulting file path to the script.
- For WorkBuddy packaging compatibility, a command line that begins with
- `kb_retrieve.py` is launcher-neutral shorthand only. Before execution it
- **must** be expanded to `<PYTHON> scripts/kb_retrieve.py`; never assume
- `kb_retrieve.py` is on `PATH`.
- ## Always retrieve from the knowledge base first
- The knowledge base contains rule-based identification criteria and documented pitfalls that generic training data lacks. Resolve the route and confirm its capabilities, then **retrieve within that route before synthesizing** — don't answer trading questions from memory alone and don't widen a selected school/source boundary silently.
- The semantic-card retrieval mandate applies to trading-knowledge answers, not
- to control-plane capability discovery. Capability discovery inspects the
- installed School inventory and declared profile contract without running a
- normal query/top-K search; follow the special case in `workflows/qna.md`.
- ## Analysis profile orchestration
- First detect capability-discovery questions about the installed skill's
- available models/profiles, lenses, Schools, modes, supported intents, or a
- named School's market-analysis support. They remain `intent=qna`, but take
- priority over the default `strict` ICT/SMC route and any asset/timeframe or
- chart routing. Read both `workflows/qna.md` and
- `workflows/analysis_profiles.md`, inspect the installed inventory with
- `kb_retrieve.py --layer school --list-schools --format json` (expanded through
- the launcher-neutral rule above),
- then answer immediately from that inventory and the declared profile contract.
- This is an intentionally bounded, single-agent control-plane operation: do not
- delegate to a subagent/background task, recursively invoke this skill, run Git,
- scan source code/cards/manifests, or verify analyzer implementations. Do not
- construct or inherit an analytical School route for this branch, and stop after
- the capability response.
- For all normal analysis and knowledge requests, resolve a route before
- retrieval, indicator calls, analysis, or drawing:
- `route = {intent, mode, primary_lens, secondary_lenses, schools, sources, capabilities}`
- - `intent` must be exactly one of `qna`, `analyze`, `annotate`, or `klines`.
- Do not emit aliases such as `kline_analysis`.
- - `capabilities` must always be an object, never a list or string. Use the
- canonical fields and values defined in `workflows/analysis_profiles.md`.
- - For the plain default route, set `exact_primary_school_filter=true`,
- `source_filter=not_requested`, `intent_supported=true`, and `reason=null`;
- set `native_market_analyzer=not_required` for Q&A or `supported` for a market
- intent. This default does not require loading the profile reference.
- - `lens` (also called a profile) is an analytical methodology such as
- `ict_smc` or `chanlun`; `source` is a corpus/teacher collection such as
- `Teach-Wuyuan`. A source does not automatically select a lens.
- - With **no explicit lens, school, source, or composition selector**, use
- `mode=strict`, `primary_lens=ict_smc`, and `schools=[ICT, SMC]`; retrieve
- with `--layer school --schools ICT SMC`.
- - A single explicit selector is strict by default. In Phase 1, `compare` is
- supported for Q&A only; market-analysis, chart, and annotation comparisons
- fail closed before network or artifact work. `augment` gives one primary lens
- authority over bias and trade levels while secondary lenses only confirm,
- challenge, or add risk context.
- - School-scoped grounding uses `school_knowledge_v2`, which omits
- cross-School fused rules that cannot be attributed. Any requested source
- uses `source_evidence_v2` with `--layer evidence --sources ...`; combine it
- with `--schools ...` for an exact intersection. Never use the fused
- canonical layer to claim strict School/source isolation.
- - School/evidence queries use hard-filtered hybrid retrieval by default
- (BM25 + semantic RRF over independently embedded scoped documents). Keep
- `--search-mode auto` unless diagnosing retrieval; exact terms/aliases stay
- first and the hard School/source boundary is never widened.
- - **Never silently fall back** from an explicit lens/source to `ict_smc` or to
- an unfiltered search. Check `capabilities` before doing work and report an
- unsupported or empty route plainly.
- - ChanLun knowledge Q&A is supported, but this skill currently has no native
- ChanLun market-structure analyzer or overlay. Never present SMC indicator
- output as ChanLun analysis.
- Read [workflows/analysis_profiles.md](workflows/analysis_profiles.md) whenever
- the user names a lens/school/source, requests comparison or augmentation,
- excludes a profile, or the selected capability is uncertain. Plain default
- `ict_smc` requests can proceed directly to the intent workflow below.
- ## Market-analysis output format is mandatory
- The Analyze and Kline workflows end in a synthesis step with mandatory `##`
- section headings. Those headings must appear verbatim and in the specified
- order. Q&A and Annotate use the output structures defined in their own workflow
- documents. A capability-gap response that stops before analysis is also exempt
- from the market-analysis template and freshness footer.
- ## Scenario Router
- Pick the right sub-workflow based on the user's input. Each workflow has detailed steps in its own document:
- | User input | Workflow | Document to read |
- |---|---|---|
- | Installed-skill capability question ("当前有哪些分析模型", "which Schools are available", "缠论能分析 BTC 1h 吗") — even with an asset/timeframe or chart reference | **Q&A capability discovery** | `workflows/qna.md` + `workflows/analysis_profiles.md` |
- | Concept question, **no chart, no data, no asset name** ("什么是 FVG", "how to identify OB", "止损放哪里") | **Q&A** | `workflows/qna.md` |
- | **Chart attached** + any question about it ("分析", "看一下", "走势", "where to enter", "what's happening") | **Analyze** (auto-fetches real OHLCV + annotation) | `workflows/analyze.md` |
- | User explicitly asks to **draw/annotate** an image, OR follows up after analysis with "把这个标在图上" | **Annotate** | `workflows/annotate.md` |
- | User pastes **OHLCV data** OR mentions **asset + timeframe by name** without chart ("BTC 1h 怎么样" / pastes CSV / "茅台日线") | **Kline analysis** (auto-generates a fresh chart PNG) | `workflows/klines.md` |
- > **Chart output is part of the standard reply** for the **Analyze** and
- > **Kline analysis** workflows — render a PNG and include its path in the
- > output. Skip the chart step ONLY when the user explicitly opts out
- > ("只要文字" / "skip chart" / "no image" / "不用画图"). For
- > user-pasted OHLCV, follow the Path B exception in `workflows/klines.md` and
- > never fetch a different live series merely to satisfy chart output.
