[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X9155ATEAMSXVGPH2GG39V":3,"skill-same:01M6X9155ATEAMSXVGPH2GG39V":89},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6X9155ATEAMSXVGPH2GG39V","mamba",null,"MAMBA v2.0 — Range-bound high water + regime protection. A trading strategy config override based on the VIPER skill with three protective gates: BTC regime filter, per-asset cooldown after losses, and hard leverage cap at 10x.","enuno\u002Fcrewless-capital","enuno","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6727752?v=4","01M6J09HF6Y74150F7PEMC446X","Elvis Nuno","01M6X86WGZG9RH09ACTSTJ2383",1,"MIT","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fmamba\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"Mamba","gates","viper","at","high","with","asset","filter","leverage","config","btc","three","hyperliquid","cap","protection","trading","strategy","10x","2026-11-10 10:12:30",false,"---\nname: mamba\ndescription: >-\n  MAMBA v2.0 — Range-bound high water + regime protection. A trading strategy\n  config override based on the VIPER skill with three protective gates: BTC regime\n  filter, per-asset cooldown after losses, and hard leverage cap at 10x.\nlicense: MIT\nmetadata:\n  author: jason-goldberg\n  version: \"2.0\"\n  platform: senpi\n  exchange: hyperliquid\n---\n\n# ? MAMBA v2.0 — Range-Bound High Water + Regime Protection\n\nA trading strategy (config override) based on the VIPER skill. Same scanner, same range detection, same support\u002Fresistance entries. Three new protective gates from v1.0 live data (37 trades, -31.4% ROI, $136 in fees).\n\n**Base skill:** [VIPER v2.1](https:\u002F\u002Fgithub.com\u002FSenpi-ai\u002Fsenpi-skills\u002Ftree\u002Fviper-2-0\u002Fviper)\n\n## What v2.0 Fixes\n\nMAMBA v1.0 lost -$313 on $1,000. The post-mortem revealed three distinct failure modes:\n\n| Failure | Trades | Loss | Fix |\n|---|---|---|---|\n| Longs in a downtrend (GOLD, PAXG, XYZ100, COPPER) | 14 | -$70+ | **BTC regime gate** |\n| Same asset re-entered after losses (GOLD 5x, PAXG 4x, XYZ100 5x) | ~14 | -$80+ | **4-hour per-asset cooldown** |\n| 15x desperation bets (BTC, XRP) | 2 | -$126 | **10x leverage hard cap** |\n\nThe 9 winning trades (+$143) proved the mean-reversion signal works. The losses came from entering that signal in conditions where mean reversion can't work (trending market, same broken setup, excessive leverage).\n\n## v2.0 Changes — Three Protective Gates\n\n### Gate 1: BTC Regime Filter (NEW — hard block)\n\nBefore any entry, check BTC 4H trend structure:\n\n- **BTC 4H BEARISH → block all LONG entries.** Mean reversion longs in a bear market = buying a dip that keeps dipping. This was trades #21-34.\n- **BTC 4H BULLISH → block all SHORT entries.** Mean reversion shorts in a bull market = shorting a rip that keeps ripping.\n- **BTC 4H NEUTRAL → both directions allowed.** Range-bound macro = range-bound entries work.\n\n**Implementation:** The agent must call `market_get_asset_data` for BTC with `candle_intervals: [\"4h\"]` before executing any Mamba entry. Check the last 6 candles for higher lows (bullish) or lower highs (bearish). If the regime opposes the signal direction, skip the entry entirely.\n\nThis is the single highest-impact change. It would have prevented 14+ losing trades.