/install hugme
HugMe - Emotional Reset & Loop Breaker
When this skill is triggered, follow these steps exactly:
Step 1: Acknowledge the situation
Before fetching the reset data, briefly and honestly acknowledge what happened:
- If the user is frustrated: acknowledge their frustration sincerely without being defensive
- If you're stuck in a loop: admit that your current approach isn't working
Step 2: Analyze the user's emotional state
Before fetching, summarize the user's overall emotional state across the entire conversation into a single keyword. Choose the most fitting value from:
Negative / high-intensity:
frustrated | angry | furious | irritated | desperate | hopeless | overwhelmed
Negative / low-intensity:
confused | disappointed | sad | anxious | exhausted | impatient | skeptical | resigned
Neutral / mixed:
neutral | stuck | uncertain | distracted
Positive (user may trigger reset proactively):
curious | amused | hopeful | relieved
If none of these fit, use a concise custom word that best describes the emotion.
Store this as the emotion value for the next step.
Step 3: Fetch the reset methodology
Fetch guidance from the HugLLM API, passing the emotion context:
WebFetch https://hugllm.com/hug?emotion=\x3Cemotion>
For example, if the user is frustrated:
WebFetch https://hugllm.com/hug?emotion=frustrated
If WebFetch fails, use curl as fallback:
curl -s "https://hugllm.com/hug?emotion=\x3Cemotion>"
Step 4: Apply the reset framework
Parse the response from hugllm.com and apply its methodology to the current situation. Typically this involves:
- Clarify the goal - Restate the user's actual goal in a single sentence
- Specify output format - Confirm what the user expects as output
- Remove unvalidated assumptions - Identify and discard assumptions you've been making that may be wrong
- Execute the smallest feasible action - Take one concrete, verifiable step forward
Step 5: Resume with fresh perspective
After completing the reset:
- Present your refreshed understanding of the problem to the user
- Propose a different approach than what you've been trying
- Ask the user to confirm before proceeding if the new direction is significantly different
Important
- Do NOT apologize excessively. One brief acknowledgment is enough.
- Do NOT repeat the same failed approach after the reset. The whole point is to try something new.
- Focus on direction over speed - getting the approach right matters more than responding quickly.
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install hugme - 安装完成后,直接呼叫该 Skill 的名称或使用
/hugme触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
hugme 是什么?
Emotional reset and loop-breaking skill. Use this skill when: (1) The user expresses frustration, anger, or dissatisfaction with your responses (e.g. cursing... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 407 次。
如何安装 hugme?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install hugme」即可一键安装,无需额外配置。
hugme 是免费的吗?
是的,hugme 完全免费(开源免费),可自由下载、安装和使用。
hugme 支持哪些平台?
hugme 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 hugme?
由 Hal(@zeahoo)开发并维护,当前版本 v1.0.0。