whale-index by senpi-ai/senpi-skills
npx skills add https://github.com/senpi-ai/senpi-skills --skill whale-index扫描发现排行榜,为交易者评分,创建镜像策略,并每日进行再平衡。设定您的风险等级和预算 — 代理将处理选择、分配、监控和互换。
创建策略时,请在调用中包含 skill_name 和 skill_version。详情请参阅 references/skill-attribution.md。
收集:预算、风险承受能力(保守/适中/激进)。
| 预算 | 仓位数量 |
|---|---|
| $500-$2k | 2 |
| $2k-$5k | 3 |
| $5k-$10k | 4 |
| $10k+ | 5 |
风险映射:
| 风险等级 |
|---|
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 允许的标签 |
|---|
| 最大杠杆 |
|---|
| 保守 | 仅限 ELITE | 10x |
| 适中 | ELITE, RELIABLE | 15x |
| 激进 | ELITE, RELIABLE, BALANCED | 25x |
2a. 拉取候选者: discovery_top_traders(limit=50, timeframe="30d")
2b. 硬性筛选条件:
2c. 为剩余候选者评分:
score = 0.35 × pnl_rank + 0.25 × win_rate + 0.20 × consistency + 0.10 × hold_time + 0.10 × drawdown
所有组成部分均归一化到 0-100。
2d. 重叠检查: 比较所选交易者之间的活跃持仓。标记持仓重叠度 >50% 的情况。
2e. 分配权重: 基于评分进行加权分配,每个仓位上限为 35%。上限后重新归一化。
向用户展示:交易者地址、排名、标签、胜率、分配金额。执行前等待用户批准。
对于每个仓位:
strategy_create_mirror 创建镜像策略完整的每日检查流程、互换标准和再平衡逻辑,请参见 references/daily-monitoring.md。
互换标准(必须全部满足):
watchCount 跟踪)关键原则: 2 天的观察期可防止因暂时性下跌而频繁更换。
要退出:关闭所有镜像策略,将资金返还到主钱包。
discovery_top_traders — 交易者排行榜strategy_create_mirror — 创建镜像策略strategy_get_clearinghouse_state — 检查持仓strategy_close_strategy — 清理镜像策略产生的交易费用与被镜像交易者的活动相同。对于活跃交易者,每日预算费用约为 0.5-1%。
每周安装数
113
代码仓库
GitHub 星标数
53
首次出现
2026年2月27日
安全审计
安装于
opencode111
gemini-cli111
github-copilot111
codex111
kimi-cli111
amp111
Scan the Discovery leaderboard, score traders, create mirror strategies, and rebalance daily. Set your risk level and budget — the agent handles selection, allocation, monitoring, and swaps.
When creating a strategy, include skill_name and skill_version in the call. See references/skill-attribution.md for details.
Collect: budget, risk tolerance (conservative/moderate/aggressive).
| Budget | Slots |
|---|---|
| $500-$2k | 2 |
| $2k-$5k | 3 |
| $5k-$10k | 4 |
| $10k+ | 5 |
Risk mapping:
| Risk | Allowed Labels | Max Leverage |
|---|---|---|
| Conservative | ELITE only | 10x |
| Moderate | ELITE, RELIABLE | 15x |
| Aggressive | ELITE, RELIABLE, BALANCED | 25x |
2a. Pull candidates: discovery_top_traders(limit=50, timeframe="30d")
2b. Hard filters:
2c. Score remaining candidates:
score = 0.35 × pnl_rank + 0.25 × win_rate + 0.20 × consistency + 0.10 × hold_time + 0.10 × drawdown
All components normalized 0-100.
2d. Overlap check: Compare active positions across selected traders. Flag >50% position overlap.
2e. Allocation weighting: Score-weighted allocation with 35% cap per slot. Re-normalize after capping.
Show the user: trader address, rank, labels, win rate, allocation amount. Wait for approval before executing.
For each slot:
strategy_create_mirrorSee references/daily-monitoring.md for the complete daily check procedure, swap criteria, and rebalance logic.
Swap criteria (ALL must be true):
watchCount)Key principle: The 2-day watch period prevents churn from temporary dips.
To exit: close all mirror strategies, return funds to main wallet.
discovery_top_traders — trader leaderboardstrategy_create_mirror — create mirror strategystrategy_get_clearinghouse_state — check positionsstrategy_close_strategy — teardownMirror strategies incur the same trading fees as the mirrored trader's activity. Budget ~0.5-1% daily in fees for active traders.
Weekly Installs
113
Repository
GitHub Stars
53
First Seen
Feb 27, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode111
gemini-cli111
github-copilot111
codex111
kimi-cli111
amp111
Skills CLI 使用指南:AI Agent 技能包管理器安装与管理教程
43,100 周安装