\n\n### Gate 2: Per-Asset Cooldown After Losses (NEW — 4 hours)\n\nAfter any losing exit on an asset, that specific asset is blocked for 4 hours.\n\n- GOLD exits at a loss → no GOLD entries for 4 hours\n- Other assets unaffected\n- After 4 hours, if the setup appears again with the regime gate passing, it's a valid fresh entry\n\n**Why 4 hours (not 2 like Vixen):** Mean-reversion setups take longer to reset than momentum setups. The range needs to re-establish after a breakdown. 4 hours gives enough time for the failed level to either confirm as broken (asset keeps trending) or rebuild (new range forms).\n\n**Implementation:** The agent tracks `{asset: exitTimestamp}` in state. Before executing, check if the asset has a losing exit within the last 4 hours.\n\n### Gate 3: Hard Leverage Cap at 10x (NEW)\n\n- **Maximum leverage: 10x.** No exceptions.\n- **Default leverage: 8x.** This is what v1.0 used on most trades and it's appropriate for mean-reversion.\n- **Never exceed 10x.** The 15x BTC\u002FXRP shorts lost -$126 combined. Mean reversion captures small moves back to the mean — it doesn't need high leverage.\n\n**Implementation:** If the agent computes leverage > 10x for any reason, cap it at 10.\n\n## MANDATORY: DSL High Water Mode\n\n**MAMBA MUST use DSL High Water Mode. This is not optional.**\n\nSpec: https:\u002F\u002Fgithub.com\u002FSenpi-ai\u002Fsenpi-skills\u002Fblob\u002Fmain\u002Fdsl-dynamic-stop-loss\u002Fdsl-high-water-spec%201.0.md\n\n```json\n{\n  \"lockMode\": \"pct_of_high_water\",\n  \"phase2TriggerRoe\": 5,\n  \"tiers\": [\n    {\"triggerPct\": 5,  \"lockHwPct\": 30, \"consecutiveBreachesRequired\": 3},\n    {\"triggerPct\": 10, \"lockHwPct\": 50, \"consecutiveBreachesRequired\": 2},\n    {\"triggerPct\": 15, \"lockHwPct\": 70, \"consecutiveBreachesRequired\": 2},\n    {\"triggerPct\": 20, \"lockHwPct\": 85, \"consecutiveBreachesRequired\": 1}\n  ]\n}\n```\n\n## Config Override File (v2.0)\n\n```json\n{\n  \"basedOn\": \"viper-2.1\",\n  \"version\": \"2.0\",\n  \"name\": \"Mamba\",\n  \"description\": \"Range-bound entries + High Water trailing + regime protection + per-asset cooldown\",\n\n  \"entry\": {\n    \"maxBbWidthPct\": 4.0,\n    \"maxAtrPct\": 1.5,\n    \"rsiOversold\": 35,\n    \"rsiOverbought\": 65,\n    \"minScore\": 5,\n    \"marginPct\": 0.28,\n    \"minOiUsd\": 5000000,\n    \"regimeFilter\": {\n      \"enabled\": true,\n      \"asset\": \"BTC\",\n      \"interval\": \"4h\",\n      \"lookback\": 6,\n      \"blockLongsInBearish\": true,\n      \"blockShortsInBullish\": true,\n      \"_note\": \"Check BTC 4H trend before every entry. Block counter-trend mean reversion.\"\n    },\n    \"assetCooldown\": {\n      \"enabled\": true,\n      \"cooldownMinutesAfterLoss\": 240,\n      \"_note\": \"4-hour cooldown per asset after a losing exit. Mean reversion needs time to reset.\"\n    },\n    \"bannedPrefixes\": [\"xyz:\"],\n    \"_note_banned\": \"XYZ equities (GOLD, PAXG, NVDA, etc.) accounted for -$80+ in v1.0 losses. SM data is weak for equities on Hyperliquid. Ban until proven otherwise.\"\n  },\n\n  \"leverage\": {\n    \"default\": 8,\n    \"min\": 5,\n    \"max\": 10,\n    \"_note\": \"Hard cap at 10x. Mean reversion captures small moves — doesn't need 15x. The 15x BTC\u002FXRP shorts lost -$126.