← 返回 Skills 市场
colbertlee

码虫日报补课系统

作者 colbertlee · GitHub ↗ · v1.5.0 · MIT-0
cross-platform ⚠ suspicious
136
总下载
0
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install daily-report-catchup
功能描述
Automatically detects missed daily reports, regenerates missing ones, updates the index, and logs reflections for seamless report catch-up management.
使用说明 (SKILL.md)

Daily Report Catch-Up Skill

作者: colbertlee
版本: 1.5.0
许可证: MIT-0

码虫日报补课系统 - 基于 Hermes Agent 学习循环思路

更新日志 (v1.5.0)

修复内容

  • check_quality.py KeyError:文件不存在或为空时,返回完整 dict(含 sections_found 等字段)
  • check_quality.py exit code:默认返回 0,避免自动化误判;新增 --check-only 获取真实状态码
  • catch-up.py 调用模式:新增 --detect(只检测)、--quiet(静默)模式
  • skills.sh symlink 警告:过滤 reason=symlink-escapeSkipping escaped skill path 警告
  • catch-up.sh 注释:添加 exec 预检安全机制说明(需使用绝对路径)

新增内容

  • TEMPLATE.md:内置标准日报模板(今日工作、学习、复盘、明日计划)
  • 集成说明:在 daily-precheck.cjs 中集成作为质量保障层

功能模块

脚本 功能
catch-up.py 漏发检测 + 自动补录
check_quality.py 日报质量检查
multi_agent_monitor.py 多 Agent 汇总监控
dashboard.py HTML 可视化 Dashboard
skills.sh 技能管理美化脚本
TEMPLATE.md 内置日报模板(标准板块)
REPORT_CHECKLIST.md 质量检查清单

1. 漏发检测与补录

# 完整模式(检测 + 生成补录)
bash skills/daily-report-catchup/catch-up.sh

# 只检测,不生成(用于预检集成)
python3 skills/daily-report-catchup/catch-up.py --detect

# 静默模式(无输出,只返回 exit code: 0=无漏发, 1=有漏发)
python3 skills/daily-report-catchup/catch-up.py --quiet

检测逻辑

  • 扫描过去 7 个工作日
  • INDEX 无记录 → 标记为 missed 并补录
  • success 文件丢失 → 补录
  • failed/skipped 无文件 → 正常,不补录

退出码

  • 0 - 无漏发
  • 1 - 有漏发(已补录或待补录)

2. 日报质量检查

# 标准检查(完整输出)
python3 skills/daily-report-catchup/check_quality.py \x3C报告文件>

# 静默模式(只返回 exit code: 0=合格, 1=不合格)
python3 skills/daily-report-catchup/check_quality.py --check-only \x3C报告文件>

# 详细模式(包含问题列表)
python3 skills/daily-report-catchup/check_quality.py \x3C报告文件> --verbose

评分标准

  • ⭐⭐⭐ ≥90分:优秀
  • ⭐⭐ ≥60分:合格
  • ⭐ ≥30分:需改进
  • ❌ \x3C30分:不合格

⚠️ 注意:默认 exit code 始终为 0,避免自动化场景被误判为错误。使用 --check-only 获取实际质量状态码。

3. 多 Agent 汇总监控

python3 skills/daily-report-catchup/multi_agent_monitor.py

4. HTML Dashboard 可视化

python3 skills/daily-report-catchup/dashboard.py [输出路径]
# 默认输出: /tmp/daily-report-dashboard.html

打开生成的 HTML 文件即可查看可视化 Dashboard。

5. 技能管理助手

# 查看已安装的技能
bash skills/daily-report-catchup/skills.sh list

# 搜索技能(美化输出)
bash skills/daily-report-catchup/skills.sh search daily-report-catchup

# 安装技能
bash skills/daily-report-catchup/skills.sh install \x3C技能名>

# 更新技能
bash skills/daily-report-catchup/skills.sh update [技能名]

6. 日报模板

内置标准板块,新写日报时直接使用:

