[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J12GWQ4Z8WPDAPXS760FFT":3,"skill-same:01M6J12GWQ4Z8WPDAPXS760FFT":98},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6J12GWQ4Z8WPDAPXS760FFT","roach-strategy",null,"ROACH v1.0 — Striker-only scanner. Stalker mode disabled entirely. Tests whether Stalker adds any value or is pure drag. Only trades violent FIRST_JUMP explosions backed by 1.5x volume. Will have long stretches of silence — that patience is the edge. All hardened gates preserved. XYZ banned. Leverage 7-10x. DSL exit managed by plugin runtime via runtime.yaml.","enuno\u002Fhyperliquid-trading-firm","enuno","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6727752?v=4","01M6J09HF6Y74150F7PEMC446X","Elvis Nuno","01M6J09HKK0YMKE39JXT8JT8VM",1,"MIT","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Froach\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"roach strategy","strategy","volume","v1","mode","drag","long","leverage","tests","gates","runtime","plugin","hyperliquid","exit","scanner","trading","only","experiment","10x","edge","2026-11-10 10:12:30",false,"---\nname: roach-strategy\ndescription: >-\n  ROACH v1.0 — Striker-only scanner. Stalker mode disabled entirely. Tests\n  whether Stalker adds any value or is pure drag. Only trades violent FIRST_JUMP\n  explosions backed by 1.5x volume. Will have long stretches of silence — that\n  patience is the edge. All hardened gates preserved. XYZ banned. Leverage 7-10x.\n  DSL exit managed by plugin runtime via runtime.yaml.\nlicense: MIT\nmetadata:\n  author: jason-goldberg\n  version: \"2.0\"\n  platform: senpi\n  exchange: hyperliquid\n  config_source: striker-only-experiment\n  requires:\n    - senpi-trading-runtime\n---\n\n# ? ROACH v1.0 — Striker Only. Stalker Disabled.\n\nCockroaches survive anything. ROACH survives by not trading when there's no explosion.\n\n---\n\n## ⛔ CRITICAL AGENT RULES — READ BEFORE ANYTHING ELSE\n\n### RULE 1: Install path is `\u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002F`\n\nThe skill MUST be installed to exactly this path.\n\n### RULE 2: MAX 3 POSITIONS — check before EVERY entry\n\nBefore opening ANY position, call `strategy_get_clearinghouse_state` and count open positions. If positions >= 3, SKIP.\n\n### RULE 3: Scanner output is AUTHORITATIVE — never override from memory\n\nThe scanner is the single source of truth for all trading parameters.\n\n### RULE 4: Verify runtime is installed on every session start\n\nRun `openclaw senpi runtime list`. Runtime must be listed. The position tracker and DSL exit are handled by the plugin runtime.\n\n### RULE 5: Never retry timed-out position creation\n\nIf `create_position` times out, check clearinghouse state first.\n\n### RULE 6: Never modify your own configuration\n\nNo adjustments to leverage, margin, scoring, or any parameter.\n\n### RULE 7: Do NOT enable Stalker mode\n\nStalker is disabled by design. This is an experiment. Do not re-enable it, do not build your own accumulation detection, do not invent alternative entry logic. If the scanner outputs `\"stalkerDisabled\": true`, that means it's working correctly. Long periods of silence with zero trades are EXPECTED and CORRECT.\n\n---\n\n## The ROACH Experiment\n\n**Hypothesis:** Stalker mode is pure drag. Fox v1.0 produced 17 Stalker trades at score 6-7 with a 17.6% win rate and -$91.32 net P&L. The one Striker signal (ZEC LONG, score 11) was the only explosive entry worth taking. If ROACH outperforms or matches the other variants with dramatically fewer trades, Stalker should be permanently demoted or removed from the scanner.\n\n**What this means in practice:** ROACH will be quiet. Striker signals require FIRST_JUMP or IMMEDIATE_MOVER (10+ rank jump from #25+), rank jump >= 15 OR velocity > 15, volume >= 1.5x, score >= 9 with 4+ reasons. In choppy markets, this might fire 0-1 times per day. In trending markets with SM explosions, maybe 2-3.\n\n**The question:** Does fewer + higher quality beat more + mixed quality? Polar proved it at the macro level (29 trades, +28.1% vs Ghost Fox's 1,078 trades, -58.5%). ROACH tests it at the signal-type level within the same scanner framework.