\"\n  },\n\n  \"dsl\": {\n    \"_spec\": \"https:\u002F\u002Fgithub.com\u002FSenpi-ai\u002Fsenpi-skills\u002Fblob\u002Fmain\u002Fdsl-dynamic-stop-loss\u002Fdsl-high-water-spec%201.0.md\",\n    \"lockMode\": \"pct_of_high_water\",\n    \"phase2TriggerRoe\": 5,\n    \"phase1RetraceRoe\": 10,\n    \"phase1HardTimeoutMin\": 0,\n    \"phase1WeakPeakMin\": 0,\n    \"phase1DeadWeightMin\": 0,\n    \"convictionTiers\": [\n      {\"minScore\": 5, \"absoluteFloorRoe\": -15, \"hardTimeoutMin\": 0, \"weakPeakCutMin\": 0, \"deadWeightCutMin\": 0},\n      {\"minScore\": 7, \"absoluteFloorRoe\": -20, \"hardTimeoutMin\": 0, \"weakPeakCutMin\": 0, \"deadWeightCutMin\": 0},\n      {\"minScore\": 9, \"absoluteFloorRoe\": 0,   \"hardTimeoutMin\": 0, \"weakPeakCutMin\": 0, \"deadWeightCutMin\": 0}\n    ],\n    \"tiers\": [\n      {\"triggerPct\": 5,  \"lockHwPct\": 30, \"consecutiveBreachesRequired\": 3},\n      {\"triggerPct\": 10, \"lockHwPct\": 50, \"consecutiveBreachesRequired\": 2},\n      {\"triggerPct\": 15, \"lockHwPct\": 70, \"consecutiveBreachesRequired\": 2},\n      {\"triggerPct\": 20, \"lockHwPct\": 85, \"consecutiveBreachesRequired\": 1}\n    ],\n    \"stagnationTp\": {\n      \"enabled\": true,\n      \"roeMin\": 8,\n      \"hwStaleMin\": 45\n    }\n  },\n\n  \"risk\": {\n    \"maxEntriesPerDay\": 6,\n    \"maxDailyLossPct\": 8,\n    \"maxDrawdownPct\": 18,\n    \"maxSingleLossPct\": 5,\n    \"maxConsecutiveLosses\": 3,\n    \"cooldownMinutes\": 30\n  },\n\n  \"execution\": {\n    \"entryOrderType\": \"FEE_OPTIMIZED_LIMIT\",\n    \"entryEnsureTaker\": true,\n    \"exitOrderType\": \"MARKET\",\n    \"slOrderType\": \"MARKET\",\n    \"takeProfitOrderType\": \"FEE_OPTIMIZED_LIMIT\"\n  }\n}\n```\n\n## Key Changes from v1.0\n\n| Setting | v1.0 | v2.0 | Impact |\n|---|---|---|---|\n| BTC regime gate | None | **Hard block** | Prevents longs in bear, shorts in bull |\n| Per-asset cooldown | None | **4 hours after loss** | Prevents re-entering failed setups |\n| Leverage cap | Uncapped (agent went to 15x) | **Hard cap 10x, default 8x** | Eliminates desperation bets |\n| XYZ equities | Allowed | **Banned** | Removes -$80+ in weak-SM-data losses |\n| Max entries\u002Fday | 8 | **6** | Fewer trades, less fee drag |\n| Max consecutive losses | 4 | **3** | Faster cooldown trigger |\n| Cooldown after consecutive losses | 20 min | **30 min** | More recovery time |\n\n## v1.0 → v2.0 Simulated Impact\n\nApplying v2.0 rules retroactively to v1.0's 37 trades:\n\n| | v1.0 (actual) | v2.0 (simulated) |\n|---|---|---|\n| Trades taken | 37 | ~15-18 (regime gate + cooldown blocks ~20 trades) |\n| Fees | $136 | ~$55-65 |\n| Worst losses | BTC 15x (-$65), XRP 15x (-$61) | Blocked (leverage cap + regime gate) |\n| GOLD\u002FPAXG\u002FXYZ100 repeat losses | -$80+ | Blocked after first loss (cooldown) |\n| Winners preserved | 9 wins (+$143) | ~7-8 wins preserved (~$120-130) |\n| Estimated net | -$313 | **~+$30 to +$60** |\n\nThe 9 winning trades were mostly early-session shorts during neutral\u002Fbearish conditions — they'd pass the regime gate. Most of the 28 losers were longs during bearish conditions or repeat entries on the same failing asset — they'd be blocked.\n\n## Agent Instructions (v2.0 Entry Checklist)\n\nBefore executing any Mamba entry, the agent MUST check ALL of these in order:\n\n1. **Leverage ≤ 10x?