- **How to route**:
- 1. Detect capability discovery first; if matched, follow its Q&A control-plane
- special case and stop without applying an analytical route
- 2. Otherwise resolve the route above; load `analysis_profiles.md` when its
- trigger applies
- 3. Identify the user's intent in the scenario table
- 4. Use the `Read` tool to load the relevant workflow document (relative to this SKILL.md: `workflows/<name>.md`)
- 5. Follow that workflow while preserving the route's lens/source boundaries
- > **Important — Analyze workflow now auto-fetches data**: If a chart is attached AND the asset/timeframe is identifiable from the chart, `analyze.md` will fetch real OHLCV from Mobius API to **complement visual analysis with precise prices**. This is on by default; user can opt out by saying "只看图不拉数据" / "skip data fetch".
- > **Note**: The **Analyze** workflow already auto-generates an annotated image as its final step. You do NOT need to separately invoke Annotate after Analyze unless the user wants to re-render with different parameters (different colors, new bbox, JSON-only output, etc.).
- ## Two chart generation paths
- When the user wants a visual chart, choose the right tool:
- | Situation | Tool | Output |
- |---|---|---|
- | User uploaded their own chart image; wants markup ON that image | `scripts/kb_draw_annotation.py` (PIL) | Annotated copy of original image |
- | No chart image, OR user wants a clean new chart | `scripts/kb_klines.py chart` + `render` | Fresh TradingView-grade chart: K-lines + structural overlays (FVG/OB rectangles, sweep lines, swing markers, trade-setup lines) |
- For path #2, the typical pipeline is:
- ```text
- # 1. Pull K-lines + auto-filled SMC structural overlay for an ict_smc route
- <PYTHON> scripts/kb_klines.py chart --query "BTC" --interval 1h --limit 200 --output <TEMP_DIR>/chart.json
- # 2. Optionally create a separate trade-setup JSON containing only entry/SL/
- # target hlines; do not duplicate the structural items already auto-filled.
- # 3. Render PNG (add --trade-setup <TEMP_DIR>/setup.json only when one exists)
- <PYTHON> scripts/kb_klines.py render --input <TEMP_DIR>/chart.json --output <USER_OUTPUT_DIR>/chart.png --theme dark --width 1400 --height 900
- ```
- ## Indicator fetching
- ### Default `ict_smc` profile: SMC structural indicator
- For a market-analysis branch whose lens is `ict_smc`, fetch the **SMC
- structural indicator** first. A request with no explicit selector creates this
- default branch. Do not fetch or use SMC as structural evidence for a strict
- non-`ict_smc` branch; in `augment`, keep its evidence within the labelled
- secondary role assigned to that branch.
- ```text
- <PYTHON> scripts/kb_klines.py indicators --query "BTC" --interval 1h --limit 200 --format compact
- ```
- No `--inds` flag means SMC by default. The response covers, in one call:
- - **Per-bar state**: swing/internal trend bias, active swing & internal
- pivots, trailing extremes (running max/min since last pivot), the SMC
- indicator's internal volatility baseline (`smc_atr200`)
- - **`objects` sidecar**: structural events with full geometry, ready to
- drop straight into chart overlays
- - `swing_pivots` (HH/HL/LH/LL), `swing_structures` & `internal_structures`
- (BOS / CHoCH events with `pivot_time` + `confirm_time` + `bias`)
- - `equal_highs` / `equal_lows` (liquidity-pool levels)
- - `order_blocks_swing` / `order_blocks_internal` (each with
- `top`/`bottom`/`anchor_time`/`bias`/`status: active|mitigated`)
- - `fair_value_gaps` (same field shape as OBs)
- - `trailing_extremes`: `{top, top_label, bottom, bottom_label}` where
- the labels are one of `Strong High` / `Strong Low` / `Weak High` /
- `Weak Low`
- - `premium_zone` / `equilibrium_zone` / `discount_zone`
- (`{top, bottom}` price bands at the swing range's top/middle/bottom)
- - `alerts_last_bar`: dictionary of booleans flagging events that fired
- on the most recent candle (e.g. `swing_bullish_choch`, `equal_highs`,
- `bullish_fair_value_gap`)
- ### SMC field semantics (use these to structure your analysis)
- Order of consultation for the 5-section output:
- 1. **Trend bias**: compare `smc_swing_trend` vs `smc_internal_trend`.
- Same sign = strong trend; opposite sign = potential reversal or range.
- 2. **Most recent structural event** (look at last entry of
- `swing_structures` / `internal_structures`): is it `kind: BOS`
- (trend continuation) or `kind: CHoCH` (trend reversal)? **CHoCH has
- higher priority** than BOS as a forward signal.
- 3. **Trailing extremes labels**: `Strong High` + `Weak Low` together =
- confirmed bearish structure (the high holds, the low is breakable);
- `Strong Low` + `Weak High` = confirmed bullish. A break of a `Strong`
- pivot is the structural confirmation of a reversal.
- 4. **Active Order Blocks**: filter `objects.order_blocks_*` by
- `status: active`. Bull OBs below price = support candidates. Bear OBs
- above price = resistance candidates. Closer to current price = more
- relevant.
- 5. **Active Fair Value Gaps** (same filter): three-bar imbalance regions
- that price tends to revisit / fill.
- 6. **Equal highs / equal lows**: stops-cluster liquidity that Smart
- Money tends to sweep before reversing.
- 7. **Premium / equilibrium / discount placement**: which zone is the
- current price in? Bull-favored entries are in `discount`; short-
- favored entries are in `premium`; `equilibrium` is wait-and-see.
- ### Caveats (always disclose when an SMC branch is used)
- - Swing pivots are confirmed only `swing_size` bars after they form
- (typically ~50 bars); recent pivots may still adjust.
- - Order Blocks are reverse-engineered from later price action; a freshly
- formed OB may be revised by subsequent bars.
- - FVG thresholds fire more frequently in low-volatility regimes — treat
- low-vol FVG counts with caution.
- - All events are structural signals, not entry triggers. They complement
- but do not replace risk management.