\n\n---\n\n## Single Entry Mode\n\n### STRIKER (Explosion) — Score >= 9, min 4 reasons\n- FIRST_JUMP or IMMEDIATE_MOVER (10+ rank jump from #25+)\n- Rank jump >= 15 OR contribution velocity > 15\n- Raw volume >= 1.5x of 6h average\n- Score >= 9 with at least 4 distinct reasons\n- 4H trend aligned, XYZ banned, asset not in cooldown\n\n### STALKER — DISABLED\n- Scanner still builds scan history (needed for Striker's rank jump detection)\n- Stalker signals are never generated or emitted\n- Output always contains `\"stalkerDisabled\": true` and `\"stalkerSignals\": []`\n\n---\n\n## Exit Management\n\nDSL exit is handled by the plugin runtime via `runtime.yaml`. The `position_tracker` scanner auto-detects position opens\u002Fcloses on-chain. See `runtime.yaml` for configuration details.\n\n**Entry flow:**\n1. Scanner outputs Striker signal\n2. Verify positions \u003C 3\n3. Verify exchange max leverage >= 7\n4. Call `create_position`\n5. Send ONE notification: position opened\n6. `position_tracker` detects the new position automatically\n7. Plugin DSL monitor applies trailing stop-loss protection\n\n**Monitor positions:**\n- `openclaw senpi dsl positions` — list all DSL-tracked positions\n- `openclaw senpi dsl inspect \u003CASSET>` — full position details\n\n---\n\n## Runtime Setup\n\n**Step 1:** Set your strategy wallet address in runtime.yaml:\n```bash\nsed -i 's\u002F${WALLET_ADDRESS}\u002F\u003CSTRATEGY_WALLET_ADDRESS>\u002F' \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml\n```\nReplace `\u003CSTRATEGY_WALLET_ADDRESS>` with the actual wallet address.\n\n**Step 2:** Set telegram chat ID for notifications:\n```bash\nsed -i 's\u002F${TELEGRAM_CHAT_ID}\u002F\u003CCHAT_ID>\u002F' \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml\n```\nReplace `\u003CCHAT_ID>` with the actual Telegram chat ID.\n\n**Step 3:** Install the runtime:\n```bash\nopenclaw senpi runtime create --path \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml\n```\n\n**Step 4:** Verify:\n```bash\nopenclaw senpi runtime list\n```\n\n---\n\n## Bootstrap Gate\n\nOn EVERY session start, check `config\u002Fbootstrap-complete.json`. If missing:\n1. Read the senpi-trading-runtime skill: `cat \u002Fdata\u002Fworkspace\u002Fskills\u002Fsenpi-trading-runtime\u002FSKILL.md` — this provides all CLI commands for runtime management and DSL position inspection.\n2. Verify Senpi MCP\n3. Set wallet in runtime.yaml: `sed -i 's\u002F${WALLET_ADDRESS}\u002FACTUAL_ADDRESS\u002F' \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml`\n4. Set Telegram in runtime.yaml: `sed -i 's\u002F${TELEGRAM_CHAT_ID}\u002FCHAT_ID\u002F' \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml`\n5. Install runtime: `openclaw senpi runtime create --path \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml`\n6. Verify runtime installed: `openclaw senpi runtime list`\n7. Remove old DSL cron (if upgrading): run `openclaw crons list`, delete any cron containing `dsl-v5.py` via `openclaw crons delete \u003Cid>`\n8. Create scanner cron (90s, main)\n9. Write `config\u002Fbootstrap-complete.json`\n10. Send: \"? ROACH v1.0 online. Striker only. Stalker disabled. Waiting for explosions. Silence = no explosion.\"\n\nIf bootstrap exists, still verify runtime and scanner cron on every session start.\n\n---\n\n## Expected Behavior\n\n| Metric | Expected |\n|---|---|\n| Trades\u002Fday (chop) | 0-1 |\n| Trades\u002Fday (trending) | 1-3 |\n| Days with zero trades | Common and correct |\n| Win rate | Higher than Stalker variants (60-70% target) |\n| Avg winner | Larger (explosive entries with 1.5x volume) |\n| Avg loser | Similar to other variants (DSL-managed) |\n| Total P&L | Hypothesis: matches or beats Stalker variants with far fewer trades |\n\n**SILENCE IS CORRECT.** If ROACH goes 24-48 hours without a trade, that means there were no FIRST_JUMP explosions worth taking. That's the experiment working, not a bug.\n\n---\n\n## Risk Management\n\n| Rule | Value |\n|---|---|\n| Max positions | 3 |\n| Max entries\u002Fday | 6 |\n| Leverage | 7-10x |\n| Daily loss limit | 10% |\n| Per-asset cooldown | 2 hours |\n| XYZ equities | Banned |\n| Stalker mode | DISABLED |\n\n---\n\n## Notification Policy\n\n**ONLY alert:** Position OPENED (Striker signal with score + reasons), position CLOSED (P&L + reason), critical error.\n\n**NEVER alert:** Scanner found no Striker signals (this is normal and expected), any reasoning about whether to enable Stalker, any analysis of market conditions.