** If not, cap at 10x. If exchange max is below 5x, skip entirely.\n2. **Asset banned?** If it starts with `xyz:`, skip.\n3. **Asset in cooldown?** Check state for losing exit within last 4 hours. If yes, skip.\n4. **BTC regime allows this direction?** Fetch BTC 4H candles, check trend. Bearish = no longs. Bullish = no shorts. Neutral = both OK.\n5. **All standard Viper entry gates pass?** BB width, ATR, RSI, volume, score.\n6. **Slot available?** Max 3 positions.\n7. **Daily entry limit?** Max 6\u002Fday.\n\nIf ALL pass → enter. If any fails → skip, NO_REPLY.\n\n## Notification Policy\n\n**ONLY alert:** Position OPENED or CLOSED, risk guardian triggered, critical error.\n**NEVER alert:** Scanner found nothing, regime gate blocked, cooldown blocked, DSL routine check, any reasoning.\n\n## Expected Behavior (v2.0)\n\n| Metric | v1.0 (actual) | v2.0 (expected) |\n|---|---|---|\n| Trades\u002Fday | ~12 | 4-6 |\n| Win rate | 24% | ~45-55% (bad entries filtered) |\n| Avg winner | +$15.85 | +$15-20 (same good trades preserved) |\n| Avg loser | -$11.42 | -$8-12 (no 15x blowups, faster cooldown) |\n| Fee drag\u002Fday | $45+ | ~$15-20 |\n| Net PnL\u002Fday | -$100+ | Target breakeven to +$20 |\n\n## License\n\nMIT — Built by Senpi (https:\u002F\u002Fsenpi.ai).\nSource: https:\u002F\u002Fgithub.com\u002FSenpi-ai\u002Fsenpi-skills\n","# ? MAMBA v2.0 — Range-Bound High Water + Regime Protection\n\nA trading strategy (config override) based on the VIPER skill. Same scanner, same range detection, same support\u002Fresistance entries. Three new protective gates from v1.0 live data (37 trades, -31.4% ROI, $136 in fees).\n\n**Base skill:** [VIPER v2.1](https:\u002F\u002Fgithub.com\u002FSenpi-ai\u002Fsenpi-skills\u002Ftree\u002Fviper-2-0\u002Fviper)\n\n## What v2.0 Fixes\n\nMAMBA v1.0 lost -$313 on $1,000. The post-mortem revealed three distinct failure modes:\n\n| Failure | Trades | Loss | Fix |\n|---|---|---|---|\n| Longs in a downtrend (GOLD, PAXG, XYZ100, COPPER) | 14 | -$70+ | **BTC regime gate** |\n| Same asset re-entered after losses (GOLD 5x, PAXG 4x, XYZ100 5x) | ~14 | -$80+ | **4-hour per-asset cooldown** |\n| 15x desperation bets (BTC, XRP) | 2 | -$126 | **10x leverage hard cap** |\n\nThe 9 winning trades (+$143) proved the mean-reversion signal works. The losses came from entering that signal in conditions where mean reversion can't work (trending market, same broken setup, excessive leverage).\n\n## v2.0 Changes — Three Protective Gates\n\n### Gate 1: BTC Regime Filter (NEW — hard block)\n\nBefore any entry, check BTC 4H trend structure:\n\n- **BTC 4H BEARISH → block all LONG entries.** Mean reversion longs in a bear market = buying a dip that keeps dipping. This was trades #21-34.\n- **BTC 4H BULLISH → block all SHORT entries.** Mean reversion shorts in a bull market = shorting a rip that keeps ripping.\n- **BTC 4H NEUTRAL → both directions allowed.** Range-bound macro = range-bound entries work.\n\n**Implementation:** The agent must call `market_get_asset_data` for BTC with `candle_intervals: [\"4h\"]` before executing any Mamba entry. Check the last 6 candles for higher lows (bullish) or lower highs (bearish). If the regime opposes the signal direction, skip the entry entirely.\n\nThis is the single highest-impact change. It would have prevented 14+ losing trades.