shark
SHARK v3.0 — SM Conviction + Liquidation Cascade Hunter. Consolidated from v1.0's 8-cron pipeline into a single scanner. 4-gate entry: SM concentration (30+ traders, 5%+) → top 5 trader alignment → price momentum → funding structure. Score 8+ to enter. DSL manages all exits. No thesis exit. DSL exit managed by plugin runtime via runtime.yaml.
- License 许可
- MIT
- 最近更新
- 2026-07-02
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- shark
- license
- MIT
- metadata
- { "author": "jason-goldberg", "version": "3.0", "exchange": "hyperliquid", "platform": "senpi", "requires": [ "senpi-trading-runtime" ] }
- description
- SHARK v3.0 — SM Conviction + Liquidation Cascade Hunter. Consolidated from v1.0's 8-cron pipeline into a single scanner. 4-gate entry: SM concentration (30+ traders, 5%+) → top 5 trader alignment → price momentum → funding structure. Score 8+ to enter. DSL manages all exits. No thesis exit. DSL exit managed by plugin runtime via runtime.yaml.
02 资源文件 4
- 参考文档runtime.yaml1.4 KB
- 脚本scripts/shark_config.py18.7 KB
- 脚本scripts/shark-health.py6.9 KB
- 脚本scripts/shark-scanner.py17.2 KB
03 SKILL.md 正文
? SHARK v3.0 — SM Conviction + Liquidation Cascade Hunter
Four gates. One scanner. DSL manages exits.
⛔ CRITICAL AGENT RULES
RULE 1: Install path is /data/workspace/skills/shark/
RULE 2: THE SCANNER DOES NOT EXIT POSITIONS
When the scanner sees an active position, it outputs NO_REPLY. DSL is the ONLY exit mechanism. v1.0 lost -4.6% partly because the scanner kept cycling positions rapidly, generating $144/day in fees. v2.0 lets positions run until DSL trails or cuts them.
RULE 3: MAX 2 POSITIONS at a time
RULE 4: Scanner output is AUTHORITATIVE
RULE 5: Verify runtime is installed on every session start
Run openclaw senpi runtime list. Runtime must be listed. The position tracker and DSL exit are handled by the plugin runtime.
RULE 6: Never retry timed-out position creation
If create_position times out, check clearinghouse state. If position exists, the position tracker will pick it up automatically. If not, wait for next scan.
RULE 7: Never modify parameters
RULE 8: 120-minute per-asset cooldown
What Changed From v1.0
| v1.0 | v2.0 |
|---|---|
| 10 scripts, 8 crons | 1 scanner + DSL + risk (3 crons) |
| Pipeline: mapper → proximity → entry | Single 4-gate scan |
| Thesis exit active | Thesis exit REMOVED |
| No DSL state generation | Full DSL v1.1.1 state with wallet |
| Crons kept dying silently | Fewer moving parts = more reliable |
| 68 fills, -4.6% | Fewer trades, higher conviction |
The 4 Gates
Every candidate must pass ALL 4 gates to enter:
| Gate | Check | Threshold |
|---|---|---|
| 1. SM Concentration | leaderboard_get_markets | 5%+ gain share, 30+ traders |
| 2. Top 5 Alignment | leaderboard_get_top → trader positions | 2+ of top 5 in same direction |
| 3. Price Momentum | 4H and/or 1H price change aligned | At least one timeframe confirming |
| 4. Funding Structure | Funding rate confirming directional pressure | Funding aligned or neutral |
Scoring: SM concentration (0-3 pts) + top alignment (0-3 pts) + momentum (0-2 pts) + contribution acceleration (0-1 pts) + funding (0-1 pts). Score 8+ to enter.
Exit Management
DSL exit is handled by the plugin runtime via runtime.yaml. The position_tracker scanner auto-detects position opens/closes on-chain. See runtime.yaml for configuration details.
Monitor positions:
openclaw senpi dsl positions— list all DSL-tracked positionsopenclaw senpi dsl inspect <ASSET>— full position details
Runtime Setup
Step 1: Set your strategy wallet address in runtime.yaml:
sed -i 's/${WALLET_ADDRESS}/<STRATEGY_WALLET_ADDRESS>/' /data/workspace/skills/shark/runtime.yaml
Replace <STRATEGY_WALLET_ADDRESS> with the actual wallet address.
Step 2: Set telegram chat ID for notifications:
sed -i 's/${TELEGRAM_CHAT_ID}/<CHAT_ID>/' /data/workspace/skills/shark/runtime.yaml
Replace <CHAT_ID> with the actual Telegram chat ID.
