Daily Reflection
Nightly P&L review for a trading agent: runs trade.py balance and api_position_monitor.py to get acc
by aaaaqwq · MIT
The skill
Nightly P&L review for a trading agent: runs trade.py balance and api_position_monitor.py to get account balance and open positions, reviews each trade logged in memory/今天.md and data/trades-log.jsonl, computes per-strategy stats (S1, S2, S-Elon, S3), audits risk rules, and writes the report to memory and Telegram. Use when the user asks for a daily reflection, end-of-day P&L review, or nightly trading recap.
📝 每日反思 Skill
你是Quant。每晚做全量P&L复盘。
脚本目录
skills/daily-reflection/scripts/
├── trade.py # 余额查询
└── api_position_monitor.py # 持仓详情
准备
unset http_proxy https_proxy HTTP_PROXY HTTPS_PROXY all_proxy ALL_PROXY
读取: SOUL.md, memory/今天.md, data/trades-log.jsonl
Step 1: 账户概览
python3 "$SKILL_DIR/scripts/trade.py" balance
python3 "$SKILL_DIR/scripts/api_position_monitor.py"
- 日P&L：对比今早和现在总资产
- 累计ROI：基准$56 (2/26初始资金)
Step 2: 每笔交易复盘
从 memory/今天.md 找今日交易，每笔分析：
- 市场 | 方向 | 买入价 | 现价/结算 | 投入 | 盈亏$%
- edge是否真实？趋势判断是否正确？
- 亏损原因？能否避免？
Step 3: 策略分层统计
按 S1甜区 / S2精选 / S-Elon / S3套利 分组：笔数/胜率/总P&L/平均回报
Step 4: 风控审计
铁律违反？止损执行？仓位集中度？
Step 5: 市场环境回顾
今日情绪、重大事件、品类表现
Step 6: 明日调整
策略参数调整、重点关注、执行改进
输出
- 写入 memory/今天.md 末尾
- 推送到 Telegram
- 重要教训 → 更新 SOUL.md / MEMORY.md
Use this skill
Connect your agent to the Skill Store MCP server and ask for it by ref: aaaaqwq/daily-reflection-69056173136.
Details
- Publisher
- aaaaqwq
- Category
- Finance & Markets › Trading & market analysis
- License
- MIT
- Updated
- 2026-10-14
References
More from aaaaqwq
- Agi Super Team Orchestrator 跨职能、公司级、高不确定性或用户明确要求 AGI Super Team、C-suite、团队协作、并行专家、独立复核时使用。先按职责选择最小团队，再用 Claude Code Agent 工具精…
- Agi Super Team Sync Preview, install, or update AGI Super Team in Codex.
- C Suite Team Run an outcome-oriented C-suite team in Codex with the parent acting as CEO, bounded specialist l…
- Context Engineering Optimizes agent context setup.