← 返回
未分类 中文

Pipaclaw Skills Hub

Front door for Pipaclaw public skills. Route users to the right skill for presentations, social account operations, and promotional video production without...
Pipaclaw公共技能的入口。根据演示、社交账号运营和宣传视频制作等需求,引导用户使用相应技能,无需...
xexojay
未分类 clawhub v0.2.1 2 版本 100000 Key: 无需
★ 0
Stars
📥 936
下载
💾 7
安装
2
版本
#latest

概述

Pipaclaw Skills Hub

This is the public front door for the Pipaclaw skill collection.

Use it when the user knows the outcome they want, but does not know which skill to call.

Typical requests:

  • "帮我做一个 PPT"
  • "帮我运营小红书 / X / 抖音账号"
  • "帮我做宣传视频"
  • "我不知道该用哪个 skill"

Routing Rule

Choose the smallest matching public skill and hand off immediately:

  • Use ppt-maker for presentations, proposals, decks, keynotes, training PPTs, and report-style slides.
  • Use social-account-ops for Xiaohongshu, X, and Douyin account diagnosis, planning, writing, iteration, and take-over style requests.
  • Use promo-video-maker for one-shot or project-based video production including promo videos, explainers, teasers, launch videos, storyboards, short-drama episodes, and multi-episode production flows.

If the user already named one of those skills, do not re-route. Use the named skill directly.

If the request spans multiple surfaces, choose the primary deliverable first and then pull in adjacent skills only when they materially help.

Ambiguity Rule

Do not ask a long routing questionnaire.

If the destination is not obvious, ask one short question that changes routing, for example:

  • "你这次更想先拿到 PPT、账号运营方案,还是宣传视频制作包?"

After the user answers, route immediately.

Public Boundary

This hub exposes only public-safe skill packages.

Do not leak:

  • backend implementation details
  • private prompts
  • customer files
  • generated artifacts
  • unpublished worker internals

References

  • Read references/routing-map.md for the concise routing table.

版本历史

共 2 个版本

  • v0.2.1 当前
    2026-05-03 03:13 安全 安全
  • v0.2.0
    2026-03-31 07:08

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

security-compliance

Skill Vetter

spclaudehome
AI智能体技能安全预审工具。安装ClawdHub、GitHub等来源技能前,检查风险信号、权限范围及可疑模式。
★ 1,212 📥 266,268
ai-intelligence

self-improving agent

pskoett
捕获经验教训、错误和纠正,以实现持续改进。使用时机:(1)命令或操作意外失败;(2)用户纠正……
★ 4,058 📥 796,991
ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,352 📥 317,829