- ### Cross-referencing the ICT/SMC knowledge base
- Each SMC field maps directly to a KB concept card. After identifying the
- structural pattern, retrieve the corresponding card for rule citations:
- | SMC field / event | KB concept |
- |---|---|
- | `swing_structures` with `kind: BOS` | `break_of_structure` |
- | `swing_structures` with `kind: CHoCH` | `change_of_character` |
- | `order_blocks_*` | `order_block` |
- | `fair_value_gaps` | `fair_value_gap` |
- | `equal_highs` / `equal_lows` | `equal_highs` / `equal_lows` |
- | `premium_zone` / `discount_zone` / `equilibrium_zone` | `premium_and_discount`, `equilibrium` |
- | `trailing_extremes` with Strong/Weak labels | `strong_and_weak_highs_and_lows`, `protected_high_low` |
- | `smc_atr200`, `smc_volatility`, `high_vol_bar` | `displacement` |
- ### When the user explicitly names a specific indicator
- If — and **only if** — the user's message contains a specific indicator
- name (whatever the abbreviation), pass that name through as `--inds`:
- ```text
- <PYTHON> scripts/kb_klines.py indicators --query "BTC" --interval 1h --inds "<exact-name-user-said>" --format compact
- ```
- For multi-param indicators use the compact form `name:p1:p2` (e.g. one
- positional param after the name); the server interprets the rest.
- **Strict rules**:
- 1. **Do not pre-emptively fetch any indicator the user did not name.**
- Do not "complement the SMC reading" with another indicator on your
- own initiative.
- 2. **Do not suggest specific indicator names to the user.** If the user
- did not ask for an indicator, do not mention any. Within an `ict_smc`
- branch, the SMC indicator is sufficient as the structural ground truth;
- it is not a substitute for another lens's native analyzer.
- 3. **Text-only**: indicator output is reported in prose / tables; chart
- rendering stays structure-only (FVG/OB/Sweep overlays from the SMC
- `objects` sidecar). Do not draw oscillator-style sub-panels.
- ## Chart authoring (LLM responsibility is small)
- For an `ict_smc` branch, `kb_klines.py chart` auto-fills
- `panels[0].items` with the SMC indicator's structural overlay (BOS/CHoCH
- markers, trailing-extreme labels, active
- Order Blocks, active Fair Value Gaps, equal H/L, internal OBs, and mitigated
- history). Premium/equilibrium/discount bands are optional and require
- `--include-zones`. You do **not** author
- rectangles, markers, or structural hlines.
- **The only items the LLM ever writes** are trade-setup hlines (entry /
- SL / target), passed at render time via `--trade-setup PATH`:
- ```json
- {"items": [
- {"type": "hline", "value": 78500, "label": "Short 78500",
- "style": {"role": "entry_short", "width": 2}},
- {"type": "hline", "value": 80000, "label": "SL 80000",
- "style": {"role": "stop_loss", "dash": "dashed", "width": 2}},
- {"type": "hline", "value": 77000, "label": "T1 77000",
- "style": {"role": "target", "width": 2}}
- ]}
- ```
- **Label rule**: ≤ 12 characters including the price. Put rationale
- (`"entry at FVG mid"`, `"SL above 4h OB"`) in the prose reply, not in
- the chart label.
- **Trade-setup `style.role` values**: `entry_long`, `entry_short`,
- `stop_loss`, `target`.
- Skip the trade-setup file when you have no specific trade levels to draw
- — the SMC structural overlay alone is a valid market chart.
- ## Shared Rules (apply to all workflows)
- 1. **No fabrication** — every price level cited must be visible on the chart or computed from a retrieved rule applied to a visible price.
- 2. **Cite the knowledge base** — every confirmed pattern must reference a retrieved card. Format: `"Rule N of <concept>: '<rule text>' — visible at <evidence>"`.
- 3. **Language rules**:
- - Prose language matches user's input: Chinese question → Chinese prose; English → English prose
- - Technical terms stay in English regardless of prose language: FVG, Order Block, Breaker, CISD, OTE, Liquidity Sweep, Killzone, IFVG, MSS, BOS, CHoCH, Displacement, etc. Do NOT translate to "公允价值缺口" — keep "Fair Value Gap" or "FVG"
- - Numbers/prices/percentages: keep original form
- 4. **State uncertainty explicitly** — prefer `null` or "uncertain — <reason>" over speculation.
- 5. **Multiple retrievals are OK** — for complex charts or multi-concept questions, run `kb_retrieve.py` more than once with different keyword combinations.
- 6. **Probability tiers (5 levels, semantic only)** — use exactly these names; do NOT expose internal percentages to users:
- | Tier | 中文 | Meaning |
- |---|---|---|
- | `very_high` | 很高 | Dominant scenario; strong rule-based confirmation |
- | `high` | 较高 | Primary plausible scenario; most rules confirm |
- | `medium` | 中等 | Plausible but partial rule confirmation |
- | `low` | 较低 | Edge case; speculative |
- | `very_low` | 很低 | Tail risk; mentioned for completeness only |
- 7. **Non-trading content** — if the image or question is not about trading, say so and stop.
- ## Tools
- Use the host-neutral placeholders defined above. OpenClaw can resolve
- `<SKILL_ROOT>` from `{baseDir}` and Hermes from `${HERMES_SKILL_DIR}`; on
- Antigravity (`agy`), Claude Code, Codex, Cursor, Grok Bot, Muse, and WorkBuddy
- resolve it from the loaded `SKILL.md`. Do not execute an undefined
- `${SKILL_DIR}` variable or assume that a virtual environment is on `PATH`.