\n\n---\n\n## Files\n\n| File | Purpose |\n|---|---|\n| `scripts\u002Froach-scanner.py` | Striker-only scanner (Stalker disabled in run()) |\n| `scripts\u002Froach_config.py` | Config helper |\n| `config\u002Froach-config.json` | Config (Stalker settings present but unused) |\n| `runtime.yaml` | Runtime config for plugin (DSL exit + position tracker) |\n\n---\n\n## License\n\nMIT — Built by Senpi (https:\u002F\u002Fsenpi.ai).\nSource: https:\u002F\u002Fgithub.com\u002FSenpi-ai\u002Fsenpi-skills\n","# ? ROACH v1.0 — Striker Only. Stalker Disabled.\n\nCockroaches survive anything. ROACH survives by not trading when there's no explosion.\n\n---\n\n## ⛔ CRITICAL AGENT RULES — READ BEFORE ANYTHING ELSE\n\n### RULE 1: Install path is `\u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002F`\n\nThe skill MUST be installed to exactly this path.\n\n### RULE 2: MAX 3 POSITIONS — check before EVERY entry\n\nBefore opening ANY position, call `strategy_get_clearinghouse_state` and count open positions. If positions >= 3, SKIP.\n\n### RULE 3: Scanner output is AUTHORITATIVE — never override from memory\n\nThe scanner is the single source of truth for all trading parameters.\n\n### RULE 4: Verify runtime is installed on every session start\n\nRun `openclaw senpi runtime list`. Runtime must be listed. The position tracker and DSL exit are handled by the plugin runtime.\n\n### RULE 5: Never retry timed-out position creation\n\nIf `create_position` times out, check clearinghouse state first.\n\n### RULE 6: Never modify your own configuration\n\nNo adjustments to leverage, margin, scoring, or any parameter.\n\n### RULE 7: Do NOT enable Stalker mode\n\nStalker is disabled by design. This is an experiment. Do not re-enable it, do not build your own accumulation detection, do not invent alternative entry logic. If the scanner outputs `\"stalkerDisabled\": true`, that means it's working correctly. Long periods of silence with zero trades are EXPECTED and CORRECT.\n\n---\n\n## The ROACH Experiment\n\n**Hypothesis:** Stalker mode is pure drag. Fox v1.0 produced 17 Stalker trades at score 6-7 with a 17.6% win rate and -$91.32 net P&L. The one Striker signal (ZEC LONG, score 11) was the only explosive entry worth taking. If ROACH outperforms or matches the other variants with dramatically fewer trades, Stalker should be permanently demoted or removed from the scanner.\n\n**What this means in practice:** ROACH will be quiet. Striker signals require FIRST_JUMP or IMMEDIATE_MOVER (10+ rank jump from #25+), rank jump >= 15 OR velocity > 15, volume >= 1.5x, score >= 9 with 4+ reasons. In choppy markets, this might fire 0-1 times per day. In trending markets with SM explosions, maybe 2-3.\n\n**The question:** Does fewer + higher quality beat more + mixed quality? Polar proved it at the macro level (29 trades, +28.1% vs Ghost Fox's 1,078 trades, -58.5%). ROACH tests it at the signal-type level within the same scanner framework.\n\n---\n\n## Single Entry Mode\n\n### STRIKER (Explosion) — Score >= 9, min 4 reasons\n- FIRST_JUMP or IMMEDIATE_MOVER (10+ rank jump from #25+)\n- Rank jump >= 15 OR contribution velocity > 15\n- Raw volume >= 1.5x of 6h average\n- Score >= 9 with at least 4 distinct reasons\n- 4H trend aligned, XYZ banned, asset not in cooldown\n\n### STALKER — DISABLED\n- Scanner still builds scan history (needed for Striker's rank jump detection)\n- Stalker signals are never generated or emitted\n- Output always contains `\"stalkerDisabled\": true` and `\"stalkerSignals\": []`\n\n---\n\n## Exit Management\n\nDSL exit is handled by the plugin runtime via `runtime.yaml`. The `position_tracker` scanner auto-detects position opens\u002Fcloses on-chain. See `runtime.yaml` for configuration details.\n\n**Entry flow:**\n1. Scanner outputs Striker signal\n2. Verify positions \u003C 3\n3. Verify exchange max leverage >= 7\n4. Call `create_position`\n5. Send ONE notification: position opened\n6. `position_tracker` detects the new position automatically\n7. Plugin DSL monitor applies trailing stop-loss protection\n\n**Monitor positions:**\n- `openclaw senpi dsl positions` — list all DSL-tracked positions\n- `openclaw senpi dsl inspect \u003CASSET>` — full position details\n\n---\n\n## Runtime Setup\n\n**Step 1:** Set your strategy wallet address in runtime.yaml:\n```bash\nsed -i 's\u002F${WALLET_ADDRESS}\u002F\u003CSTRATEGY_WALLET_ADDRESS>\u002F' \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml\n```\nReplace `\u003CSTRATEGY_WALLET_ADDRESS>` with the actual wallet address.