\n\n### Gate 2: Per-Asset Cooldown After Losses (NEW — 4 hours)\n\nAfter any losing exit on an asset, that specific asset is blocked for 4 hours.\n\n- GOLD exits at a loss → no GOLD entries for 4 hours\n- Other assets unaffected\n- After 4 hours, if the setup appears again with the regime gate passing, it's a valid fresh entry\n\n**Why 4 hours (not 2 like Vixen):** Mean-reversion setups take longer to reset than momentum setups. The range needs to re-establish after a breakdown. 4 hours gives enough time for the failed level to either confirm as broken (asset keeps trending) or rebuild (new range forms).\n\n**Implementation:** The agent tracks `{asset: exitTimestamp}` in state. Before executing, check if the asset has a losing exit within the last 4 hours.\n\n### Gate 3: Hard Leverage Cap at 10x (NEW)\n\n- **Maximum leverage: 10x.** No exceptions.\n- **Default leverage: 8x.** This is what v1.0 used on most trades and it's appropriate for mean-reversion.\n- **Never exceed 10x.** The 15x BTC\u002FXRP shorts lost -$126 combined. Mean reversion captures small moves back to the mean — it doesn't need high leverage.\n\n**Implementation:** If the agent computes leverage > 10x for any reason, cap it at 10.\n\n## MANDATORY: DSL High Water Mode\n\n**MAMBA MUST use DSL High Water Mode. This is not optional.**\n\nSpec: https:\u002F\u002Fgithub.com\u002FSenpi-ai\u002Fsenpi-skills\u002Fblob\u002Fmain\u002Fdsl-dynamic-stop-loss\u002Fdsl-high-water-spec%201.0.md\n\n```json\n{\n  \"lockMode\": \"pct_of_high_water\",\n  \"phase2TriggerRoe\": 5,\n  \"tiers\": [\n    {\"triggerPct\": 5,  \"lockHwPct\": 30, \"consecutiveBreachesRequired\": 3},\n    {\"triggerPct\": 10, \"lockHwPct\": 50, \"consecutiveBreachesRequired\": 2},\n    {\"triggerPct\": 15, \"lockHwPct\": 70, \"consecutiveBreachesRequired\": 2},\n    {\"triggerPct\": 20, \"lockHwPct\": 85, \"consecutiveBreachesRequired\": 1}\n  ]\n}\n```\n\n## Config Override File (v2.0)\n\n```json\n{\n  \"basedOn\": \"viper-2.1\",\n  \"version\": \"2.0\",\n  \"name\": \"Mamba\",\n  \"description\": \"Range-bound entries + High Water trailing + regime protection + per-asset cooldown\",\n\n  \"entry\": {\n    \"maxBbWidthPct\": 4.0,\n    \"maxAtrPct\": 1.5,\n    \"rsiOversold\": 35,\n    \"rsiOverbought\": 65,\n    \"minScore\": 5,\n    \"marginPct\": 0.28,\n    \"minOiUsd\": 5000000,\n    \"regimeFilter\": {\n      \"enabled\": true,\n      \"asset\": \"BTC\",\n      \"interval\": \"4h\",\n      \"lookback\": 6,\n      \"blockLongsInBearish\": true,\n      \"blockShortsInBullish\": true,\n      \"_note\": \"Check BTC 4H trend before every entry. Block counter-trend mean reversion.\"\n    },\n    \"assetCooldown\": {\n      \"enabled\": true,\n      \"cooldownMinutesAfterLoss\": 240,\n      \"_note\": \"4-hour cooldown per asset after a losing exit. Mean reversion needs time to reset.\"\n    },\n    \"bannedPrefixes\": [\"xyz:\"],\n    \"_note_banned\": \"XYZ equities (GOLD, PAXG, NVDA, etc.) accounted for -$80+ in v1.0 losses. SM data is weak for equities on Hyperliquid. Ban until proven otherwise.\"\n  },\n\n  \"leverage\": {\n    \"default\": 8,\n    \"min\": 5,\n    \"max\": 10,\n    \"_note\": \"Hard cap at 10x. Mean reversion captures small moves — doesn't need 15x. The 15x BTC\u002FXRP shorts lost -$126.