Vibe-Trading is a personal trading agent that gives an AI system tools for market analysis, algorithmic trading, backtesting, and related workflows. It is for users who want an agent to research and evaluate trading strategies or manage simulated and other trading activities. The catalogue contains skills that expose these trading capabilities to compatible agents.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HKUDS/Vibe-Trading --skill shadow-accountgit clone --depth 1 https://github.com/HKUDS/Vibe-TradingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hkuds/vibe-trading/shadow-account)<a href="https://agentmods.dev/skills/hkuds/vibe-trading/shadow-account"><img src="https://agentmods.dev/badge/skills/hkuds/vibe-trading/shadow-account/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hkuds/vibe-trading/shadow-account"><img src="https://agentmods.dev/badge/skills/hkuds/vibe-trading/shadow-account.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.01137 |
| Opus 5 | $0.00035 | $0.00568 |
| Sonnet 5 | $0.00014 | $0.00227 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
shadow-account scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- shadow-account — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shadow Account — 影子账户
何时触发
当用户说 "提炼我的策略" / "训练影子" / "我的打法回测一下" / "我能多赚多少" / "我的盈利模式" 时,加载此 skill。
前提:用户已上传交割单且 analyze_trade_journal 已跑过。若没有,先跑 Phase 4a 工具。
工作流(四步)
extract_shadow_strategy(journal_path=...)- 返回
shadow_id+ 3-5 条人话规则 - 向用户 confirm:"这些规则像你本人吗?" 如果用户说"不像",提高
min_support重跑
- 返回
run_shadow_backtest(shadow_id=..., journal_path=...)- 返回 per-market 指标 +
delta_pnl+ attribution breakdown - 默认四市场并跑(china_a/hk/us/crypto)
- 返回 per-market 指标 +
render_shadow_report(shadow_id=...)- 生成 HTML + PDF(weasyprint 失败时自动降级成 HTML-only)
- 返回
html_path/pdf_path/delta_pnl
- (可选)
scan_shadow_signals(shadow_id=...)— 今日落在影子入场窗口的标的列表(研究用)
产出解读
规则卡
每条规则含:rule_id、human_text(≤30 字)、support_count、coverage_rate、holding_days_range。规则不是"必赚公式",而是"用户盈利时的共性画像"。
回测矩阵
per_market:四市场的 Sharpe/年化/最大回撤combined:合并池表现equity_curve:净值时序(进入 PDF Section 3)
差值归因(PDF Section 5 — gut punch)
所有数值 signed,正值=影子相对赚更多:
noise_trades_pnl:不命中任何规则的真实交易累计 PnL(用户的情绪单)early_exit_pnl:赢单但持仓 < 规则下限,按不足比例折算的机会成本late_exit_pnl:亏单但持仓 > 规则上限,按超额比例折算的放大损失overtrading_pnl:超出规则频率的真实交易 PnLmissed_signals_pnl:残差(shadow_pnl − real_pnl − 上面四项之和)
反事实 Top 5
按 |impact| 排序,列出 5 条"最该做没做 / 最不该做却做了"的交易,带具体日期、原因。
对话模板
确认规则:
从你 {profitable_roundtrips} 笔盈利回合中提炼出这些规则:{rules}。这些看起来像你本人的打法吗?
展示差值(Section 5):
影子 PnL {shadow_pnl:+.0f} / 你真实 {real_pnl:+.0f} / 差值 {delta_pnl:+.0f}。其中 {noise_trades_pnl:+.0f} 来自不符合你任何盈利规则的"情绪单"。
今日扫描(强制附带免责):
今日落在你影子入场节奏的标的:{symbols}。仅研究用,不是买入建议。
规则翻译 Prompt 模板
当 extract_shadow_strategy 被调用时,可以注入一个 llm_translator callable 以把结构化 entry_condition 翻译成中文自然语言:
[上下文] 一位散户的盈利回合中,{N} 笔满足同一组条件:
market = {market}
entry_hour ∈ [{hour_min}, {hour_max}]
持有 {hold_lo}-{hold_hi} 天
[任务] 用 ≤30 字的中文写一条规则,口吻像用户自述的交易习惯,不要堆术语。
[输出] 只返回一行规则文本,不要解释。
不注入时走 f-string 模板(见 extractor._translate_rule)。
红线
- 不落单:这些工具永远不会对接任何下单通道,仅研究输出
- 不复制他人策略:Shadow Account 是"用户自己"的影子,不从社区/公开策略提取规则
- 样本不足必报错:profitable roundtrips < 5 → 直接 raise,不编造
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 80 lines · 70 tokens per session scan A 22635f9d11c9
shadow-account is a skill published in the GitHub repository HKUDS/Vibe-Trading (33,177 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,137 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hyperliquid
Use when backtesting, deploying, checking funding readiness, or debugging a Hyperliquid strategy through Superior Trade Unified API — writing Freqtrade configs and strategy code, running sweeps, checking managed-wallet balances, trading HIP-3 perps, or diagnosing a deployment that will not start or trade.
polymarket
Use when the user wants to trade, research, or backtest Polymarket prediction markets through Superior Trade — finding markets by slug or event URL, placing a single immediate market order, writing NautilusTrader strategies, running filled-data backtests, funding pUSD, or deploying and monitoring a live Polymarket…
aerodrome
Use when creating, validating, backtesting, deploying, sizing, or troubleshooting Aerodrome/Base spot trading strategies through the Superior Trade API, especially Freqtrade configs using exchange.name "aerodrome", AERO/USDC or CHECK/USDC pairs, AMM market swaps, wallet/gas balance checks, no-orderbook pricing, or…
backtesting
Use when running, interpreting, or designing backtests on Superior Trade — anything about backtest windows, trade-count thresholds, exit-reason mix, parameter sweeps, walk-forward validation, zero-trade diagnosis, compute-cost estimation, or "is this backtest result trustworthy?". Pair with the relevant strategy…
basis-arb
Use when the user asks for spot-perp basis trade, basis arbitrage, cash-and-carry, perp discount, or any setup that reads the spot–perp basis as a positioning signal. Long-perp leg only — pure two-leg basis arb requires a paired spot short (or long) which Freqtrade can't run cleanly. The strategy below captures the…
fees-optimizations
Use when the user asks about fees, fee optimization, slippage, maker vs taker, post-only or ALO orders, fee tiers, builder code fees, effective spread, order pricing, lowering trading costs, or why a live Hyperliquid Freqtrade strategy underperforms its backtest. Also use proactively for high-turnover designs (5m or…