\n\n**Step 2:** Set telegram chat ID for notifications:\n```bash\nsed -i 's\u002F${TELEGRAM_CHAT_ID}\u002F\u003CCHAT_ID>\u002F' \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml\n```\nReplace `\u003CCHAT_ID>` with the actual Telegram chat ID.\n\n**Step 3:** Install the runtime:\n```bash\nopenclaw senpi runtime create --path \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml\n```\n\n**Step 4:** Verify:\n```bash\nopenclaw senpi runtime list\n```\n\n---\n\n## Bootstrap Gate\n\nOn EVERY session start, check `config\u002Fbootstrap-complete.json`. If missing:\n1. Read the senpi-trading-runtime skill: `cat \u002Fdata\u002Fworkspace\u002Fskills\u002Fsenpi-trading-runtime\u002FSKILL.md` — this provides all CLI commands for runtime management and DSL position inspection.\n2. Verify Senpi MCP\n3. Set wallet in runtime.yaml: `sed -i 's\u002F${WALLET_ADDRESS}\u002FACTUAL_ADDRESS\u002F' \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml`\n4. Set Telegram in runtime.yaml: `sed -i 's\u002F${TELEGRAM_CHAT_ID}\u002FCHAT_ID\u002F' \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml`\n5. Install runtime: `openclaw senpi runtime create --path \u002Fdata\u002Fworkspace\u002Fskills\u002Froach-strategy\u002Fruntime.yaml`\n6. Verify runtime installed: `openclaw senpi runtime list`\n7. Remove old DSL cron (if upgrading): run `openclaw crons list`, delete any cron containing `dsl-v5.py` via `openclaw crons delete \u003Cid>`\n8. Create scanner cron (90s, main)\n9. Write `config\u002Fbootstrap-complete.json`\n10. Send: \"? ROACH v1.0 online. Striker only. Stalker disabled. Waiting for explosions. Silence = no explosion.\"\n\nIf bootstrap exists, still verify runtime and scanner cron on every session start.\n\n---\n\n## Expected Behavior\n\n| Metric | Expected |\n|---|---|\n| Trades\u002Fday (chop) | 0-1 |\n| Trades\u002Fday (trending) | 1-3 |\n| Days with zero trades | Common and correct |\n| Win rate | Higher than Stalker variants (60-70% target) |\n| Avg winner | Larger (explosive entries with 1.5x volume) |\n| Avg loser | Similar to other variants (DSL-managed) |\n| Total P&L | Hypothesis: matches or beats Stalker variants with far fewer trades |\n\n**SILENCE IS CORRECT.** If ROACH goes 24-48 hours without a trade, that means there were no FIRST_JUMP explosions worth taking. That's the experiment working, not a bug.\n\n---\n\n## Risk Management\n\n| Rule | Value |\n|---|---|\n| Max positions | 3 |\n| Max entries\u002Fday | 6 |\n| Leverage | 7-10x |\n| Daily loss limit | 10% |\n| Per-asset cooldown | 2 hours |\n| XYZ equities | Banned |\n| Stalker mode | DISABLED |\n\n---\n\n## Notification Policy\n\n**ONLY alert:** Position OPENED (Striker signal with score + reasons), position CLOSED (P&L + reason), critical error.\n\n**NEVER alert:** Scanner found no Striker signals (this is normal and expected), any reasoning about whether to enable Stalker, any analysis of market conditions.\n\n---\n\n## Files\n\n| File | Purpose |\n|---|---|\n| `scripts\u002Froach-scanner.py` | Striker-only scanner (Stalker disabled in run()) |\n| `scripts\u002Froach_config.py` | Config helper |\n| `config\u002Froach-config.json` | Config (Stalker settings present but unused) |\n| `runtime.yaml` | Runtime config for plugin (DSL exit + position tracker) |\n\n---\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":44,"description":7},{"author":45,"version":46,"exchange":31,"platform":47,"requires":48,"config_source":50},"jason-goldberg","2.0","senpi",[49],"senpi-trading-runtime","striker-only-experiment","main","cc32fdacf303e9c64064829787a5e690bb29cd47","skills\u002Fsenpi-skills\u002Froach",0,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm","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 12:46:02",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add enuno\u002Fhyperliquid-trading-firm --skill roach-strategy",{"tool":66,"command":67},"bunx","bunx skills add enuno\u002Fhyperliquid-trading-firm --skill roach-strategy",{"tool":69,"command":70},"pnpm","pnpm dlx skills add enuno\u002Fhyperliquid-trading-firm --skill roach-strategy","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Froach\u002FSKILL.md",true,[74,80,84,88,94],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"config\u002Froach-config.json","REFERENCE","参考文档",1392,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Froach\u002Fconfig\u002Froach-config.json",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"README.md",996,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Froach\u002FREADME.