# 查看模板
cat skills/daily-report-catchup/TEMPLATE.md

# 生成带模板的新日报
cp skills/daily-report-catchup/TEMPLATE.md memory/daily-reports/$(date +%Y-%m-%d).md

标准板块

  • 📋 今日工作
  • 📚 学习总结
  • 🔍 复盘(做得好的 + 需要改进)
  • 💡 明日计划 / 建议

7. 部署到其他 Agent

# 搜索
openclaw skills search daily-report-catchup

# 安装
openclaw skills install daily-report-catchup

配置多工作区监控

编辑 dashboard.pymulti_agent_monitor.py 开头的工作区列表:

WORKSPACES = [
    "/path/to/workspace-1",
    "/path/to/workspace-2",
    # 添加更多...
]

索引格式

| 日期 | 星期 | 状态 | 执行时间 | 备注 |
|------|------|------|----------|------|

状态枚举

  • success - 发送成功
  • failed - 发送失败
  • skipped - 跳过(周末/节假日)
  • missed - 漏发(系统离线)
  • caught-up - 漏发后补录

文件结构

skills/daily-report-catchup/
├── SKILL.md                 # 本文件
├── catch-up.sh              # 入口脚本(含 exec 预检说明)
├── catch-up.py              # 漏发检测核心(支持 --detect/--quiet)
├── check_quality.py         # 质量检查(修复 KeyError + exit code)
├── multi_agent_monitor.py   # 多 Agent 监控
├── dashboard.py              # HTML Dashboard
├── skills.sh                # 技能管理助手(过滤 symlink 警告)
├── TEMPLATE.md              # 内置日报模板
└── REPORT_CHECKLIST.md      # 质量清单(含快速开始)
安全使用建议
This skill appears to implement report detection/generation as advertised, but there are notable surprises you should consider before installing: - Hard-coded absolute paths: The scripts assume /home/colbert/.openclaw/workspace-coding-advisor (and related paths). If you are not the user 'colbert' the code will either fail or attempt to create/modify files under /home/colbert, which may be unintended or require elevated permissions. Before running, edit the WORKSPACE and path constants to point to the correct workspace for your environment. - Cross-agent file writes: The skill appends events to ~/hermes-agent/reflections.md (hermes_reflect). That modifies a different agent's artifact without declaring it. If you run multiple agents or have a Hermes agent, confirm you want these reflections written there or remove/redirect that behavior. - Masked exit codes: Both check_quality.py and catch-up.py intentionally default to returning exit code 0 unless special flags are provided. This will hide failures from automation pipelines. Use the provided flags (--check-only, --detect, --quiet) to get real exit codes, or modify the scripts if you want honest failure signals. - File writes: The skill will create/overwrite INDEX.md, report files (YYYY-MM-DD.md), logs, and a .catch-up-state file in the workspace. Backup important data before running and test in a safe/isolated workspace first. - No network calls were found (no obvious exfiltration), but absence of a scan finding doesn't guarantee safety. Read the code, run in a sandbox, and update paths/behavior to match your environment before granting it regular use. Practical steps: run the scripts in --detect/--check-only mode first; inspect what files would be created; change WORKSPACES constants to your paths; remove or control hermes_reflect if you don't want cross-agent writes; and consider running inside a throwaway workspace to validate behavior.
功能分析
Type: OpenClaw Skill Name: daily-report-catchup Version: 1.5.0 The skill bundle contains logic designed to suppress security warnings and bypass execution restrictions. Specifically, 'skills.sh' explicitly filters out 'symlink-escape' and 'escaped skill path' warnings from the OpenClaw CLI output, which could hide legitimate security risks from the user. Additionally, 'catch-up.sh' provides instructions on how to bypass 'exec pre-check' mechanisms using absolute paths. The scripts also rely on hardcoded absolute paths to a specific user's home directory ('/home/colbert/'), which is a privacy and portability concern, though not inherently malicious.
能力评估
Purpose & Capability
Name/description claim is aligned with the code: scripts detect missing reports, generate catch-up reports, update an INDEX, and render dashboards. However the code is tightly bound to a specific absolute workspace (/home/colbert/.openclaw/workspace-coding-advisor) and to a Hermes reflections path in the user's home (~/hermes-agent/reflections.md). A general-purpose 'daily report catch-up' skill should not hardcode a specific user's home path or another agent's reflection file; this is an odd design choice and reduces portability and safety.
