← 返回 Skills 市场
j97feng-beep

Daily Review Dashboard

作者 j97feng-beep · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
201
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install daily-review-dashboard
功能描述
Manage Steven's daily subjective review dashboard by reading, updating, and displaying daily reviews, issue tracking, sentiment tags, and next plans in revie...
使用说明 (SKILL.md)

Daily Review Dashboard

Dashboard Location

review_egg/dashboard/index.html — 复盘看板,双击用浏览器打开

Core Data Files

File Purpose
review_egg/dashboard/index.html Dashboard HTML (self-contained, stores DATA in JS)
review_egg/今日复盘-YYYY-MM-DD.md Daily review raw text
review_egg/review_index.jsonl Structured review index (JSONL, one line per day)
review_egg/review_summary.csv CSV summary of all reviews
review_egg/dashboard_data/summary.json Aggregated stats (issue counts, streaks)
review_egg/dashboard_data/issues_tracker.json Issue tracking list

Data Schema (reviews array in HTML DATA object)

{
  "date": "2026-03-18",
  "review_id": "review_20260318",
  "market_summary": "阳光电源持仓浮盈...",
  "biggest_gain": "...",
  "biggest_loss": "...",
  "top_issue": "...",
  "tags": ["买点错误", "无逻辑买入"],
  "sentiment_tags": ["反省", "冲动"],
  "daily_return_pct": 2.74,
  "trade_count": 1,
  "positions_count": 1,
  "open_positions": "阳光电源 300股",
  "issue_recurrence_count": 1,
  "issue_category": "冲动交易",
  "linked_trades": ["300274"],
  "next_plan": "兆易创新若回调至支撑可轻仓试探...",
  "original_text": "1. 阳光电源清仓...\
2. 艾罗能源...\
3. 兆易创新...",
  "holdings": [
    {
      "name": "阳光电源",
      "symbol": "300274",
      "quantity": 300,
      "cost": 163.16,
      "current_price": 166.59,
      "unrealized_pnl": 1029,
      "unrealized_pnl_pct": 2.10
    }
  ]
}

Standard Workflows

Opening the Dashboard

open ~/.openclaw/workspace/review_egg/dashboard/index.html

Adding a New Daily Review

  1. Write raw text to review_egg/今日复盘-YYYY-MM-DD.md
  2. Append structured entry to review_egg/review_index.jsonl
  3. Append summary row to review_egg/review_summary.csv
  4. Update review_egg/dashboard_data/summary.json (issues_summary, daily_returns, totals)
  5. Update review_egg/dashboard_data/issues_tracker.json if new issues
  6. Update review_egg/dashboard/index.html DATA object:
    • Add to reviews[] array
    • Add to daily_returns[]
    • Update totals (total_reviews, avg_daily_return, etc.)
  7. Run open review_egg/dashboard/index.html

Dashboard Sections

The dashboard has these sections (in order):

  1. 总览卡片(复盘次数、收益率、问题统计、连胜)
  2. 📈 每日收益率柱状图
  3. ⚠️ 问题出现统计
  4. 💼 持股状况(from holdings[]
  5. 📄 复盘原文(from original_text
  6. 📋 复盘历史(structured summary cards)

Key Rules

  • 原文 stored in original_text field — displayed verbatim
  • 结构化摘要 from fields (biggest_gain, top_issue, tags, etc.)
  • 持股状况 from holdings[] — only shows latest date with holdings
  • No field = don't fabricate; leave empty
  • Problem tags: 追高, 卖飞, 拿不住盈利单, 频繁交易, 情绪化交易, 不止损, 仓位过重, 买点错误, 无逻辑买入

Update Checklist

After receiving new review from Steven:

  • review_egg/今日复盘-YYYY-MM-DD.md (raw text)
  • review_egg/review_index.jsonl (append JSONL)
  • review_egg/review_summary.csv (append CSV row)
  • review_egg/dashboard_data/summary.json (update aggregates)
  • review_egg/dashboard_data/issues_tracker.json (new issues)
  • review_egg/dashboard/index.html (update DATA object)

Separation from Trade System

Steven's daily review = subjective (复盘) ≠ trade records (交易流水)

  • review_egg/ = Steven's personal reflection system
  • trade/ = objective trading ledger
  • Do NOT mix content between the two systems
安全使用建议
This skill appears to only operate on local files under review_egg/ and needs no credentials or installs. Before installing: (1) confirm where your workspace lives (SKILL.md mixes relative and ~/.openclaw/workspace paths), (2) back up review_egg/ (the workflow requires editing index.html's DATA object directly), and (3) if you let the agent perform automated edits, consider requiring user review/approval for changes (or inspect diffs) so accidental or malformed edits to the dashboard's JS/HTML can't break your dashboard. If you run on a non-mac system, replace the 'open' command with your platform's equivalent (xdg-open) as needed.
功能分析
Type: OpenClaw Skill Name: daily-review-dashboard Version: 1.0.0 The skill bundle provides instructions for an AI agent to manage a local trading review dashboard within the `review_egg/` directory. It defines workflows for updating structured data (JSON, CSV, JSONL) and an HTML dashboard based on user input. No indicators of malicious intent, data exfiltration, or harmful execution were found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name/description say 'daily review dashboard' and the instructions only require reading and writing local review_egg/ files (index.html, .md, JSONL, CSV). The requested actions align with the stated purpose. Minor operational inconsistency: the 'Opening the Dashboard' example uses a full path (~/.openclaw/workspace/review_egg/...) while other references use relative review_egg/; this is a usability note, not a security mismatch.
Instruction Scope
SKILL.md explicitly instructs editing files under review_egg/ and opening the local dashboard in a browser. It does not instruct reading other system paths, accessing network endpoints, or exfiltrating data. It does require direct edits to the index.html DATA object (JS) which is expected for a self-contained dashboard.
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing will be downloaded or written to disk by the skill itself beyond the normal file edits it tells the agent to perform.
Credentials
The skill requests no environment variables, credentials, or external config paths. The only path-like reference is the user's workspace (~/.openclaw/workspace) which is reasonable for a local dashboard.
Persistence & Privilege
always is false and the skill does not request persistent/system-wide privileges or modifications to other skills. It only describes editing files within its own review_egg/ area.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install daily-review-dashboard
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /daily-review-dashboard 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Daily Review Dashboard skill initial release: - Manages Steven's subjective daily review dashboard, triggered on review-related actions or requests. - Reads and writes structured daily review data under review_egg/, including raw text, index, summaries, and issue tracking. - Uses a dashboard HTML file that stores review data directly in JS for local browsing. - Clearly separates subjective review data from objective trade records. - Supports workflows for adding and displaying daily reviews, tagging issues, tracking sentiment, and updating aggregated stats.
元数据
Slug daily-review-dashboard
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Daily Review Dashboard 是什么?

Manage Steven's daily subjective review dashboard by reading, updating, and displaying daily reviews, issue tracking, sentiment tags, and next plans in revie... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 201 次。

如何安装 Daily Review Dashboard?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install daily-review-dashboard」即可一键安装,无需额外配置。

Daily Review Dashboard 是免费的吗?

是的,Daily Review Dashboard 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Daily Review Dashboard 支持哪些平台?

Daily Review Dashboard 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Daily Review Dashboard?

由 j97feng-beep(@j97feng-beep)开发并维护,当前版本 v1.0.0。

💬 留言讨论