技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.2
统计：⭐ 0 · 113 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：可疑 · OpenClaw ：可疑
Package：databian/daily-report-bian
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：可疑
OpenClaw 评估
The skill overall behaves like a daily-report generator and reads local agent sessions and memory files as expected, but it contains undeclared behaviors (runtime exec usage) and lacks a clear, proportional authentication mechanism for pushing to Feishu, so its real push/communication path and data access require review before install.
目的
Name/description claim to generate and push daily reports; the code reads session JSONL and recent memory files and writes an appended report — this aligns with the stated purpose. However the skill reads agent session storage (/root/.openclaw/agents/main/sessions) and workspace memory (/root/.openclaw/workspace/memory), which are broader OS paths than a purely 'report formatting' task and may contain unrelated or sensitive conversations. That…
说明范围
SKILL.md explicitly directs reading today's session JSONL and recent memory files and appending the generated report to memory files — these steps are within a report generator's scope. But the instructions promise pushing to Feishu without explaining how authentication is obtained. The code references platform-specific paths and includes child_process.execSync (imported at top), which gives the script the ability to run arbitrary shell comman…
安装机制
The skill is instruction-only with no install spec; generate.js and supporting files are included in the skill bundle. No network downloads or package installs are performed during install, which minimizes install-time risk.
证书
The skill claims to push messages via Feishu but declares no required environment variables or credentials. There's no visible Feishu app ID/secret or token in the manifest. This is inconsistent: pushing to an external service normally requires credentials. Possible explanations: (a) it relies on platform-provided push infrastructure/credentials (not declared), (b) the remainder of generate.js (truncated in the review) contains credential hand…
持久
The skill does not request always:true and has no install hooks modifying other skills or system-wide settings. Autonomous invocation is allowed (platform default). It writes to its own memory files (appending generated reports), which is expected. Note: autonomously reading agent sessions + sending externally (if it does) would increase blast radius, so autonomy combined with the other concerns is important to consider.
generate.js:186
Shell command execution detected (child_process).
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「daily-report-bian」。简介：自动生成并在指定时间通过飞书推送每日研究进展报告，内容涵盖今日进展、延续项目、明日计划及系统状态，字数不超1000字。。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/databian/daily-report-bian/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
# Daily Report Skill - 每日研究进展推送
## 功能说明
自动生成每日研究进展报告，并在指定时间推送给用户。报告总字数控制在 1000 字以内。
## 数据源
1. **当天会话记录** - 从飞书会话 JSONL 文件读取
2. **最近 7 天记忆文件** - 读取 `memory/YYYY-MM-DD.md`
## 核心逻辑
### 1. 项目识别
- 从当天会话中提取完成的任务/项目
- 从最近 7 天记忆文件中识别延续性项目
- 保持项目命名前后一致
### 2. 报告生成
- 按模板填充内容
- 总字数 ≤1000 字
- 结构清晰，分条罗列
### 3. 记忆更新
- 报告生成后追加到当天记忆文件
- 避免重复记录
### 4. 推送配置
- 默认推送时间：22:00
- 推送渠道：飞书私聊
- 支持用户自定义时间
## 文件结构
```
daily-report/
├── SKILL.md # 本文件
├── generate.js # 报告生成核心逻辑
├── config.json # 配置（推送时间、数据源天数等）
└── template.md # 报告模板
```
## 报告结构
1. **今日进展** - 从会话记录和记忆文件提取
2. **延续性项目** - 持续进行中的项目列表
3. **明日计划** - 基于今日进展推导
4. **系统状态** - 上下文占用等
5. **月度工作热力图** - GitHub 风格，展示最近 30 天工作量
## 使用方法
### 手动生成
```bash
node /root/.openclaw/workspace/skills/daily-report/generate.js
```
### Cron 定时任务（已配置）
```bash
# 查看任务
openclaw cron list
# 修改推送时间（如改为 21:00）
openclaw cron edit <job-id> --cron "0 21 * * *"
# 手动测试
openclaw cron run <job-id>
```
### 默认配置
- **推送时间**: 22:00 (Asia/Shanghai)
- **推送渠道**: 飞书私聊
- **字数限制**: ≤1000 字
- **数据源**: 当天会话 + 最近 7 天记忆文件
## 热力图说明
- ⬜ **白色** - 无工作
- 🟨 **黄色** - 少量工作（<500 字）
- 🟩 **绿色** - 中等工作（500-2000 字）
- 🟥 **红色** - 大量工作（>2000 字）
## 注意事项
1. 首次运行需确保 `memory/` 目录存在
2. 推送前检查上下文占用，避免超限
3. 延续性项目名需保持一致，便于追踪