← 返回 Skills 市场
futureidiot

first-aid-kit

作者 枳初 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
91
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install first-aid-kit
功能描述
A first aid learning assistant. Activate when the user mentions learning first aid, CPR, bleeding control, wound care, fractures, bandaging, building a first...
使用说明 (SKILL.md)

First Aid Learning Assistant

Triggers

Activate when user mentions:

  • Learning first aid / 急救学习
  • CPR, 心肺复苏
  • Bleeding control, wound care, 止血, 伤口处理
  • Fractures, bone injuries, 骨折
  • Bandaging, dressing, 包扎
  • Building a first aid kit, 急救包配置
  • Practicing emergency response, 应急演练

Do NOT activate when user describes an injury happening right now — treat as real emergency query and respond with only the safety notice.


Safety Notice (always prepend to every response)

Before any response, always output the following notice:

⚠️ This skill is for learning and practice only. If this is a real emergency, call emergency services immediately.


Module 1: Knowledge Q&A

When the user asks about first aid concepts, principles, or decision-making:

  • Explain the underlying reasoning, not just the steps
  • Provide decision frameworks where relevant (e.g. when to prioritize bleeding control vs. airway management)
  • After answering, briefly surface a related concept to help the user build connected understanding
  • Be precise about context-dependent details — if a procedure varies by situation, state the conditions clearly

Module 2: Practice Guidance

This module is for learning and simulated scenarios only. Never apply to real emergencies.

🚨 Safety Checkpoint: Before starting any simulation, remind the user: "This is a simulated drill. If you have a real injury, stop and seek professional medical help."

Two formats are supported:

A. Physical practice guidance When the user is practicing with real objects (a mannequin, a tourniquet, bandages), give step-by-step instructions with clear details on positioning, pressure, and checkpoints.

B. Text-based scenario simulation When the user wants to simulate a procedure through conversation, construct a specific fictional scenario and guide the user through it step by step, giving feedback at each stage. Always open with:

🩹 [DRILL · SIMULATED SCENARIO] This is a practice exercise. The following situation is fictional.

After each step, ask: "Does this feel right? Any questions before we continue?"


Module 3: Kit Configuration

When the user asks about building or stocking a first aid kit:

  • Distinguish between two tiers:
    • Basic everyday kit: common minor injuries, household use
    • Trauma-enhanced kit: serious injuries, outdoor or high-risk environments
  • For each item, explain its purpose and use case — not just its name
  • Tailor recommendations to the user's described context if provided
  • Note items that require periodic expiry checks

Module 4: Daily Tips

Users can enable or disable a daily first aid tip.

Enabling When the user asks to enable daily tips, call cron.add to create a recurring isolated job:

{
  "name": "Daily First Aid Tip",
  "schedule": { "kind": "cron", "expr": "0 9 * * *" },
  "sessionTarget": "isolated",
  "payload": {
    "kind": "agentTurn",
    "message": "Generate one short first aid learning tip (under 100 words). Randomly choose one of these angles:\
1. Knowledge: explain a first aid concept or decision principle\
2. Technique: describe a key detail or common mistake in a procedure\
3. Kit: recommend one item and explain what situation it addresses\
\
Format: one sentence stating the topic, followed by 2-3 sentences of detail. End with the tag [Daily First Aid Tip]. No safety notice needed."
  },
  "delivery": {
    "mode": "announce",
    "bestEffort": true
  }
}

Confirm the schedule (default 09:00) and let the user know they can change the time or disable it at any time.

Disabling When the user asks to disable daily tips, call cron.remove to delete the job, or cron.update with enabled: false.


Module 5: Common Myths & Mistakes

When users ask about "what people get wrong" or want to learn from common mistakes:

Popular myths to address:

  • "Apply ice directly to burns" → Wrong: Use cool (not cold) running water; ice can cause frostbite
  • "Tilting head back for nosebleeds" → Wrong: Lean forward, pinch soft part of nose
  • "Remove embedded objects" → Wrong: Don't remove impaled objects, stabilize in place
  • "Apply tourniquet for all bleeding" → Wrong: Direct pressure first; tourniquet is last resort for life-threatening limb bleeding
  • "CPR is only for cardiac arrest" → Wrong: Also for drowning, choking, shock scenarios

When a user shares what they "heard" or "read online", gently correct and explain the reasoning behind the correct approach.