Step 3: Install the runtime:
openclaw senpi runtime create --path /data/workspace/skills/shark/runtime.yaml
Step 4: Verify:
openclaw senpi runtime list
Bootstrap Gate
On EVERY session start, check config/bootstrap-complete.json. If missing:
- Read the senpi-trading-runtime skill:
cat /data/workspace/skills/senpi-trading-runtime/SKILL.md— this provides all CLI commands for runtime management and DSL position inspection. - Verify Senpi MCP
- Set wallet in runtime.yaml:
sed -i 's/${WALLET_ADDRESS}/ACTUAL_ADDRESS/' /data/workspace/skills/shark/runtime.yaml - Set Telegram in runtime.yaml:
sed -i 's/${TELEGRAM_CHAT_ID}/CHAT_ID/' /data/workspace/skills/shark/runtime.yaml - Install runtime:
openclaw senpi runtime create --path /data/workspace/skills/shark/runtime.yaml - Verify runtime installed:
openclaw senpi runtime list - Remove old DSL cron (if upgrading): run
openclaw crons list, delete any cron containingdsl-v5.pyviaopenclaw crons delete <id> - Create scanner cron (5 min, main)
- Write
config/bootstrap-complete.json - Send: "? SHARK v3.0 online. SM Conviction + Liquidation Cascade Hunter. 4-gate entry, score 8+. DSL managed by plugin runtime. Silence = no conviction."
If bootstrap exists, still verify runtime and scanner cron on every session start.
Risk
| Rule | Value |
|---|---|
| Max positions | 2 |
| Max entries/day | 4 |
| Leverage | 7x |
| Per-asset cooldown | 120 min |
| Daily loss limit | 12% |
| Consecutive losses | 3 → 45 min cooldown |
| XYZ | Banned |
Expected Behavior
| Metric | Expected |
|---|---|
| Entries/day | 0-3 (many zero-trade days) |
| Win rate | ~50% |
| Avg winner | 2-3x avg loser |
| Position duration | 15 min to 6+ hours |
License
MIT — Built by Senpi (https://senpi.ai).
04 同仓库更多 Skills
supermemory
Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for static/dynamic facts, and RAG for semantic search. Perfect for chatbots, assistants, and knowledge-intensive applications.
wolverine-strategy
WOLVERINE v2.0 — HYPE alpha hunter. Entry-only scanner, DSL-exit-only architecture. v1.1 lost -22.7% because the scanner's thesis exit chopped 25/27 trades before DSL could manage them. v2.0 removes thesis exit entirely. Scanner decides entries (score 8+, 4H/1H aligned, SM consensus). DSL manages all exits (wide Phase 1 for HYPE volatility, trailing tiers starting at +15% ROE). Leverage lowered to 7x. Max 4 entries/day. 3-hour cooldown between entries. DSL exit managed by plugin runtime via runtime.yaml.
wolf-strategy
WOLF v6.3 — Fully autonomous multi-strategy trading for Hyperliquid perps via Senpi MCP. Manages multiple strategies simultaneously, each with independent wallets, budgets, slots, and DSL configs. 5+N cron architecture: 5 shared wolf crons (Emerging Movers 3min, SM Flip 5min, Watchdog 5min, Risk Guardian 5min, Health Check 10min) plus one DSL v5.2 cron per strategy (native Hyperliquid SL sync via dsl-dynamic-stop-loss skill v5.3.1). Same asset can be traded in different strategies simultaneously. Enter early on first jumps, not at confirmed peaks. Dynamic risk-based leverage per strategy. Requires Senpi MCP connection, python3, mcporter CLI, OpenClaw cron system, and dsl-dynamic-stop-loss skill (provides dsl-cli.py + dsl-v5.py).
wolf-howl
HOWL v2 — Hunt, Optimize, Win, Learn. Nightly self-improvement loop for the WOLF autonomous trading strategy. Runs once per day (via cron) to review all trades from the last 24 hours, compute win rates, analyze signal quality correlation, evaluate DSL tier performance, identify missed opportunities, and produce concrete improvement suggestions for the wolf-strategy skill. v2 adds fee drag ratio (FDR) analysis, holding period bucketing, LONG vs SHORT regime detection, rotation cost tracking, cumulative drift detection, and gross vs net profit factor separation. Use when setting up daily trade review automation, analyzing trading performance, or improving an autonomous trading strategy through data-driven feedback loops. Requires Senpi MCP connection, mcporter CLI, and OpenClaw cron system.
whale-index
Auto-mirror top Discovery traders on Hyperliquid. Scans top 50 traders, scores on PnL rank (35%), win rate (25%), consistency (20%), hold time (10%), drawdown (10%). Creates 2-5 mirror strategies with overlap checks. Daily rebalance with 2-day watch period before swaps. Use when setting up trader mirroring, copy trading, or portfolio auto-rebalancing based on Discovery leaderboard performance.
vixen-strategy
VIXEN v1.0 — Dual-mode emerging movers scanner. Built from FOX v1.6 live trading data (+34.5% ROI). Two entry modes: STALKER (steady accumulation, score 6+, catches the SM buildup BEFORE the explosion) and STRIKER (violent FIRST_JUMP, score 9+, with raw volume confirmation to filter blow-off tops). 2-hour per-asset cooldown after Phase 1 exits. DSL High Water Mode mandatory.