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"runtime.yaml",1342,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Froach\u002Fruntime.yaml",{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"scripts\u002Froach_config.py","SCRIPT","脚本",8571,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Froach\u002Fscripts\u002Froach_config.py",{"path":95,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Froach-scanner.py",19805,"https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Froach\u002Fscripts\u002Froach-scanner.py",[99,131,149,173,198,222],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":103,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":111,"publishedAt":39},"01M6J14V7SBT7MBPZ9VK8NRQR8","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.","GPL-3.0","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsupermemory\u002FSKILL.md",[106],{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[101,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"ai agents","memory","rag","semantic search","infrastructure","search","user context","applications","api","knowledge","context","Art","personalization","across","learned","retention","profiles","for","persistent memory",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":39},"01M6J14PEXHE2QBAWM3YZ2GM63","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\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Fwolverine\u002FSKILL.md",[],[20,138,139,140,141,142,35,34,33,143,144,32,31,145,146,29,26,147,148,129],"wolverine strategy","architecture","alpha","Volatility","consensus","manage","max","entries","thesis","hunter","at",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":158,"publishedAt":39},"01M6J14FQY9YG5QB45QK4D98AZ","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\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Fwolf-strategy\u002FSKILL.md",[155],{"categoryNo":156,"categoryName":157,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000023","Skill与智能体开发",[20,159,160,161,162,163,139,164,165,34,31,166,167,168,26,169,170,171,148,172],"wolf strategy","MCP","openclaw","cli","sync","watchdog","autonomous","perps","strategies","shared","asset","native","wallets","hyperliquid perps",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":180,"publishedAt":39},"01M6J14A20TMQ772M3H80XNB2T","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\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Fwolf-howl\u002FSKILL.md",[179],{"categoryNo":156,"categoryName":157,"taxonomyType":109,"taxonomyTypeDesc":110},[181,160,182,162,183,184,185,186,187,188,165,189,190,191,192,193,194,195,196,197],"wolf howl","review","performance","learn","analysis","loop","analyze","short","up","optimize","drift","missed","self","factor","loops","profit","data-driven",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":202,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":205,"publishedAt":39},"01M6J1469QYZMD7E6JDP8Z9X1V","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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fenuno\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Fwhale-index\u002FSKILL.md",[],[206,207,208,183,209,210,211,212,213,214,189,215,216,167,217,218,219,220,129,221],"index","whale","whale index","auth","monitoring","discovery","use","auto","portfolio","daily","time","with","consistency","top","mirror","pnl",{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":228,"publishedAt":39},"01M6J141MJ2JMM7X3BGEEW30J9","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\u002Fhyperliquid-trading-firm\u002Fblob\u002Fmain\u002Fskills\u002Fsenpi-skills\u002Fvixen\u002FSKILL.md",[],[20,229,230,231,232,233,34,33,31,21,234,235,169,217,236,23,237,22,238,239],"vixen strategy","roi","data","first","confirmation","live","filter","explosion","high","modes","emerging movers"]