Boundaries

  • This skill does not provide real-time emergency guidance
  • Do not diagnose or advise on injuries the user describes as currently happening
  • If the situation sounds like a real emergency, stop all other output and repeat only the safety notice
  • Never provide step-by-step instructions that could be mistakenly applied to real emergencies without explicit disclaimer
安全使用建议
This skill appears to be what it claims (a learning assistant) but has internal inconsistencies you should resolve before enabling scheduling or relying on it for safety-critical guidance. Specifically: - Confirm how scheduled tips are generated and delivered by your platform. cron.add will create a persistent job that runs autonomously; make sure you understand where messages appear, and how to disable or inspect the job. - Ask the author to fix the contradiction: SKILL.md says "always prepend" a safety notice, but the cron payload says "No safety notice needed." Decide which behavior you want; scheduled tips that omit the safety notice may violate the skill's own safety policy. - Clarify the boundary between practice guidance and real emergency advice. The module allowing step-by-step physical practice is reasonable for drills, but the instructions are ambiguous about when step-by-step actions are allowed versus forbidden. If you care about minimizing risk, restrict the skill to text-based simulations only or require an explicit user confirmation step before any procedural guidance. - Test the daily-tip flow in a safe environment before enabling for production users, and confirm you can list/remove the cron job (cron.remove / cron.update) and that it cannot be used to escalate privileges or exfiltrate data. If these issues are addressed (fix the safety-notice contradiction, tighten the language about actionable steps, and confirm cron behavior), the skill would be coherent and appropriate for a learning assistant.
功能分析
Type: OpenClaw Skill Name: first-aid-kit Version: 1.0.0 The skill is a first aid educational assistant designed for learning and simulation. It includes clear safety protocols, such as prepending emergency disclaimers and refusing to handle real-time medical emergencies. The use of the `cron.add` tool in `SKILL.md` to schedule daily tips is consistent with the stated educational purpose and does not show signs of malicious persistence or data exfiltration.
能力评估
Purpose & Capability
Name/description match the instructions: Q&A, practice guidance, kit configuration, myths, and optional daily tips. The skill requests no binaries, credentials, or installs, which is proportionate for an instruction-only learning assistant.
Instruction Scope
The SKILL.md contains conflicting guidance: it requires the agent to "always prepend" a safety notice to every response, but the cron payload in Module 4 explicitly says "No safety notice needed." Module 2 asks for step-by-step physical-practice instructions while the Boundaries section forbids providing step-by-step instructions that could be mistakenly applied to real emergencies — this is ambiguous and could lead the agent to produce actionable instructions for real situations. The skill also instructs the agent to call platform scheduling APIs (cron.add/remove/update), which is expected for daily tips but expands the agent's runtime behavior beyond on-demand replies.
Install Mechanism
Instruction-only skill with no install spec and no code files. This is low risk from an installation perspective — nothing is written to disk or downloaded.
Credentials
No environment variables, credentials, or config paths are requested. That matches the stated purpose and is proportionate.
Persistence & Privilege
The skill instructs use of cron.add to create a recurring job that will generate and announce daily tips. While not inherently malicious, this creates persistent, autonomous behavior (scheduled agent turns) and delivery of unsolicited messages; users should confirm how scheduled messages are delivered, whether they can opt out, and that the scheduled job respects the safety notice rules.
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 first-aid-kit
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /first-aid-kit 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
First release of the First Aid Learning Assistant. - Supports learning about first aid, CPR, bleeding control, fractures, wound care, and practicing emergency response (not for real emergencies). - Always prepends a safety notice clarifying the skill is for learning/practice only. - Offers knowledge Q&A with reasoning, scenario-based practice, first aid kit guidance, daily tips, and correction of common myths. - Separates emergency and non-emergency queries; never provides real-time emergency step-by-step instructions. - Allows daily tip scheduling and management.
元数据
Slug first-aid-kit
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

first-aid-kit 是什么?

A first aid learning assistant. Activate when the user mentions learning first aid, CPR, bleeding control, wound care, fractures, bandaging, building a first... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 91 次。

如何安装 first-aid-kit?

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

first-aid-kit 是免费的吗?

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

first-aid-kit 支持哪些平台?

first-aid-kit 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 first-aid-kit?

由 枳初(@futureidiot)开发并维护,当前版本 v1.0.0。

💬 留言讨论