patpat
v1.0.2PatPat（摸摸头）— 3-8岁儿童情绪共调节助手。帮助家长在孩子情绪爆发时快速获得可用的应对指导，包括当下爆发、事后修复和日常练习三种场景。当用户提到孩子哭闹、发脾气、打人、不听话、亲子冲突、情绪崩溃、育儿焦虑、如何安抚孩子、怎么跟孩子道歉、孩子不愿刷牙/睡觉/出门、兄弟姐妹吵架、屏幕时间结束大哭等任何涉及幼...
⭐ 0· 51·0 current·0 all-time
by@gglinux
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (3–8yo co-regulation assistant) matches the provided SKILL.md and logic files. There are no unexpected requested binaries, environment variables, or config paths — everything in the repo is instructional content appropriate for the stated purpose.
Instruction Scope
Runtime instructions are narrowly scoped to triage (mode, child age band, visible state, parent regulation) and to produce structured parent/child guidance. The SKILL.md does not instruct the agent to read system files, environment variables, or send data to external endpoints, and it contains explicit safety routing (green/yellow/red).
Install Mechanism
This is an instruction-only skill with no install spec or code to fetch/execute. No downloads, package installs, or executables are declared.
Credentials
No environment variables, credentials, or config paths are required. The guidance logic does not reference secrets or unrelated external services, so requested environment access is proportionate (i.e., none).
Persistence & Privilege
always is false and the skill does not request persistent system privileges or to alter other skills. It permits normal autonomous invocation (platform default), which is expected for skills but not itself a sign of over-privilege.
Assessment
This skill appears coherent and focused on in-the-moment parenting support. Before installing: (1) remember it is not a replacement for professional mental health or emergency services — follow the skill's own Red-route guidance when safety risks appear; (2) the skill is instruction-only (no code/network endpoints in the bundle), but any content you send to the agent will be processed by your LLM provider — avoid sharing unnecessary personal identifiers about children or family members; (3) test it in low-stakes situations first to confirm the phrasing and cultural fit, and monitor outputs for inappropriate or unsafe advice (report or remove if you see guidance that conflicts with local medical/legal emergency procedures).Like a lobster shell, security has layers — review code before you run it.
latestvk97ex9hry3qacaxkp0gkxjpm9x84sbgn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.