YouTip

A Skill that can only run under ideal conditions is fragile. A robust Skill needs to anticipate common errors, provide clear feedback, and recover automatically when possible. * * * ## Three Levels of Error Handling | Level | Location | Handling | | --- | --- | --- | | Input Validation Error | Before Execution | Check input, reject directly if invalid and explain why | | Runtime Error | During Script Execution | Catch exceptions, output structured error information | | Result Anomaly | After Execution | Verify if output meets expectations, trigger remediation if not | * * * ## Define Error Handling Strategy in SKILL.md SKILL.md should contain a clear error handling section that tells Claude what to do when encountering problems. ## Examples ## Error Handling ### Input Issues - File does not exist: Inform the user the file path is incorrect, please re-upload - File format not supported: List supported formats (pdf, docx, txt), please convert and try again - File is empty: Inform the user the file content is empty and cannot be processed ### Execution Issues - Script execution failed: Display the complete error message to the user, do not hide it - Dependency not installed: Try auto-install first (pip install), if it fails inform the user to install manually - Timeout: If not completed after 60 seconds, output current progress and ask the user whether to continue waiting ### Result Issues - Output file is empty: Re-check the processing logic and explain possible reasons to the user - Output format does not match expectations: Display actual output and ask the user if they are satisfied * * * ## Standard Error Handling Patterns in Scripts Python scripts should use try-except structure and uniformly return JSON containing status field. ## Example # File path: scripts/error_handling_demo.py import json import sys import os class SkillError(Exception): """Skill custom exception base class""" def __init__ (self, message: str,code: str): self.message= message self.code=code# Error code for program to determine error type super(). __init__ (message) class InputError(SkillError): """Input validation error""" pass class ProcessError(SkillError): """Processing error""" pass def validate_input(file_path: str) ->None: """Validate input, raise InputError when error occurs""" if not file_path: raise InputError("File path not provided","MISSING_FILE") if not os.path.exists(file_path): raise InputError(f"File does not exist：{file_path}","FILE_NOT_FOUND") if os.path.getsize(file_path)==0: raise InputError(f"File is empty：{file_path}","EMPTY_FILE") def process(file_path: str) ->dict: """Main processing logic""" try: validate_input(file_path) with open(file_path,"r", encoding="utf-8")as f: content = f.read() # Actual processing logic (simplified to line count here) lines = content.split(" ") return{ "status": "success", "data": { "file": file_path, "lines": len(lines), "chars": len(content) } } except InputError as e: # Input error: user can retry after correction return{ "st ```