[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ECP40BX56PS7A2DS5MMWF0":3,"skill-same:01M7ECP40BX56PS7A2DS5MMWF0":49},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":13,"repositoryHtmlUrl":25,"repositoryHomepageUrl":6,"ownerHtmlUrl":26,"ownerBlogUrl":6,"ownerDescription":27,"updatedAt":28,"install":29,"resources":42},"01M7ECP40BX56PS7A2DS5MMWF0","cortexquant-trading",null,"jonahthan433\u002FCortexOS","jonahthan433","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211465495?v=4","01M7ECH9HPHGA89DCXHHJBTS3C","jonah.ai","01M7ECH9JCEM45DZMWPT7148S1",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fcortexquant-trading\u002Fcortexquant-trading\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# cortexquant-trading\n\n# CortexQuant CT106 — 24\u002F7 Trading System\n\nOperate the BingX demo trading platform with supervised worker fleet, signal pipeline, and ML components.\n\n## Topology\n- Proxmox host `ninyi` = `192.168.1.11`. CT106 `cortexquant` = `192.168.1.19` (reachable only via `pct exec 106` from the host — direct SSH from agent host fails with \"No route to host\")\n- Access pattern: `ssh root@192.168.1.11 'pct exec 106 -- bash -c \"...\"'`\n- Copy files: pipe via stdin → `pct exec 106 -- cat > \u002Fpath\u002Fto\u002Ffile`\n- DB: PostgreSQL `cortexquant`, user `cortexquant`, password `cq_secure_2026`\n- Codebase: `\u002Fopt\u002Fcortexquant\u002F` (old full system) — **WIPED AND REPLACED** with Phase 1 scaffold at `\u002Fopt\u002Fcortexquant\u002Ftrading_system\u002F`\n- Service venv: `\u002Fopt\u002Fcortexquant\u002Ftrading_system\u002F.venv\u002F` (Phase 1 scaffold venv with loguru, ccxt, telethon, pandas, numpy, python-dotenv, tenacity)\n- Systemd: `systemctl {restart,status} cortexquant` inside CT106 — currently **stopped+disabled**; Phase 1 scaffold has no service file yet\n- ML gate: `ML_SKIP_VALIDATION=true` via systemd drop-in — **no longer applicable** (Phase 1 scaffold has no ML component)\n\n## Deployment\n\n### Push code to CT106 (choose method by reliability, not size)\n\n**Most reliable for text files of ANY size — stdin pipe directly to pct exec cat:**\n```bash\ncat \u002Flocal\u002Ffile.py | ssh -i ~\u002F.ssh\u002Fhermes_ninyi -o StrictHostKeyChecking=no \\\n  root@192.168.1.11 'pct exec 106 -- bash -c \"cat > \u002Fopt\u002Fcortexquant\u002Ftrading_system\u002Fpath\u002Ffile.py\"'\n```\nThis is the primary method. It works for small and large text files. Always clear\n`__pycache__` after pushing updated modules:\n```bash\nssh root@192.168.1.11 'pct exec 106 -- bash -c \"rm -rf \u002Fopt\u002Fcortexquant\u002Ftrading_system\u002Fsrc\u002F__pycache__ \u002Fopt\u002Fcortexquant\u002Ftrading_system\u002Ftests\u002F__pycache__\"'\n```\n\n**Large files or binary — base64 pipe (most reliable, avoids shell-quoting corruption):**\n```bash\nbase64 -w0 \u002Flocal\u002Ffile.py | ssh -i ~\u002F.ssh\u002Fhermes_ninyi -o StrictHostKeyChecking=no \\\n  root@192.168.1.11 'pct exec 106 -- bash -c \"base64 -d > \u002Fopt\u002Fcortexquant\u002Ftrading_system\u002Fpath\u002Ffile.py\"'\n```\n\n**DO NOT use scp to PVE \u002Ftmp then cp inside container** — PVE host `\u002Ftmp\u002F` is NOT\nvisible inside the container (`cp: cannot stat '\u002Ftmp\u002Ffile.py'`). The file lands on\nthe PVE host but the container cannot see it.\n\n**DO NOT use inline python3 -c through SSH** — quoting through the SSH layer\nmangles escape sequences and Unicode (emoji bytes get corrupted). Write scripts to\nhost `\u002Ftmp\u002F*.py` files and pipe them through, or use the stdin cat method above.