- | Tool | Purpose |
- |---|---|
- | `scripts/kb_retrieve.py "<query>" --layer school --schools ICT SMC --top-k 5` | Default/School-scoped retrieval from attributable School projections |
- | `scripts/kb_retrieve.py "<query>" --layer evidence --sources <SOURCE>` | Exact source-evidence retrieval; optionally combine with `--schools` and `--type` |
- | `scripts/kb_klines.py resolve "<name>"` | Natural name → canonical asset spec |
- | `scripts/kb_klines.py fetch --query "<name>" --interval <tf> --with-htf` | Pull real OHLCV (+ HTF) from Mobius API |
- | `scripts/kb_klines.py parse --input <file>` | Parse pasted CSV/JSON/Markdown → standard OHLCV |
- | `scripts/kb_klines.py analyze --input <ohlcv.json>` | Extract features (swing/FVG/OB/sweep/displacement/structure). Add `--format json` to get structured features + `suggested_overlay_items` |
- | `scripts/kb_klines.py chart --query <name> --interval <tf>` | Pull K-lines and auto-fill the SMC structural overlay for an `ict_smc` route; use `--no-auto-overlay` for an empty overlay |
- | `scripts/kb_klines.py render --input <panels.json> --output <png>` | Render panels JSON → PNG via Playwright + lightweight-charts (TradingView-grade chart) |
- | `scripts/kb_klines.py indicators --query <name> --interval <tf>` | Default: fetch the SMC structural indicator (BOS/CHoCH, Order Blocks, FVGs, equal H/L, premium/discount zones, trailing pivot labels). Pass `--inds <exact-name>` only when the user explicitly named a specific indicator. Text output only, NOT rendered on chart. |
- | `scripts/kb_draw_annotation.py --json <path>` | Render annotation JSON onto chart (PIL, for **user-uploaded** images) |
- | `scripts/kb_phase_b_to_c.py --input <analysis.json> --image <png> --output <annotated.png>` | Convert analysis JSON → annotated image (one shot) |
- | `scripts/build_knowledge_v2.py` | Audit/export deterministic School projections and exact-source evidence |
- | `scripts/build_index.py` | Build canonical + independently embedded v2 collections; unchanged v2 documents reuse the local content cache |
- | `scripts/kb_doctor.py` | Environment health check (run if anything's broken) |
- Common options for `scripts/kb_retrieve.py`:
- - `--top-k N` (default 5)
- - `--type concept|case` (filter by card type)
- - `--layer canonical|school|evidence` (`canonical` is compatibility-only for strict routing)
- - `--schools <NAME...>` (multi-value OR filter; default route uses `--layer school --schools ICT SMC`)
- - `--school <NAME>` (single-school compatibility form)
- - `--sources <NAME...>` (exact OR filter; evidence layer only)
- - `--exclude-schools <NAME...>` (hard exclusion)
- - `--all-schools` (explicitly unscoped retrieval; never an automatic fallback)
- - `--search-mode auto|hybrid|semantic|lexical` (`auto` uses hybrid for v2;
- lexical does not load the embedding model)
- - `--max-per-canonical N` (v2 default 2; `0` disables diversity limiting)
- - `--list-schools` / `--explain-scope` (no embedding model load)
- - `--format markdown|json|compact`
README.md · README · 535 lines
- <div align="center">
- # OpenMobius-skill
- **Multi-school trading knowledge for AI coding agents — strict ICT/SMC market analysis by default**
- A `SKILL.md`-standard skill bringing 2008 curated knowledge cards, real-time
- market data, technical indicators, and chart generation to
- **Claude Code**, **Codex**, **Antigravity (`agy`)**, **OpenClaw**, **Hermes**,
- **Cursor**, **WorkBuddy**, **Grok Bot**, and **Muse**.
- <br>
- [](./LICENSE)
- [](https://www.python.org/)
- [](https://www.mobiusquant.ai/)
- [](#platform-support)
- [](#features)
- [English](./README.md) · [中文](./README.zh.md) · 📜 [Changelog](./CHANGELOG.md)
- </div>
- ---
- > **🤖 AI agents** — when a user asks you to install this skill,
- > follow [`README_AGENT.md`](./README_AGENT.md) for the step-by-step
- > procedure (pre-flight checks, install command, verification, error
- > handling).
- ---
- ## Community
- - [Join the OpenMobius Discord community](https://discord.com/invite/eYR75gBq6Z)
- - [Join the OpenMobius Telegram community](https://t.me/+LU3b7IGY6P4xMDU0)
- ---
- ## Overview
- <div align="center">
- <img src="./docs/assets/demo.gif" alt="OpenMobius-skill demo" width="780">
- <br>
- <sub>Works on <b>Claude Code</b>, <b>Codex</b>, <b>Antigravity (agy)</b>, <b>OpenClaw</b>, <b>Hermes</b>, <b>Cursor</b>, <b>WorkBuddy</b>, <b>Grok Bot</b>, and <b>Muse</b>.</sub>
- </div>
- <br>
- Drop this skill into your AI coding agent and ask trading questions in plain
- language. Knowledge Q&A is grounded inside the selected School/source scope.
- Supported current-market requests pass a capability gate before adding fresh,
- current-turn data and computed structure; unsupported routes stop instead of
- silently borrowing another School's analysis.
- | You ask | The skill does |
- |---|---|
- | *"What analysis models can I use?"* | Reads the current capability registry and dynamically separates native market-analysis profiles, Q&A-only lenses, and knowledge categories; also reports `strict` / `augment` / `compare`, without fetching market data or presenting categories as analysis models |
- | *"What is Fair Value Gap, how to trade it?"* | No selector means strict ICT/SMC; retrieves only attributable ICT/SMC knowledge and answers with cited rules |
- | *"Explain 中枢 using ChanLun only"* | Uses the isolated `缠论` School projection; explicit selectors never silently fall back to ICT/SMC |
- | *"Explain Order Block using Wuyuan's SMC material only"* | Hard-filters atomic evidence by both `school=SMC` and `source=Teach-Wuyuan`; an empty intersection fails closed |
- | *"Compare ICT and ChanLun definitions of market structure"* | Runs separate, attributed Q&A branches; conflicting definitions remain separate |
- | *"Use SMC as primary and Wuyuan as a reference to analyze BTC 1h"* | Uses `augment`: SMC alone controls bias and trade levels; Wuyuan evidence is clearly labelled supporting context |
- | *"Analyze BTC 1h using ChanLun"* | Stops before market-data or chart work because no native ChanLun market analyzer exists; never relabels SMC output as ChanLun |
- | *Attach a BTCUSDT 1h chart + "analyze this"* | After the route passes its capability gate, readable asset/timeframe data may be refreshed and cross-checked; if the supported route cannot identify them reliably, the result stays visual-only and discloses its limits |
- | *"How is BTC 1h looking?"* (no chart) | Defaults to strict ICT/SMC, fetches current-turn data, runs the built-in SMC structural indicator, and generates a grounded chart unless the user opts out |
- | *"What's <indicator> on BTC?"* (user names a specific indicator) | Pass-through to the indicator API — no auto-fetch of indicators the user did not name |
- | *Paste a CSV of OHLCV* | Preserves that snapshot, extracts structure locally, and never replaces it with a different live series merely to render a chart |
- | *"Generate a chart with my entry/SL/target"* | Rendered chart via Playwright + lightweight-charts |
- ---
- ## Quick start
- ```bash
- OPENMOBIUS_SRC="$(mktemp -d "${TMPDIR:-/tmp}/openmobius-src.XXXXXX")"
- git clone https://github.com/MobiusQuant/OpenMobius-skill.git "$OPENMOBIUS_SRC"
- cd "$OPENMOBIUS_SRC"
- python3 install.py --platform claude-code # or codex / agy / openclaw / hermes / cursor
- # On Linux/macOS, `all` installs all six local-path hosts. WorkBuddy, Grok Bot, and Muse use compact ZIP packages.