\"\n  },\n\n  \"dsl\": {\n    \"_spec\": \"https:\u002F\u002Fgithub.com\u002FSenpi-ai\u002Fsenpi-skills\u002Fblob\u002Fmain\u002Fdsl-dynamic-stop-loss\u002Fdsl-high-water-spec%201.0.md\",\n    \"lockMode\": \"pct_of_high_water\",\n    \"phase2TriggerRoe\": 5,\n    \"phase1RetraceRoe\": 10,\n    \"phase1HardTimeoutMin\": 0,\n    \"phase1WeakPeakMin\": 0,\n    \"phase1DeadWeightMin\": 0,\n    \"convictionTiers\": [\n      {\"minScore\": 5, \"absoluteFloorRoe\": -15, \"hardTimeoutMin\": 0, \"weakPeakCutMin\": 0, \"deadWeightCutMin\": 0},\n      {\"minScore\": 7, \"absoluteFloorRoe\": -20, \"hardTimeoutMin\": 0, \"weakPeakCutMin\": 0, \"deadWeightCutMin\": 0},\n      {\"minScore\": 9, \"absoluteFloorRoe\": 0,   \"hardTimeoutMin\": 0, \"weakPeakCutMin\": 0, \"deadWeightCutMin\": 0}\n    ],\n    \"tiers\": [\n      {\"triggerPct\": 5,  \"lockHwPct\": 30, \"consecutiveBreachesRequired\": 3},\n      {\"triggerPct\": 10, \"lockHwPct\": 50, \"consecutiveBreachesRequired\": 2},\n      {\"triggerPct\": 15, \"lockHwPct\": 70, \"consecutiveBreachesRequired\": 2},\n      {\"triggerPct\": 20, \"lockHwPct\": 85, \"consecutiveBreachesRequired\": 1}\n    ],\n    \"stagnationTp\": {\n      \"enabled\": true,\n      \"roeMin\": 8,\n      \"hwStaleMin\": 45\n    }\n  },\n\n  \"risk\": {\n    \"maxEntriesPerDay\": 6,\n    \"maxDailyLossPct\": 8,\n    \"maxDrawdownPct\": 18,\n    \"maxSingleLossPct\": 5,\n    \"maxConsecutiveLosses\": 3,\n    \"cooldownMinutes\": 30\n  },\n\n  \"execution\": {\n    \"entryOrderType\": \"FEE_OPTIMIZED_LIMIT\",\n    \"entryEnsureTaker\": true,\n    \"exitOrderType\": \"MARKET\",\n    \"slOrderType\": \"MARKET\",\n    \"takeProfitOrderType\": \"FEE_OPTIMIZED_LIMIT\"\n  }\n}\n```\n\n## Key Changes from v1.0\n\n| Setting | v1.0 | v2.0 | Impact |\n|---|---|---|---|\n| BTC regime gate | None | **Hard block** | Prevents longs in bear, shorts in bull |\n| Per-asset cooldown | None | **4 hours after loss** | Prevents re-entering failed setups |\n| Leverage cap | Uncapped (agent went to 15x) | **Hard cap 10x, default 8x** | Eliminates desperation bets |\n| XYZ equities | Allowed | **Banned** | Removes -$80+ in weak-SM-data losses |\n| Max entries\u002Fday | 8 | **6** | Fewer trades, less fee drag |\n| Max consecutive losses | 4 | **3** | Faster cooldown trigger |\n| Cooldown after consecutive losses | 20 min | **30 min** | More recovery time |\n\n## v1.0 → v2.0 Simulated Impact\n\nApplying v2.0 rules retroactively to v1.0's 37 trades:\n\n| | v1.0 (actual) | v2.0 (simulated) |\n|---|---|---|\n| Trades taken | 37 | ~15-18 (regime gate + cooldown blocks ~20 trades) |\n| Fees | $136 | ~$55-65 |\n| Worst losses | BTC 15x (-$65), XRP 15x (-$61) | Blocked (leverage cap + regime gate) |\n| GOLD\u002FPAXG\u002FXYZ100 repeat losses | -$80+ | Blocked after first loss (cooldown) |\n| Winners preserved | 9 wins (+$143) | ~7-8 wins preserved (~$120-130) |\n| Estimated net | -$313 | **~+$30 to +$60** |\n\nThe 9 winning trades were mostly early-session shorts during neutral\u002Fbearish conditions — they'd pass the regime gate. Most of the 28 losers were longs during bearish conditions or repeat entries on the same failing asset — they'd be blocked.\n\n## Agent Instructions (v2.0 Entry Checklist)\n\nBefore executing any Mamba entry, the agent MUST check ALL of these in order:\n\n1. **Leverage ≤ 10x?