\n\n### Apply config changes (sed inline)\n```bash\nssh root@192.168.1.11 'pct exec 106 -- bash -c \"sed -i \\\\\"s|OLD|NEW|\\\\\" \u002Fopt\u002Fcortexquant\u002Ftrading_system\u002Fsrc\u002Ffile.py\"'\n```\n\n### Run self-check tests (Phase 1 scaffold)\n```bash\nssh root@192.168.1.11 'pct exec 106 -- bash -c \"cd \u002Fopt\u002Fcortexquant\u002Ftrading_system && PYTHONPATH=. .venv\u002Fbin\u002Fpython3 tests\u002Ftest_self_check.py\"'\n```\nNot pytest, not system python — use the venv python with PYTHONPATH set to the\nproject root. The self-check is a standalone script, not a pytest suite.\n\nIf any check fails, stop and report the blocker — do not proceed to the next fix.\n\n## Database queries\n```bash\ncat > \u002Ftmp\u002Fquery.py \u003C\u003C 'PYEOF'\nimport asyncio, asyncpg\nasync def main():\n    conn = await asyncpg.connect(\"postgresql:\u002F\u002Fcortexquant:cq_secure_2026@localhost:5432\u002Fcortexquant\")\n    rows = await conn.fetch(\"SELECT symbol, direction, order_status FROM demo_trades WHERE order_status = 'OPEN'\")\n    for r in rows:\n        print(dict(r))\n    conn.close()\nasyncio.run(main())\nPYEOF\ncat \u002Ftmp\u002Fquery.py | ssh root@192.168.1.11 'pct exec 106 -- bash -c \"cat > \u002Ftmp\u002Fquery.py && \u002Fopt\u002Fcortexquant\u002Fvenv\u002Fbin\u002Fpython \u002Ftmp\u002Fquery.py\"'\n```\n\n## BingX position management\n\n### Close positions\n```python\nimport asyncio, ccxt\nexchange = ccxt.bingx({'apiKey': api_key, 'secret': secret, 'enableRateLimit': True, 'options': {'defaultType': 'swap'}})\nexchange.set_sandbox_mode(True)\npositions = await asyncio.to_thread(exchange.fetch_positions)\nfor pos in positions:\n    if pos['contracts'] > 0 and symbol in to_close:\n        side = 'sell' if pos['side'] == 'long' else 'buy'\n        await asyncio.to_thread(exchange.create_order, symbol=pos['symbol'], type='market', side=side, amount=pos['contracts'])\n```\n\n## Worker fleet\n\n**16 workers** (restored from git HEAD 2c42cf4). All supervised by `WorkerSupervisor`:\n- `dashboard_feed` (5s), `monitor` (60s), `demo_reconcile` (30s), `tg_ingestion` (120s)\n- `market_data` (600s), `ml_predict` (300s), `backtest_adapter` (600s), `risk_committee` (240s)\n- `hypothesis` (120s), `strategy_version` (300s), `walkforward` (600s), `red_team` (300s)\n- `incentive_scoring` (240s), `room_tasks` (120s), `quantum_optimize` (600s), `portfolio_optimize` (600s)\n- `signal_aggregator` (60s)\n\nAPI: `GET \u002Fapi\u002Fworkers\u002Fhealth`\n\nTo list: `curl -s http:\u002F\u002Flocalhost:8080\u002Fapi\u002Fworkers\u002Fhealth | python3 -m json.tool`\n\n## Memory pressure on 3GB CT106\n\nWhen memory pressure persists:\n- **Kill duplicate Hermes dashboard processes**: `kill $(pgrep -f \"hermes dashboard.*9119\")` — saves ~356MB\n- **Kill Headroom MCP** (only needed for context compression): `kill $(pgrep -f \"headroom mcp serve\")` — saves ~59MB\n- These respawn via systemd — that's normal and acceptable\n- **Cut Nextcloud PHP workers**: `pm.max_children = 5` (already low, ~200MB total)\n- Verify savings: `free -h` should show Available > 1.2GB on a 3GB host\n- **Never use `sort=-%mem` in `ps` on CT106** — it runs BusyBox `ps` which doesn't support `--sort`. Use `ps aux | head` and read RSS manually.\n\n## Signal pipeline\nTelegram (CKPscanner) → `tg_service.py` → `tg_parser.py` → `tg_publisher` → `FullPipeline` → `DemoTradingService` → BingX\n\n### Pipeline checks (order matters)\n1. Idempotency (decision_records table)\n2. Market data snapshot (symbol normalized to base: `ETH\u002FUSDT` → `ETH`)\n3. ML prediction (observation-only until approved; gates via `ML_SKIP_VALIDATION`)\n4. Strategy selection\n5. Classical\u002Fquantum optimization\n6. Risk check (real values, not hardcoded)\n7. Signal freshness (5-minute max)\n8. BingX market existence check\n9. Duplicate position check\n10. Execution\n\n### Pipeline execution paths (unified)\nBoth Telegram signals and `\u002Fapi\u002Fdemo\u002Ftest-signal` now route through the same orchestrator (`DemoExperimentOrchestrator.process_signal`) and shared `FullPipeline` instance. Do not create fresh pipeline instances per call.