- cd "${TMPDIR:-/tmp}"
- rm -rf -- "$OPENMOBIUS_SRC" # ✓ exact mktemp directory only
- ```
- On Windows, clone into a writable directory and run
- `py -3 install.py --platform claude-code` (or use `.\install.ps1`).
- The installer copies source files into `~/.claude/skills/openmobius-skill/`
- (or your chosen platform's skills dir), then in that directory:
- 1. Creates `.venv/` and installs dependencies
- 2. Downloads Playwright chromium (~280 MB, into your OS's user-global cache)
- 3. Downloads the pinned `nomic-embed-text-v1.5` weights (~547 MB / 522 MiB, into your HuggingFace cache)
- 4. Loads bundled canonical vectors and the verified release seed for independent
- School/evidence vectors, then builds and verifies all three collections.
- Only locally changed or missing documents are embedded and cached.
- 5. Generates the platform-specific `SKILL.md`
- 6. Runs a health check
- Each installer-managed local copy is **self-contained**: it owns its own
- `.venv` and `_index`. The clone is just a one-shot source bundle.
- **First run**: dependency/model downloads plus seed-accelerated index build ·
- **Subsequent runs**: unchanged records use the release seed or local embedding cache
- After install, try capability discovery plus the default, scoped, and composed
- routes directly:
- ```
- # Default: strict ICT/SMC
- "What is Liquidity Sweep?"
- "How is ETH 4h looking?"
- # Discover the installed capabilities (no market-data request)
- "What analysis models can I use?"
- # Select an exact School or source
- "Explain 中枢 using ChanLun only"
- "Explain Order Block using Wuyuan's SMC material only"
- # Compose or compare
- "Compare ICT and ChanLun definitions of market structure"
- "Use SMC as primary and Wuyuan as a reference to analyze BTC 1h"
- ```
- Other Schools can scope knowledge Q&A when attributable material exists.
- Current-market analysis additionally requires a native analyzer; unsupported
- routes stop before market-data or chart work. Capability-discovery questions
- read the installed registry dynamically and report native market profiles,
- Q&A-only lenses, knowledge categories, and the available composition modes as
- separate concepts; they do not fetch market data or describe a category as an
- analysis model.
- > **Prerequisites**: Python 3.10+. See [INSTALL.md](./INSTALL.md) for details.
- ---
- ## Analysis lenses and routing
- The skill resolves both the user's intent and analysis route before knowledge
- retrieval, market-data calls, or drawing:
- ```text
- User request
- → choose intent: Q&A / chart analysis / annotation / K-line analysis
- → resolve mode + lens + School/source scope
- → capability gate
- → scoped knowledge retrieval
- → supported market analyzer and fresh data, when required
- → grounded answer and chart, or an explicit capability-gap response
- ```
- **Default:** when neither the current request nor an established conversation
- route supplies a lens, School, source, exclusion, or composition mode, the
- route is `strict` ICT/SMC. A current explicit selector overrides an inherited
- preference and is never silently widened or replaced.
- | Dimension | What it controls | Example |
- |---|---|---|
- | Lens/profile | The methodology allowed to interpret structure and form market conclusions | `ict_smc`; future native analyzers may add other lenses |
- | School | The attributable knowledge boundary | ICT, SMC, 缠论, Wyckoff, Price Action |
- | Source | A teacher, course, or material collection | `Teach-Wuyuan`; a source does not select a lens |
- ### Composition modes
- | Mode | Meaning | Behavior |
- |---|---|---|
- | `strict` | Use only the selected boundary | A single explicit selector is strict by default; without one, use ICT/SMC |
- | `augment` | Use A as primary and B as supporting context | The primary lens alone owns bias, entry, stop, targets, and the primary chart; secondary contributions are labelled confirmation, challenge, or risk context |
- | `compare` | Compare A and B independently | Supported for Q&A only in Phase 1; branches use equal queries and remain separately attributed |
- ### Current capability boundary
- | Selection | Knowledge Q&A | Market/chart/annotation |
- |---|---|---|
- | ICT and/or SMC | Supported | Supported by the native ICT/SMC structural analyzer |
- | Other registered Schools/categories | Supported when attributable knowledge exists | Unsupported unless that School has a native analyzer |
- | Exact source | Supported as an exact evidence scope and may intersect a School | Requires a separately selected, supported primary lens |
- | Multi-School `compare` | Supported as isolated Q&A branches | Not supported in Phase 1; stops before data or artifact generation |
- The complete installed taxonomy is deliberately broader than the native
- market-analysis models:
- - **Native market-analysis lens:** `ICT`, `SMC` (one `ict_smc` analyzer).
- - **Q&A knowledge lenses:** `缠论`, `Price Action`, `Order Flow`,
- `Volume Analysis`, `Elliott Wave`, `Wyckoff`, `The Strat`.
- - **Knowledge categories, not analysis models:** `Indicator Based`,
- `Risk Management`, `General`, `On-chain`, `Market Structure`.
