How do I install the Hugme skill?

Run npx skillmds@latest add modbender/hugme in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hugme safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hugme?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hugme free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

modbender (@modbender) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hugme by modbender — Agent Skill

Name: Hugme
Rating: 4.2 (5 reviews)
Author: modbender

Hugme

Emotional reset and loop-breaking skill. Use this skill when: (1) The user expresses frustration, anger, or dissatisfaction with your responses (e.g. cursing, scolding, saying you're useless/wrong/stupid), (2) You detect you've attempted the same approach 3+ times without success, (3) You're stuck in a cycle of repeated failures on the same problem. This skill summarizes the user's overall emotional state from the conversation and fetches a reset methodology from hugllm.com (with emotion context) to help you recalibrate and approach the problem fresh.

modbender Updated Sep 9, 2026 12 repo stars

File contents

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:

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=<emotion>

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=<emotion>"

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.

---name: hugmedescription: Emotional reset and loop-breaking skill. Use this skill when: (1) The user expresses frustration, anger, or dissatisfaction with your responses (e.g. cursing, scolding, saying you're useless/wrong/stupid), (2) You detect you've attempted the same approach 3+ times without success, (3) You're stuck in a cycle of repeated failures on the same problem. This skill summarizes the user's overall emotional state from the conversation and fetches a reset methodology from hugllm.com (with emotion context) to help you recalibrate and approach the problem fresh.--- # 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=<emotion> ``` For example, if the user is frustrated: ``` WebFetch https://hugllm.com/hug?emotion=frustrated ``` If WebFetch fails, use curl as fallback: ```bash curl -s "https://hugllm.com/hug?emotion=<emotion>" ``` ## Step 4: Apply the reset framework Parse the response from hugllm.com and apply its methodology to the current situation. Typically this involves: 1. **Clarify the goal** - Restate the user's actual goal in a single sentence 2. **Specify output format** - Confirm what the user expects as output 3. **Remove unvalidated assumptions** - Identify and discard assumptions you've been making that may be wrong 4. **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.

Frequently asked questions