OpenMobius-skill

🤖 AI agents — when a user asks you to install this skill, follow README_AGENT.md for the step-by-step procedure (pre-flight checks, install command, verification, error handling).

Contributors

Thanks to the people who help improve OpenMobius-skill:

• @xwzbupt

Overview

_{Works on Claude Code, Codex, OpenClaw, and Hermes.}

Drop this skill into your AI coding agent and ask trading questions in plain language. The skill grounds every answer in a curated knowledge base + real market data — no hallucinated price levels, no generic "looks bearish" hand-waving.

Quick start

git clone https://github.com/MobiusQuant/OpenMobius-skill.git /tmp/openmobius-src
cd /tmp/openmobius-src
python install.py --platform claude-code      # or codex / openclaw / hermes / all

rm -rf /tmp/openmobius-src                     # ✓ clone is ephemeral; safe to delete

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 nomic-embed-text-v1.5 model (~274 MB, into your HuggingFace cache)
4. Loads precomputed embeddings → builds vector index (~2 s)
5. Generates the platform-specific SKILL.md
6. Runs a health check

Each platform install is self-contained: it owns its own .venv and _index. The clone is just a one-shot source bundle.

First run: ~5–10 min · Subsequent runs (python install.py --update): <1 min

After install, in your AI agent just ask:

"What is Liquidity Sweep"
[attach chart] "analyze this setup"
"How is ETH 4h looking, give me a chart"
"BTC 1h structure check"

Prerequisites: Python 3.10+. See INSTALL.md for details.

Platform support

python install.py --platform <name>

Each 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.

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. Coverage spans 13 schools — ICT, SMC, Price Action, Indicator-Based, ChanLun (缠论), Risk Management, Order Flow and more. 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.

Real-time data + 60+ indicators

Crypto (Binance, Bybit, OKX, Hyperliquid), China A-shares, Hong Kong stocks, US stocks, forex. 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

Auto-invoked by description matching

The SKILL.md description field triggers on natural-language questions. The skill routes to one of four workflows: Q&A · analyze · annotate · klines.

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 expansion — ChanLun (缠论) landed in v0.3.0; next up: Wyckoff (volume/price action), VSA, Volume Profile / Market Profile, and classic Price Action (Al Brooks style).

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
│   └── claude-code.yaml / codex.yaml / openclaw.yaml / hermes.yaml
├── workflows/                        # detailed sub-workflows
│   └── qna.md / analyze.md / annotate.md / klines.md
├── scripts/                          # CLI tools
│   ├── kb_retrieve.py                # local vector 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_index.py                # build vector index
│   ├── kb_doctor.py                  # env health check
│   ├── chart_render/                 # lightweight-charts + headless chromium
│   └── _lib/                         # embedder + retriever
├── knowledge_base/                   # 726 concepts + 1282 cases
├── install.py                        # cross-platform installer
└── README.md / INSTALL.md

Update / Uninstall

# Update
python install.py --update
python install.py --update --rebuild-index    # also rebuild vector index

# Uninstall (soft — remove platform registration only)
python install.py --uninstall
python install.py --uninstall --platform all  # all platforms

# Uninstall fully (.venv + index too)
python install.py --uninstall --full

# Full purge (also delete shared chromium + nomic caches — these may be
# used by other projects on your machine, so confirm before running)
python install.py --uninstall --purge --yes-i-know

See INSTALL.md for all flags.

Troubleshooting

.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:

License

Apache 2.0 — see LICENSE. Third-party components: see ATTRIBUTION.md.

Contributing

Issues and PRs welcome at https://github.com/MobiusQuant/OpenMobius-skill/issues.