\n\n## 7-day experiment clock\n\n- `start_experiment(duration_days=7)` arms the experiment (`is_active=True`) but does NOT start the clock.\n- The clock starts on first filled trade via `start_clock(\"first_filled_trade\")`.\n- **Auto-start on restart**: after reconciliation rehydrates positions from exchange, `start_clock(\"rehydrated_positions\")` is called so the clock survives restarts.\n- Verify: `curl -s http:\u002F\u002Flocalhost:8080\u002Fapi\u002Fdemo\u002Fstatus` → `experiment_start`, `experiment_end`, `days_remaining`.\n\n## Reconciliation\n\n- `reconcile_demo.py` fetches open positions from BingX, syncs to internal state, creates missing DB rows.\n- **MAX_CONCURRENT_TRADES guard**: DB row creation is capped at `demo_trader.config.MAX_CONCURRENT_TRADES` (default 25 for settings, 3 for demo config).\n- On startup, `demo_lifecycle.start_demo_experiment()` runs reconciliation BEFORE wiring the publisher callback.\n\n## ⚠️ Pitfalls\n\n### **LIVE_TRADING=false is a hard default — never enable it**\nThe system defaults to `LIVE_TRADING=false`. Do not change this. All fixes must preserve this. Verify after every restart: `curl -s http:\u002F\u002Flocalhost:8080\u002Fhealth | grep live_trading`.\n\n### **NEVER overwrite .env with echo > — DESTROYS API KEYS**\nThe .env file contains BingX API keys, DB creds, and other secrets. Using `echo \"...\" > \u002Fopt\u002Fcortexquant\u002F.env` **overwrites the entire file**, destroying all existing vars and bricking the service with \"credentials not configured\". ALWAYS append: `echo \"...\" >> \u002Fopt\u002Fcortexquant\u002F.env` or use `sed -i` to modify specific lines. After appending, verify with `cat \u002Fopt\u002Fcortexquant\u002F.env | grep KEY_NAME`.\n\n### **POST requests require Bearer auth (protect_mutations middleware)**\nAll POST\u002FPUT\u002FPATCH\u002FDELETE requests are rejected with 401 unless a valid `Authorization: Bearer \u003CAPI_SECRET_KEY>` header is sent. When `API_SECRET_KEY` is the default `change-me-in-production`, ALL mutations are blocked. For testing, either temporarily set a key in `.env` (and remove it after) or call Python directly on CT106.\n\n### **Service venv is `\u002Fopt\u002Fcortexquant\u002Fvenv\u002F`, not `.venv\u002F`**\nThe `.venv` folder is a separate env created during debugging — it may be incomplete. The service uses `\u002Fopt\u002Fcortexquant\u002Fvenv\u002F`. Always invoke the service venv: `\u002Fopt\u002Fcortexquant\u002Fvenv\u002Fbin\u002Fpython`.\n\n### **File transfer to CT106 requires `pct exec 106`**\nDirect SSH from agent to 192.168.1.19 fails (\"No route to host\"). All access via: `ssh root@192.168.1.11 'pct exec 106 -- ...'`\n\n### **Heredoc via SSH truncates on context compression**\nPiping a file through `ssh ... bash -c \"cat > \u002Ftmp\u002Fx \u003C\u003C 'EOF'\"` works for small files but truncates when the heredoc exceeds ~4KB (context compression eats the body). For larger files, use base64 pipe or scp.\n\n### **ta library import order kills valid names on partial failure**\nIn `src\u002Ftools\u002Ftechnical_adapter.py`, the `try: from ta.volatility import (BollingerBands, AverageTrueRange, ...)