← 返回 Skills 市场
381608544

ClawHub

作者 381608544 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
70
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install clawhub-report
功能描述
Draft Chinese daily reports, weekly/monthly summaries, meeting recaps, study notes, and concise research digests from rough notes, links, chat logs, document...
使用说明 (SKILL.md)

Clawhub

Overview

Turn rough input into clean Chinese reports, summaries, study notes, and research digests.

Prefer short sections, high information density, and accurate terminology. When networking or security topics depend on current versions, advisories, or best practices, verify freshness from the web before writing.

Core workflow

  1. Determine the target output.
    • 日报
    • 周报 / 月报
    • 项目总结 / 复盘
    • 学习笔记
    • 技术调研 / 知识卡片
  2. Collect source material.
    • User notes
    • Task lists
    • Chat logs
    • Documents
    • URLs
    • Fresh web research
  3. Extract signal.
    • What was done
    • What changed
    • What mattered
    • What is blocked
    • What should happen next
  4. Rewrite for the audience.
    • Manager-facing: progress, impact, risk, next steps
    • Peer-facing: technical facts, tradeoffs, conclusions
    • Personal learning: concepts, terms, examples, open questions
  5. Polish the result.
    • Remove repetition
    • Preserve uncertainty
    • Do not invent missing work or unsupported claims

Output modes

日报 / 站会更新

Use when the user asks for 日报, 今日进展, worklog, standup note, or a brief progress sync.

Preferred structure:

  • 今日完成
  • 当前进展
  • 问题 / 风险
  • 明日计划

If the source material is weak, keep it concise and clearly indicate incomplete input instead of fabricating accomplishments.

周报 / 月报

Use when the user asks for a broader summary over time.

Preferred structure:

  • 周期重点
  • 已完成事项
  • 阶段成果 / 影响
  • 问题与风险
  • 下阶段计划

Prefer outcomes over raw activity lists.

总结 / 复盘

Use when the user asks for 总结, recap, review, retrospective, or takeaways.

Preferred structure:

  • 背景
  • 核心过程
  • 关键结论
  • 做得好的地方
  • 可改进点
  • 后续建议

学习笔记

Use when the user wants to study and retain knowledge.

Preferred structure:

  • 主题
  • 一句话总结
  • 核心概念
  • 关键术语
  • 典型场景
  • 常见误区
  • 可继续深入的问题

技术调研 / 安全研究摘要

Use when the user asks to search, compare, or explain networking and cybersecurity topics.

Preferred structure:

  • 主题
  • 背景
  • 关键发现
  • 技术要点
  • 风险与限制
  • 建议 / 结论
  • 参考来源

Read references/security-research.md for the research checklist and references/report-templates.md for reusable templates.

Networking and security research rules

When the task involves 网络, 安全, 协议, 漏洞, 架构, hardening, attack surface, or defensive operations:

  1. Fetch current sources when freshness matters.
  2. Separate facts from interpretation.
  3. Prefer official or primary sources first.
  4. Note versions, dates, and scope.
  5. Prefer defensive and educational framing.
  6. Avoid detailed offensive procedures unless the user clearly requests authorized defensive testing support.

Writing rules

  • Prefer Chinese unless the user asks otherwise.
  • Be compact and readable.
  • Use bullets and short sections.
  • Preserve technical accuracy.
  • Translate jargon only when it improves clarity.
  • End with actionable next steps when useful.
  • If the audience is unclear, default to an internal professional tone.

Quality bar

Before finishing, check:

  • Did the output capture all important source points?
  • Did it avoid invented facts and overclaiming?
  • Is the structure easy to scan quickly?
  • Are networking or security claims fresh enough for the task?
  • Are sources cited when research mattered?

Bundled references

  • references/report-templates.md — Chinese templates for 日报 / 周报 / 月报 / 复盘 / 学习总结 / 技术调研
  • references/security-research.md — checklist for current, defensible networking and security research
  • references/publish-copy.md — ready-to-use ClawHub listing copy
安全使用建议
This skill is internally coherent and lightweight. Before installing/use: (1) only provide the agent with documents or chat logs you are comfortable sharing (avoid pasting secrets, API keys, or internal configs); (2) be aware the skill may fetch live web sources for security research — verify and vet cited sources; (3) if you do not want autonomous agent use, restrict agent invocation in your platform settings. Overall the skill looks appropriate for drafting reports and defensive/security summaries.
功能分析
Type: OpenClaw Skill Name: clawhub-report Version: 1.0.0 The skill bundle is a productivity tool designed to generate Chinese reports, summaries, and technical research digests from user-provided notes or web research. It contains no executable code, only Markdown instructions and templates (SKILL.md, report-templates.md). The security research guidelines (security-research.md) explicitly direct the agent to prioritize defensive framing, official sources, and technical accuracy, with no evidence of malicious intent, data exfiltration, or prompt-injection attacks.
能力评估
Purpose & Capability
The name/description (Chinese report drafting and security research digests) matches the SKILL.md. It requests no binaries, env vars, or installs — appropriate for an instruction-only summarization skill.
Instruction Scope
Instructions ask the agent to collect source material from user-provided notes, chat logs, documents, URLs and to 'fetch current sources' from the web when freshness matters. That is coherent for a research/reporting skill, but it implies the agent will access external web content and any user data supplied — users should avoid providing sensitive credentials or private data unless necessary.
Install Mechanism
No install spec or code files are included (instruction-only). This minimizes disk/write risk and there are no external downloads.
Credentials
No environment variables, credentials, or config paths are required. The SKILL.md does not reference hidden env vars or credentials, so requested access is proportionate to the described function.
Persistence & Privilege
always is false and autonomous invocation is allowed (platform default). The skill does not request elevated or persistent system privileges and contains no instructions to modify other skills or system-wide configuration.
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 clawhub-report
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /clawhub-report 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
Initial public release: Chinese report writing, summary drafting, study-note generation, and networking/security research digest templates.
元数据
Slug clawhub-report
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

ClawHub 是什么?

Draft Chinese daily reports, weekly/monthly summaries, meeting recaps, study notes, and concise research digests from rough notes, links, chat logs, document... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 70 次。

如何安装 ClawHub?

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

ClawHub 是免费的吗?

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

ClawHub 支持哪些平台?

ClawHub 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 ClawHub?

由 381608544(@381608544)开发并维护,当前版本 v1.0.0。

💬 留言讨论