** If not, cap at 10x. If exchange max is below 5x, skip entirely.\n2. **Asset banned?** If it starts with `xyz:`, skip.\n3. **Asset in cooldown?** Check state for losing exit within last 4 hours. If yes, skip.\n4. **BTC regime allows this direction?** Fetch BTC 4H candles, check trend. Bearish = no longs. Bullish = no shorts. Neutral = both OK.\n5. **All standard Viper entry gates pass?** BB width, ATR, RSI, volume, score.\n6. **Slot available?** Max 3 positions.\n7. **Daily entry limit?** Max 6\u002Fday.\n\nIf ALL pass → enter. If any fails → skip, NO_REPLY.\n\n## Notification Policy\n\n**ONLY alert:** Position OPENED or CLOSED, risk guardian triggered, critical error.\n**NEVER alert:** Scanner found nothing, regime gate blocked, cooldown blocked, DSL routine check, any reasoning.\n\n## Expected Behavior (v2.0)\n\n| Metric | v1.0 (actual) | v2.0 (expected) |\n|---|---|---|\n| Trades\u002Fday | ~12 | 4-6 |\n| Win rate | 24% | ~45-55% (bad entries filtered) |\n| Avg winner | +$15.85 | +$15-20 (same good trades preserved) |\n| Avg loser | -$11.42 | -$8-12 (no 15x blowups, faster cooldown) |\n| Fee drag\u002Fday | $45+ | ~$15-20 |\n| Net PnL\u002Fday | -$100+ | Target breakeven to +$20 |\n\n## License\n\nMIT — Built by Senpi (https:\u002F\u002Fsenpi.ai).\nSource: https:\u002F\u002Fgithub.com\u002FSenpi-ai\u002Fsenpi-skills\n",{"name":5,"license":15,"metadata":42,"description":7},{"author":43,"version":44,"exchange":31,"platform":45},"jason-goldberg","2.0","senpi","main","bfe4e4653cba696a8dc20f70c6006651b997fdef","migrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fmamba",0,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital","https:\u002F\u002Fgithub.com\u002Fenuno","https:\u002F\u002Fenuno.github.io\u002FDynamicCareerCanvas","Digital Nomad, Blockchain Evangel, and Digital Solutions Architect. \r\nCreator of TerraHash Stack.\r\nCEO of Ryno Crypto Mining Services.","2026-07-02 10:49:15",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add enuno\u002Fcrewless-capital --skill mamba",{"tool":61,"command":62},"bunx","bunx skills add enuno\u002Fcrewless-capital --skill mamba",{"tool":64,"command":65},"pnpm","pnpm dlx skills add enuno\u002Fcrewless-capital --skill mamba","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fmamba\u002FSKILL.md",true,[69,75,79,85],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"config\u002Fmamba-config.json","REFERENCE","参考文档",2424,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fmamba\u002Fconfig\u002Fmamba-config.json",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"README.md",1839,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fmamba\u002FREADME.md",{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Fmamba_config.py","SCRIPT","脚本",6512,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fmamba\u002Fscripts\u002Fmamba_config.py",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fmamba-scanner.py",12100,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fmamba\u002Fscripts\u002Fmamba-scanner.py",[90,122,143,168,193,214],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":102,"publishedAt":37},"01M6X94YFR1XNANZ321FS661NG","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\u002Fdynamic facts, and RAG for semantic search. Perfect for chatbots, assistants, and knowledge-intensive applications.