- - **Evidence-only category:** `Scalping`; it occurs in attributable source
- evidence but is not a top-level canonical-card School.
- Unknown selectors, empty strict scopes, empty School/source intersections,
- missing exact-filter support, missing native analyzers, and market `compare`
- requests **fail closed when they affect a required strict or primary branch**:
- the skill explains the gap and does not fall back to canonical, another
- School/source, or default ICT/SMC. In `augment`, an unavailable secondary may
- be omitted or labelled knowledge-only while a supported primary continues.
- Follow-up annotation inherits the prior analysis route. A new explicit
- School/source/profile requires re-evaluating the analysis; existing levels are
- not merely relabelled. See the full
- [route contract and capability matrix](./workflows/analysis_profiles.md) for
- aliases, precedence, partial-support rules, and exact failure behavior.
- ---
- ## Platform support
- ```bash
- python3 install.py --platform <name>
- ```
- <div align="center">
- | Platform | Flag | Default path / setup route |
- |:---|:---|:---|
- | **Claude Code** | `--platform claude-code` *(default)* | `~/.claude/skills/openmobius-skill/` |
- | **Codex** | `--platform codex` | `~/.agents/skills/openmobius-skill/` |
- | **Antigravity (`agy`)** | `--platform agy` | `~/.gemini/config/skills/openmobius-skill/` *(workspace: `.agents/skills/openmobius-skill/`)* |
- | **OpenClaw** *(Linux/macOS)* | `--platform openclaw` | `<OPENCLAW_STATE_DIR or ~/.openclaw>/skills/openmobius-skill/` |
- | **Hermes** *(Linux/macOS)* | `--platform hermes` | `<HERMES_HOME or ~/.hermes>/skills/market-data/openmobius-skill/` |
- | **Cursor** | `--platform cursor` | `~/.cursor/skills/openmobius-skill/` |
- | **WorkBuddy** | local ZIP import / marketplace | `Skills → Add Skill → Upload Skill`; published copies install from the marketplace |
- | **Grok Bot** *(xAI)* | compact ZIP upload | `python3 scripts/build_hosted_package.py --platform grok-bot --output ...` |
- | **Muse** *(Meta)* | compact ZIP upload | `python3 scripts/build_hosted_package.py --platform muse --output ...` |
- | Auto-detect | `--platform auto` | detects supported local host roots |
- | All local hosts *(Linux/macOS)* | `--platform all` | installs to the six local paths above; excludes WorkBuddy, Grok Bot, and Muse |
- </div>
- Each local-path platform install is fully **self-contained** (its own `.venv`,
- its own `_index`). The nomic model and Playwright chromium live in your OS's
- user-global cache, shared across platforms — so installing on N platforms
- doesn't N× the download.
- `OPENCLAW_STATE_DIR` and `HERMES_HOME` override the corresponding roots when
- set. The current OpenClaw and Hermes adapters/manifests target Linux and
- macOS; on Windows, select Claude Code, Codex, Antigravity (`agy`), or Cursor
- explicitly instead of using `--platform all`. Antigravity (Google Antigravity
- CLI `agy`, Antigravity IDE, and Antigravity 2.0) discovers user-global skills
- from `~/.gemini/config/skills/` and workspace-level skills from
- `.agents/skills/openmobius-skill/` (with `.gemini/skills/` legacy
- compatibility). Cursor Cloud Agents, remote SSH sessions, and other
- remote environments do not receive local user skills from `~/.cursor/skills`;
- place the skill in the repository's `.cursor/skills/openmobius-skill/` for
- those environments.
- WorkBuddy is not CodeBuddy. Its public documentation does not define a fixed
- filesystem directory that a third-party installer can write to for automatic
- discovery, so `--platform all` intentionally excludes it. Choose the workflow
- that matches your goal:
- | Goal | Official route |
- |:---|:---|
- | Import this repository's local package | In WorkBuddy, open **Skills → Add Skill → Upload Skill**, then drag or select the generated ZIP. WorkBuddy configures it after import. |
- | Install a published Skill | Open **Experts · Skills · Connectors → Skills → Skill Marketplace**, then click the `+` on its card. |
- | Publish a Skill for other users | Use the WorkBuddy Open Platform. Creation, ZIP parsing, review, and publication are separate from local import. |
- Build this repository's local-import ZIP with:
- ```bash
- python3 scripts/build_workbuddy_package.py \
- --output /tmp/openmobius-skill-workbuddy.zip
- ```
- The WorkBuddy Skill format currently accepts `.zip` packages up to 3 MB. The
- builder uses the conservative 3,000,000-byte boundary and fails before
- replacing an existing artifact if the package is too large. Local installation
- is complete only when the import succeeds and the Skill appears under
- **Installed**. A successful Open Platform parse or submission does not by
- itself mean that the Skill is installed locally or published in the marketplace.
- `--platform workbuddy --target-dir <path>` is available only for developer
- staging and validation. It does not register a locally discoverable WorkBuddy
- Skill and is not the normal installation route.
- To fit that package-size boundary without discarding attributable knowledge, the ZIP
- uses a checksummed compact corpus that reconstructs all 2,144 School
- projections and all 18,645 exact-source evidence records. It supports lexical
- BM25/exact-alias retrieval with hard School and source filters using the system
- Python alone. A manifest binds the compact corpus, School registry, and alias
- map by size and SHA-256, allowing the standard retriever to run even when a
- read-only host forbids first-run lock-file creation. The canonical fused-card
- layer, vector index, embedding cache,
- and model seed are intentionally omitted; canonical and
- auto/hybrid/semantic routes fail closed in the WorkBuddy package.
- The ZIP does not bundle Python, create a virtual environment, or install
- packages. Script-backed features require Python 3.10+. WorkBuddy 4.6.3 and
- later can detect missing Python/Node.js from **Settings** and offer one-click
- installation; verify that the installed Python still meets this Skill's 3.10+
- minimum. If no suitable Python launcher is available, script-backed
- knowledge/market operations must be reported unavailable. Q&A and text-market
- workflows need only the standard library, while PNG rendering and image
- annotation additionally require host-provided Playwright/Chromium or Pillow,
- respectively.