` block fails entirely if ANY name is missing (e.g., `StochIndicator` was renamed to `StochasticOscillator` in ta 0.11.0). When the import fails, ALL names in that block become unavailable — even valid ones like `AverageTrueRule`. Fix broken names OR split into separate try\u002Fexcept blocks per group.\n\n### **Missing imports in predictor.py**\n`src\u002Fml\u002Fpredictor.py` uses `os.environ.get(\"ML_SKIP_VALIDATION\", ...)` and `datetime.now(timezone.utc)` but historically omitted `import os` and `from datetime import datetime, timezone`. After patching, verify both imports are present — missing imports cause silent ML save failures and broken approval gates.\n\n### **Symbol normalization in pipeline**\n`FullPipeline.process_signal` fetches OHLCV using `f\"{symbol}\u002FUSDT\"`. If the signal arrives as `ETH\u002FUSDT`, this becomes `ETH\u002FUSDT\u002FUSDT` and the exchange errors. Normalize to base symbol immediately: `symbol = symbol.split(\"\u002F\")[0]`.\n\n### **Duplicate DB creation loop in reconcile_demo.py**\nWhen patching reconciliation to respect MAX_CONCURRENT_TRADES, a duplicate block was accidentally introduced. Always `grep -c \"Respect MAX\" reconcile_demo.py` after patching — there should be exactly ONE guard block, not two. Duplicate blocks can create duplicate DemoTrade rows for the same symbol.\n\n### Memory pressure on 3GB CT106\n\nWhen memory pressure persists:\n- **Kill duplicate Hermes dashboard processes**: `kill $(pgrep -f \"hermes dashboard.*9119\")` — saves ~356MB\n- **Kill Headroom MCP** (only needed for context compression): `kill $(pgrep -f \"headroom mcp serve\")` — saves ~59MB\n- These respawn via systemd — that's normal and acceptable\n- **Cut Nextcloud PHP workers**: `pm.max_children = 5` (already low, ~200MB total)\n- Verify savings: `free -h` should show Available > 1.2GB on a 3GB host\n- **Never use `sort=-%mem` in `ps` on CT106** — it runs BusyBox `ps` which doesn't support `--sort`. Use `ps aux | head` and read RSS manually.\n\n### BingX demo credentials restoration (after .env overwrite)\nIf `.env` is accidentally overwritten (see NEVER overwrite .env pitfall), BingX credentials must be re-added:\n```\nDEMO_EXCHANGE_API_KEY=\u003Ckey>\nDEMO_EXCHANGE_SECRET=\u003Csecret>\nDEMO_EXCHANGE_SANDBOX=true\n```\nThen `systemctl restart cortexquant` and verify: `curl -s http:\u002F\u002Flocalhost:8080\u002Fapi\u002Fdemo\u002Fstatus` — should show `demo_trading: true`, not \"credentials not configured\".\n\n### Risk engine hardcoded values bug\nThe risk check in `full_pipeline.py` was passing `{\"position_size_pct\": 2.0, \"risk_pct\": 2.0}` instead of real signal values — made exposure limits unenforceable. Fixed 2026-09-09.\n\n### Parser whitespace bug\nScout messages have leading whitespace (` 1. ALCH-USDT |...`). LINE_PATTERN regex needs `\\s*` prefix.\n\n### ML model always fails validation\nGradientBoostingRegressor on 34,940 samples → R²=-0.04. Until improved, `ML_SKIP_VALIDATION=true` required. Retrain via `scripts\u002Ftrain_model_standalone.py`.\n\n### N+1 meme-coin positions\nWithout enforced exposure limits, Scout signals can open 19+ positions reaching 260%+ exposure. Monitor via `\u002Fapi\u002Fdemo\u002Fstatus`.