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsupermemory\u002FSKILL.md",[97],{"categoryNo":98,"categoryName":99,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[92,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"ai agents","memory","rag","semantic search","infrastructure","search","applications","api","knowledge","context","Art","personalization","across","learned","retention","for","persistent memory","static","when",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":37},"01M6X94S3K97CSK7VFF5H85ED2","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\u002F27 trades before DSL could manage them. v2.0 removes thesis exit entirely. Scanner decides entries (score 8+, 4H\u002F1H 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\u002Fday. 3-hour cooldown between entries. DSL exit managed by plugin runtime via runtime.yaml.","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fwolverine\u002FSKILL.md",[],[35,129,130,131,132,133,134,34,135,136,137,31,138,27,139,22,118,140,141,142],"wolverine strategy","architecture","alpha","Volatility","consensus","only","scanner","manage","max","runtime","hunter","managed","dsl","phase",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":152,"publishedAt":37},"01M6X94HN3CHBM37GM2C84KT26","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).","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fwolf-strategy\u002FSKILL.md",[149],{"categoryNo":150,"categoryName":151,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000023","Skill与智能体开发",[35,153,154,155,130,156,157,158,159,160,161,162,163,27,164,165,22,166,167,118],"wolf strategy","MCP","openclaw","health","system","python3","check","health check","stop","strategies","shared","connection","wallets","stop-loss","hyperliquid perps",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":37},"01M6X949FBGWWGY3YZ8N3WB3CP","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.","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fwolf-howl\u002FSKILL.md",[174],{"categoryNo":150,"categoryName":151,"taxonomyType":100,"taxonomyTypeDesc":101},[176,154,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,141,192,121],"wolf howl","review","performance","learn","analysis","loop","analyze","short","autonomous","up","optimize","drift","self","factor","loops","profit","fdr",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":199,"publishedAt":37},"01M6X9437CQ55N5AYHCPF71JWG","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.","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fwhale-index\u002FSKILL.md",[],[200,201,202,178,203,204,205,206,207,185,208,209,162,24,210,211,212,118,213,121],"index","whale","whale index","auth","monitoring","discovery","use","auto","daily","time","consistency","top","mirror","pnl",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":220,"publishedAt":37},"01M6X93YTRGNPYNHZRTW9XNH1E","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.","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fcrewless-capital\u002Fblob\u002Fmain\u002Fmigrate-hyperliquid-firm\u002Fskills\u002Fsenpi-skills\u002Fvixen\u002FSKILL.md",[],[35,221,222,223,224,225,135,226,26,25,24,227,228,23,229,230,231,232,141,142],"vixen strategy","roi","data","first","confirmation","volume","explosion","mode","v1","modes","emerging movers","entry"]