- **Grok Bot** (xAI's hosted Agent assistant) and **Muse** (Meta's hosted
- personal AI assistant) run uploaded skill bundles inside managed cloud
- containers rather than reading a fixed directory on your local workstation, so
- `--platform all` and `--platform auto` intentionally exclude them. Build
- deterministic `<3 MB` stdlib-only compact packages (`openmobius-skill/` root,
- `compact_v2` corpus with all 2,144 School projections and 18,645
- source-evidence records, plus SHA-256 read-only bundle manifest) with:
- ```bash
- python3 scripts/build_hosted_package.py --platform grok-bot --output /tmp/openmobius-skill-grok-bot.zip
- python3 scripts/build_hosted_package.py --platform muse --output /tmp/openmobius-skill-muse.zip
- ```
- Upload the resulting ZIP (or extracted `openmobius-skill/` folder) into your
- Grok Bot or Muse workspace. `--platform <grok-bot|muse> --target-dir <path>` is
- also available in `install.py` for developer staging and validation only.
- The implementation follows the common [Agent Skills specification](https://agentskills.io/specification)
- and each host's official documentation:
- [Claude Code](https://code.claude.com/docs/en/skills),
- [Codex](https://learn.chatgpt.com/docs/build-skills),
- [OpenClaw](https://docs.openclaw.ai/tools/skills),
- [Hermes](https://github.com/NousResearch/hermes-agent/blob/main/website/docs/developer-guide/creating-skills.md),
- [Cursor](https://cursor.com/docs/skills),
- [WorkBuddy local Skill guide](https://www.workbuddy.cn/docs/workbuddy/From-Beginner-to-Expert-Guide/Function-Description/Skills-Market),
- [WorkBuddy Skill format/marketplace](https://open.workbuddy.cn/docs/skill),
- [WorkBuddy Open Platform](https://open.workbuddy.cn/docs/what-is-open-platform), and
- [WorkBuddy changelog](https://www.workbuddy.cn/docs/workbuddy/Changelog).
- ---
- ## Features
- ### Knowledge base — 726 concepts + 1282 cases
- Distilled from 300+ teaching videos and live lessons across 12 curated
- source collections, cross-merged with model-audited term fusion and
- content-level deduplication. Across concept and case cards there are 14
- top-level School/category labels: ICT, SMC, Price Action, Indicator Based,
- ChanLun (缠论), Risk Management, General, Order Flow, Volume Analysis/VSA,
- Elliott Wave, Wyckoff, The Strat, On-chain, and Market Structure. The registry
- exposes 15 retrievable labels in total: those 14 top-level labels plus the
- non-canonical, source-evidence-derived Scalping category. Each concept card carries:
- identification rules, trading
- implications, common mistakes, related concepts, per-source definitions.
- Each case card carries: market context, key observation, analysis steps,
- lessons, and source time-range provenance. Retrieved via local ChromaDB +
- multilingual `nomic-embed-text-v1.5` — no API key needed for retrieval.
- The index exposes three layers with different roles:
- | Layer | Records | Role |
- |---|---:|---|
- | Canonical | 2,008 | Backward-compatible fused exploration; never proof of strict School isolation |
- | School | 2,144 | Exact School-scoped Q&A and grounding |
- | Evidence | 18,645 | Atomic source scope and exact School/source/type intersections |
- School and evidence content is included only when it can be safely attributed.
- Ambiguous cross-School fused rules are skipped and counted, not guessed. See
- [knowledge-base architecture](./knowledge_base/README.md) for the data model,
- registry, schemas, and rebuild process.
- Each School/evidence record now has an embedding of its own scoped document;
- vectors are cached by exact content hash and model identity, so incremental
- updates embed only misses. v2 queries default to hybrid retrieval: BM25 and
- semantic candidates are generated inside the hard-filtered scope and fused by
- reciprocal rank, while exact canonical-term/alias matches remain first. Use
- `--search-mode lexical` for a model-free search or `--search-mode semantic` for
- the vector-only baseline.
- ### Real-time data + 60+ indicators
- Crypto (Binance, Bybit, OKX, Gate, Coinbase, Hyperliquid, and cross-exchange
- `composite`), commodities (spot gold `XAUUSD` and gold/silver futures
- `XAUF` / `XAGF`), China A-shares, Hong Kong stocks, US stocks, and forex —
- powered by KlineSync Engine v2.0. Each indicator carries built-in analysis
- dimensions (`summary_focus`) that the agent reads to structure its answer
- rather than dumping raw numbers.
- ### Two chart-generation paths
- | Path | Method | Output |
- |---|---|---|
- | Annotate user's image | PIL | Annotated copy preserving the original chart |
- | Generate fresh chart | lightweight-charts in headless chromium | New K-lines + FVG/OB rectangles + sweep lines + swing markers |
- ### Intent routing + analysis-profile routing
- The `SKILL.md` description field triggers on natural-language questions. The
- skill first identifies the user's intent, then resolves the independently
- selected analysis profile before executing the workflow.
- | Intent | Typical trigger | Workflow |
- |---|---|---|
- | Knowledge Q&A | Concept, definition, rule, or comparison without a chart/data request | [Q&A](./workflows/qna.md) |
- | Chart analysis | An attached trading chart plus a request to analyze it | [Analyze](./workflows/analyze.md) |
- | Annotation | An explicit request to draw, or an annotation follow-up | [Annotate](./workflows/annotate.md) |
- | K-line analysis | Pasted OHLCV, or an asset + timeframe market request | [K-lines](./workflows/klines.md) |
- Intent and analysis profile are separate: the same Q&A workflow can run in
- `strict`, `augment`, or `compare` mode, while the capability gate decides
- whether a requested market workflow has a native analyzer. An annotation
- follow-up inherits the prior route; changing a selector explicitly causes a
- fresh analysis rather than relabeling the previous result.
- ---
- ## Roadmap
- **Knowledge base**
- - **ICT/SMC coverage completion** — Rounds 1–2 distilled the ICT trunk plus
- SMC supplements from 300+ teaching videos; upcoming rounds complete ICT
- sub-schools (Inner Circle Mentorship, Silver Bullet, Power of 3 variants)
- and full SMC coverage.