Instruction Scope
SKILL.md and the scripts instruct the agent to read and write local files (reports, INDEX.md, logs, state) which is expected. Concerning points: (1) hermes_reflect() appends events to ~/hermes-agent/reflections.md — writing into what appears to be another agent's file (cross-agent modification); (2) SKILL.md and catch-up.sh recommend using absolute paths to avoid exec precheck issues, reinforcing reliance on absolute filesystem locations; (3) the quality checker and catch-up scripts intentionally mask non-zero exit codes by default (they return 0 unless flags used). These broaden the scope beyond simple detection/generation and can hide failure conditions from automation.
Install Mechanism
There is no install spec in the registry metadata (instruction-only). The package includes code files to be placed on disk when the skill is installed, but no remote downloads or package manager steps are present in the manifest.
Credentials
The skill declares no environment variables, which matches metadata, but it performs file I/O to hard-coded absolute paths under /home/colbert and to Path.home()/hermes-agent. That is disproportionate for a generic skill (it implicitly assumes a particular user's file layout). It also modifies files outside its own skill directory (logs, state, INDEX, and the Hermes reflections file). No API keys or network credentials are requested, and no network calls are present, which is good, but cross-agent file writes and hardcoded user paths are unexpected and risky.
Persistence & Privilege
The skill is not marked always:true and does not request elevated platform privileges. It does, however, write persistent files (logs, state, INDEX updates, generated reports) into user directories and into a Hermes reflections file. While writing its own state/logs is normal, writing into another agent's reflections file is a form of cross-skill persistence that should be deliberate and explicitly authorized.
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-report-catchup
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /daily-report-catchup 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
v1.5.0
修复 KeyError、exit code、symlink 警告;新增模板和集成说明
v1.4.0
- Improved the appearance and formatting of the skills.sh skill management script. - No changes to other features or documentation content.
v1.3.0
- Added new scripts: skills.sh and skills_search.sh for skill management and enhanced usability. - Updated documentation to include new "技能管理助手" section with usage instructions. - Expanded the feature table and file structure in SKILL.md to cover new scripts. - Incremented version to 1.3.0.
v1.2.0
- Updated skill documentation (SKILL.md) to include author, version, and license information in a new header block. - No changes to functionality; this update improves clarity and metadata in project documentation.
v1.1.0
Version 1.1.0 (daily-report-catchup): - Added quality check, multi-agent monitoring, and HTML dashboard modules. - Introduced check_quality.py for scoring daily reports. - Added multi_agent_monitor.py for cross-workspace monitoring. - Included dashboard.py for visual report review in HTML. - Expanded documentation: updated SKILL.md and added REPORT_CHECKLIST.md. - Enhanced file structure and deployment/config guides.
v1.0.0
Daily Report Catch-Up Skill v1.0.0 - Initial release of the Daily Report Catch-Up skill - Detects missing daily report entries automatically - Generates and records catch-up reports for missed workdays - Updates INDEX.md with up-to-date report status - Logs reflection activity to ~/hermes-agent/reflections.md - Includes both Bash and Python entry points for flexibility
元数据
Slug daily-report-catchup
版本 1.5.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 6
常见问题

码虫日报补课系统 是什么?

Automatically detects missed daily reports, regenerates missing ones, updates the index, and logs reflections for seamless report catch-up management. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 136 次。

如何安装 码虫日报补课系统?

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

码虫日报补课系统 是免费的吗?

是的,码虫日报补课系统 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

码虫日报补课系统 支持哪些平台?

码虫日报补课系统 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 码虫日报补课系统?

由 colbertlee(@colbertlee)开发并维护,当前版本 v1.5.0。

💬 留言讨论