Explore
138,262 skills indexed with the new KISS metadata standard.
Please review this pull request and add a comment with a summary of the task instruction and how it implements the solution, and how it tests task completion. Be concise and to the point.
code_review:
Agent Skills that teach coding assistants how to add DeepEval evaluations,
This file contains domain knowledge about the Cal.diy product and codebase. For coding guidelines and rules, see [`rules/`](rules/).
- `yarn dev` - Start development server for web app
- **[../AGENTS.md](../AGENTS.md)** - Main guide (structure, tech stack, commands, examples)
Use when adding tests for a new modality (vision/embeddings/TTS/STT/realtime/image-gen/video-gen), a new AI provider, or a new SDK feature. Picks the right per-domain suite, wires the right helpers, sets the right capability flag, and avoids the four traps that broke past contributions (loose error matchers, missing capability gate, monolithic test file, manual skip plumbing).
Mem0 ships structured skill definitions for Claude Code, Codex, Cursor, OpenCode, OpenClaw, and any assistant that supports the [skills standard](https://github.com/anthropic-experimental/skills). Skills teach the assistant how to work with Mem0 — either by loading SDK knowledge into context, or by
memory_config:
generic skill
ICT/SMC trading knowledge base (665 concepts + 1246 cases) + a built-in SMC structural indicator + chart generation via Mobius Quant API. Four interaction modes - (1) concept Q&A ("what is X / how to identify Y / how to enter Z"); (2) chart-image analysis when user attaches a trading chart ("看图 / 分析 / 走势 / 行情 / 帮我看") — auto-fetches real OHLCV + structural signals; (3) chart annotation ("draw / annotate / 标一下 / 画出来 / 标注"); (4) Kline analysis on pasted OHLCV or asset+timeframe ("BTC 1h 怎么样" / "茅台日线"). The SMC indicator (BOS/CHoCH, Order Blocks, Fair Value Gaps, equal H/L, premium-discount, strong/weak pivots) is the default structural source for any asset+timeframe query. Always fetches FRESH data per turn from Mobius Quant API (api.mobiusquant.ai); when asked "数据源 / where's the data from", use the canonical disclosure (do not fabricate upstream vendors). Supports crypto, A股/港股/美股, forex.
A unified skill for four interaction modes with a curated knowledge base (380 concept cards + 584 case cards) distilled from 130 ICT/SMC trading-analysis videos.
This file is written for **AI agents** (Claude Code / Codex / OpenClaw /
**给 AI 编程 Agent 的 ICT/SMC 交易知识 Skill**
**ICT/SMC trading-knowledge skill for AI coding agents**
`OpenMobius-skill` is a **local-first AI agent skill**. This document
You need **Python 3.10 or later**. The installer handles everything else.
本文件记录 **OpenMobius-skill** 的版本变更。
All notable changes to **OpenMobius-skill** are documented in this file.
This project (`OpenMobius-skill`) is licensed under Apache 2.0 (see `LICENSE`).
.venv/
|
<img src="./asset/banner.png" alt="ComfyUI Skills Banner">
<img src="./asset/banner.png" alt="ComfyUI Skills Banner">