\n\n## Key files\n- `src\u002Fworkers\u002Fsupervisor.py` — heartbeat, retry, failure classification\n- `src\u002Fworkers\u002Fjobs.py` — all 16 worker definitions\n- `src\u002Frisk\u002Frisk.py` — risk engine with LIVE_TRADING guard\n- `src\u002Fpipeline\u002Ffull_pipeline.py` — signal processing pipeline\n- `src\u002Fingestion\u002Ftg_service.py` — Telegram ingestion\n- `src\u002Fingestion\u002Ftg_parser.py` — Scout message parser\n- `src\u002Fexchange\u002Fdemo_trading_service.py` — BingX execution\n- `reconcile_demo.py` — exchange→DB reconciliation\n- `src\u002Fml\u002Fpredictor.py` — ML predictor (observation-only until approved)\n- `src\u002Ftools\u002Ftechnical_adapter.py` — TA features (watch import order)\n- `src\u002Fquant_hq\u002Fdemo_lifecycle.py` — startup, reconciliation, clock auto-start\n- `src\u002Fquant_hq\u002Fdemo_orchestrator.py` — signal orchestration\n- `src\u002Fapi\u002Fdemo_routes.py` — test-signal and start\u002Fstop endpoints\n- `scripts\u002Ftrain_model_standalone.py` — ML training\n\n## Verify health\n```bash\nssh root@192.168.1.11 'pct exec 106 -- bash -c \"systemctl is-active cortexquant && curl -s http:\u002F\u002Flocalhost:8080\u002Fapi\u002Fworkers\u002Fhealth && curl -s http:\u002F\u002Flocalhost:8080\u002Fapi\u002Fdemo\u002Fstatus\"'\n```\n\n## Test signal dry-run (synthetic e2e)\n\nRun a signal through the full pipeline without placing real trades:\n```bash\ncat > \u002Ftmp\u002Fdryrun.py \u003C\u003C 'PYEOF'\nimport json, urllib.request\nBASE = \"http:\u002F\u002Flocalhost:8080\"\ndef get(url):\n    with urllib.request.urlopen(url, timeout=30) as r:\n        return json.loads(r.read().decode())\nstatus = get(BASE + \"\u002Fapi\u002Fdemo\u002Fstatus\")\nassert status[\"live_trading\"] == False\nassert status[\"demo_trading\"] == True\nassert status[\"kill_switch\"] == False\nprint(\"OK:\", status[\"positions_open\"], \"positions\")\nPYEOF\ncat \u002Ftmp\u002Fdryrun.py | ssh root@192.168.1.11 'pct exec 106 -- bash -c \"cat > \u002Ftmp\u002Fdryrun.py && \u002Fopt\u002Fcortexquant\u002Fvenv\u002Fbin\u002Fpython \u002Ftmp\u002Fdryrun.py\"'\n```\n",{},"main","38b32c99e7ed0b8e215d638e92cfa452c1ec3079","skills\u002Fimported\u002Fcortexquant-trading\u002Fcortexquant-trading","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS","https:\u002F\u002Fgithub.com\u002Fjonahthan433","AI Consultant","2026-10-24 05:13:39",{"source":7,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add jonahthan433\u002FCortexOS --skill cortexquant-trading",{"tool":35,"command":36},"bunx","bunx skills add jonahthan433\u002FCortexOS --skill cortexquant-trading",{"tool":38,"command":39},"pnpm","pnpm dlx skills add jonahthan433\u002FCortexOS --skill cortexquant-trading","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fcortexquant-trading\u002Fcortexquant-trading\u002FSKILL.md",true,[43],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"skill.json","REFERENCE","参考文档",369,"https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fimported\u002Fcortexquant-trading\u002Fcortexquant-trading\u002Fskill.json",[50,56,62,68,74,80],{"skillNo":51,"name":52,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M7EDQZDQX3Q8Y7GCQX6KN9V7","opportunity-brief","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fsales\u002Fopportunity-brief\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M7EDQYA0V9Y99VKBREJJ3MRT","morning-intel","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fmorning-intel\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M7EDQVX1JVY0B6PDHKKGM19G","decision-brief","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Fdecision-brief\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7EDQV1GENZAC2SZSD8KZ3GM","weekly-review","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fweekly-review\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7EDQT2KETJ1Y3CGVN9EKW2J","system-health","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fops\u002Fsystem-health\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M7EDQQN2JK3XPWMS1M4T0F3K","backup-restore","https:\u002F\u002Fgithub.com\u002Fjonahthan433\u002FCortexOS\u002Fblob\u002Fmain\u002Fskills\u002Fops\u002Fbackup-restore\u002FSKILL.md",[],[]]