- - **Fundamental knowledge base** — interpretation methodologies for news,
- policy reads, economic releases (CPI / NFP / FOMC) and earnings seasons.
- - **Multi-school coverage deepening** — Wyckoff, VSA/Volume Analysis, Price
- Action, ChanLun (缠论), and other Schools are already retrievable; upcoming
- rounds deepen their coverage, provenance, and attribution quality.
- - **Native multi-school analyzers** — knowledge scope is not the same as a
- market-analysis engine. New School-native profiles and overlays will be
- added before market `compare` expands beyond Q&A.
- **Indicators & tools**
- - **Expanded SMC indicator coverage** — the built-in SMC structural
- indicator covers BOS/CHoCH, Order Blocks, FVGs, equal H/L, premium-
- discount zones and strong/weak pivot labels today. Upcoming: Killzone
- windows, Stop Run / Inducement events, and per-event probability
- scoring as computable signals.
- **Access surfaces**
- - **Non-CLI entry points** — chat-bot integrations for users who don't run a
- coding agent, so the knowledge base is reachable without the CLI.
- ---
- ## Architecture
- ```
- OpenMobius-skill/
- ├── SKILL.md # main entry (LLM reads this)
- ├── SKILL.body.md # shared body (platform-neutral)
- ├── platforms/ # per-platform frontmatter
- │ └── agy.yaml / claude-code.yaml / codex.yaml / cursor.yaml / grok-bot.yaml / hermes.yaml / muse.yaml / openclaw.yaml / workbuddy.yaml
- ├── agents/
- │ └── openai.yaml # Codex UI and invocation metadata
- ├── workflows/
- │ ├── qna.md / analyze.md / annotate.md / klines.md # intent workflows
- │ └── analysis_profiles.md # route contract + capability gate
- ├── scripts/ # CLI tools
- │ ├── kb_retrieve.py # hard-scoped hybrid retrieval
- │ ├── kb_klines.py # API client + feature extraction
- │ ├── kb_draw_annotation.py # PIL annotation
- │ ├── kb_phase_b_to_c.py # analysis JSON → annotated PNG
- │ ├── build_knowledge_v2.py # audit/export School + source-evidence records
- │ ├── build_index.py # build all three vector collections
- │ ├── export_v2_embedding_seed.py # publish verified native-vector shards
- │ ├── build_workbuddy_package.py # deterministic WorkBuddy local-import ZIP builder
- │ ├── build_hosted_package.py # deterministic Grok Bot / Muse compact ZIP builder
- │ ├── evaluate_retrieval.py # reproducible retrieval benchmark
- │ ├── kb_doctor.py # env health check
- │ ├── chart_render/ # lightweight-charts + headless chromium
- │ └── _lib/ # embedder + retriever
- ├── evals/ # versioned retrieval cases + baseline reports
- ├── knowledge_base/ # cards + registry + schemas + release seed
- ├── install.py # cross-platform installer
- └── README.md / INSTALL.md
- ```
- ---
- ## Update / Uninstall
- ```bash
- # Update
- python3 install.py --update
- python3 install.py --update --rebuild-index # also rebuild vector index
- # Uninstall the entire self-contained platform install (.venv + index included)
- python3 install.py --uninstall
- python3 install.py --uninstall --platform all # Linux/macOS: all six local hosts
- # Full purge (also delete shared chromium + nomic caches — these may be
- # used by other projects on your machine, so confirm before running)
- python3 install.py --uninstall --purge --yes-i-know
- ```
- `--full` is still accepted for backward compatibility, but is deprecated and
- has no effect: standard uninstall already removes `.venv` and the vector index.
- See [INSTALL.md](./INSTALL.md) for all flags.
- ---
- ## Troubleshooting
- ```bash
- .venv/bin/python scripts/kb_doctor.py
- ```
- Reports the state of: venv, deps, nomic model, vector index, CJK fonts,
- skill registration, API connectivity.
- Common issues:
- | Symptom | Fix |
- |---|---|
- | Chinese labels render as boxes | Install `fonts-noto-cjk` (Linux); macOS/Windows usually bundled |
- | API request fails | Check network; see `api.mobiusquant.ai/api/health` |
- | Skill not auto-invoking in Claude Code | Check `~/.claude/skills/openmobius-skill` exists. Claude Code watches an existing skills directory live; if that top-level directory was newly created, start a new session. |
- | Skill missing in Codex | Check `~/.agents/skills/openmobius-skill` exists; restart Codex |
- | Skill missing in Antigravity (`agy`) | Check `~/.gemini/config/skills/openmobius-skill` (or workspace `.agents/skills/openmobius-skill`) exists, then run `kb_doctor.py --platform agy` |
- | Skill missing in OpenClaw or Hermes | Check the effective `OPENCLAW_STATE_DIR` or `HERMES_HOME`, then run `kb_doctor.py` from that installed copy |
- | Cursor Cloud/remote cannot see the user skill | Copy/install it under the repository's `.cursor/skills/openmobius-skill/`; local `~/.cursor/skills` is not synchronized |
- | WorkBuddy cannot discover a local folder | Do not guess a local path. Build the ZIP, then use **Skills → Add Skill → Upload Skill** and select it; confirm it appears under **Installed** |
- | Grok Bot or Muse cannot discover a local folder | Build the compact ZIP via `scripts/build_hosted_package.py --platform <grok-bot\|muse> --output ...` and upload it to the hosted assistant workspace |
- | `chroma.sqlite3` not found | `.venv/bin/python scripts/build_index.py` |
- | ChanLun/Wyckoff market analysis stops | These Schools are retrievable for Q&A but do not yet have a native market analyzer; use Q&A or a supported lens |
- | Market `compare` stops before fetching data | Phase 1 supports `compare` for Q&A only; this is the capability gate working as designed |
- ---
- ## License
- Apache 2.0 — see [LICENSE](./LICENSE).
- Third-party components: see [ATTRIBUTION.md](./ATTRIBUTION.md).
- ## Contributing
- Issues and PRs welcome at
- <https://github.com/MobiusQuant/OpenMobius-skill/issues>.
- <div align="center">
- <sub>Built for AI coding agents · Apache 2.0</sub>
- </div>
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.