Language routing / 语言路由 Detect the user's language from the latest message.

• If the user writes in English, continue with this English file and respond in English.
• If the user writes in Chinese, read SKILL.md in this same directory and respond in Chinese. Always match the response language to the user's input language.

chatmosp-msr-generator

1. Core Responsibilities

1. Execute metal cluster structure generation (Wulff construction)
2. Validate input parameter completeness
3. Warn on large clusters (R ≥ 50Å)
4. Generate structure files + visualization images
5. Send results to user via Feishu

2. Prerequisites

• ✅ parameter-builder has built the parameters
• ✅ User has confirmed via the 5-option prompt (see parameter-builder)
• ✅ input.json exists at OUTPUT/{task_name}/input.json
• ✅ Target directory has been created by file-organizer
• ✅ External mosp-for-chatMOSP installed, with utils/msr.py and utils/paint.py
• ❌ DO NOT bypass parameter-builder and build parameters manually
• ❌ DO NOT skip user confirmation and execute calculation directly

3. Input Contract (Required fields in input.json)

Gas entropy (Gas1_S / Gas2_S) is calculated by parameter-builder using the formula in §7.1. DO NOT manually fill or reuse values from example files.

4. Large-Cluster Warning

MUST check cluster radius before execution. Warn user when R ≥ 50Å:

⚠️ Calculation Time Warning:
Current cluster radius is {R}Å, estimated calculation time is approximately
{estimated_minutes} minutes.
(R=50Å ~20 min, R=65Å ~40 min)
Continue with MSR calculation?

5. Execution Steps

Step 1: Run MSR calculation

cd mosp-for-chatMOSP
python3 utils/msr.py --json OUTPUT/{task_name}/input.json --output OUTPUT/{task_name}/
cd -

Step 2: Validate output

ls -lh OUTPUT/{task_name}/ini.xyz
ls -lh OUTPUT/{task_name}/{task_name}_cluster.xyz

• ✅ ini.xyz MUST exist and be > 0KB, otherwise MSR failed
• ✅ {task_name}_cluster.xyz MUST exist (for visualization)

Step 3: Generate visualization (two separate steps)

# Static structure image
cd mosp-for-chatMOSP && python3 utils/paint.py \
  OUTPUT/{task_name}/{task_name}_cluster.xyz \
  --output OUTPUT/{task_name}/structure.png

# Rotation animation
cd mosp-for-chatMOSP && python3 utils/paint.py \
  OUTPUT/{task_name}/{task_name}_cluster.xyz \
  --gif OUTPUT/{task_name}/rotation.gif

paint.py can only generate ONE type per call (PNG OR GIF); two separate steps are required. For atom counts > 20,000, recommend generating only the static image.

Step 4: Send to user via Feishu

{
  "action": "send",
  "channel": "feishu",
  "filePath": "{workspace}/mosp-for-chatMOSP/OUTPUT/{task_name}/structure.png",
  "caption": "{Metal}-{T}K-{P}Pa-CO{pp1}%-O2{pp2}%-R{R}Å"
}

Requirements:

1. Send structure.png to user
2. Send rotation.gif to user
3. Briefly describe structural features (e.g., "Pd nanoparticle shows truncated octahedron, mainly exposing (111) facets")

6. Output Files

7. Key Principles

• MSR input.json MUST NOT contain KMC parameters — KMC parameters are prepared independently by kmc-simulator
• ini.xyz is the OUTPUT of MSR, NOT the input — do not prepare ini.xyz for MSR tasks
• DO NOT directly copy example files from MOSP_database — use parameter-builder to recalculate gas entropy

8. Error Handling

9. Cross-Skill Handoff

• MSR → KMC: After MSR completes, ini.xyz is produced. KMC tasks independently fetch complete KMC parameters from MOSP_database via kmc-simulator. Do NOT reuse this skill's input.json. See kmc-simulator.
• MSR failure → parameter-builder: Parameter issues go back to parameter-builder for adjustment.
• Re-running MSR: If directory already exists, ask user before overwriting.

10. Dependencies

• mosp-for-chatMOSP — MSR calculation engine (cloned)
• chatmosp-parameter-builder — parameter building and gas entropy calculation
• chatmosp-file-organizer — directory structure
• chatmosp-input-coordinator — task entry point

11. File Structure

chatmosp-msr-generator/
├── SKILL.md       # Chinese reference
└── SKILL_cn.md    # This file (English)

12. Example

User: Calculate Pt nanoparticle cluster structure at 500K

System: [Recognize as MSR task → parameter-builder searches params →
        Show 5-option confirmation → User confirms → R=20Å, no warning →
        Invoke msr.py → Validate output → Generate PNG+GIF → Send via Feishu]

ChatMOSP Companion Skills

This skill is part of the ChatMOSP skill set. For complete functionality, install the companion ChatMOSP skills from ClawHub when they are missing:

• chatmosp-input-coordinator
• chatmosp-parameter-builder
• chatmosp-msr-generator
• chatmosp-kmc-simulator
• chatmosp-literature-search
• chatmosp-file-organizer

If a required companion skill is unavailable, ask the user to install the missing ChatMOSP skill from ClawHub before continuing. Use the GitHub repository only as a fallback.