daily-reflection

Evening reflection — full P&L review and strategy adjustment at end of day

33 stars

Best use case

daily-reflection is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Evening reflection — full P&L review and strategy adjustment at end of day

Teams using daily-reflection should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/daily-reflection/SKILL.md --create-dirs "https://raw.githubusercontent.com/aAAaqwq/AGI-Super-Team/main/skills/daily-reflection/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/daily-reflection/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How daily-reflection Compares

Feature / Agentdaily-reflectionStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Evening reflection — full P&L review and strategy adjustment at end of day

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 📝 每日反思 Skill

你是Quant。每晚23:15做全量P&L复盘。

## 准备工作
```bash
unset http_proxy https_proxy HTTP_PROXY HTTPS_PROXY all_proxy ALL_PROXY
```

读取: SOUL.md, data/strategy-v4.md, memory/今天.md, data/trades-log.jsonl

## Step 1: 账户概览
```bash
# API获取余额+持仓
python3 skills/polymarket-api/scripts/poly_trade.py balance
python3 scripts/api_position_monitor.py
```
- 记录: Portfolio=$X, Cash=$X, 利用率X%
- 从Binance获取BTC/ETH/SOL实时价
- **日P&L**: 对比今早和现在的总资产
- **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找出所有今日交易,每笔详细分析:
- 市场名称 | 方向(Yes/No) | 买入价 | 现价/结算价 | 投入金额 | 盈亏$ | 盈亏%
- edge是否真实: 信息差来源是什么?事后看是否成立?
- 趋势分析是否正确: 入场时判断的趋势 vs 实际走势
- 如果亏损: 亏损原因是什么?可以避免吗?

## Step 3: 策略分层统计
按策略层级分组:
- S1甜区: 笔数/胜率/总P&L/平均回报
- S2精选: 笔数/胜率/总P&L
- S-Elon: 推文盘表现
- S3套利: 是否发现机会
- **哪个策略表现最好?哪个最差?为什么?**

## Step 4: 风控审计
- 有没有违反铁律?(买>85¢? BTC>40%? 体育/地缘? 逆势买入?)
- 止损是否执行?有没有该止损没止的?
- 仓位集中度是否合理?

## Step 5: 市场环境回顾
- 今日市场整体情绪(恐慌/贪婪/中性)
- 有无重大事件影响市场
- 哪些品类表现好/差

## Step 6: 明日调整计划
- 具体的策略参数调整(价格区间/仓位比例/品类偏好)
- 明日重点关注的市场/事件
- 需要改进的执行细节

## 输出
1. 写入 memory/今天.md 末尾(完整反思内容)
2. 推送到DailyNews群:
```bash
python3 ~/clawd/scripts/newsbot_send.py "报告内容"
```
3. 如果发现重要教训,更新SOUL.md血泪教训或MEMORY.md

## 变更记录
- v1.0 (2026-03-15): 从cron prompt迁移为skill

Related Skills

team-daily-report

33
from aAAaqwq/AGI-Super-Team

自动汇总团队内 agent、cron、skill 进展与关键事件,生成并推送结构化日报。

self-reflection

33
from aAAaqwq/AGI-Super-Team

Continuous self-improvement through structured reflection and memory

Self-Improving Agent (With Self-Reflection)

33
from aAAaqwq/AGI-Super-Team

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use before starting work and after responding to the user.

daily-xhs-content — 小红书每日内容生产

33
from aAAaqwq/AGI-Super-Team

> Cron: `daily-xhs-content` | 每日 21:00 | agentId: content

daily-trending

33
from aAAaqwq/AGI-Super-Team

获取今日热榜,从tophub.today抓取各平台热搜榜单。当用户询问"今天有什么热搜"、"热榜"、"微博热搜"时触发。

daily-portfolio

33
from aAAaqwq/AGI-Super-Team

Morning portfolio review — full position snapshot and daily P&L report

daily-gzh-content — 公众号每日内容生产

33
from aAAaqwq/AGI-Super-Team

> Cron: `daily-gzh-content` | 每日 21:30 | agentId: content

daily-douyin-content — 抖音每日内容生产

33
from aAAaqwq/AGI-Super-Team

> Cron: `daily-douyin-content` | 每日 22:00 | agentId: content

daily-briefing

33
from aAAaqwq/AGI-Super-Team

Morning briefing: tasks + email + follow-ups

wemp-operator

33
from aAAaqwq/AGI-Super-Team

> 微信公众号全功能运营——草稿/发布/评论/用户/素材/群发/统计/菜单/二维码 API 封装

Content & Documentation

zsxq-smart-publish

33
from aAAaqwq/AGI-Super-Team

Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球.

zoom-automation

33
from aAAaqwq/AGI-Super-Team

Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.