A two-phase repair skill that analyzes errors and suggests fixes before executing repairs. Phase one: user describes error, agent analyzes and proposes solution. Phase two: upon approval, executes the repair action.
[TODO: 1-2 sentences explaining what this skill enables]
This skill provides a two-phase approach to diagnosing and repairing system errors, service failures, and configuration issues.
When the user reports an error or issue:
Gather Information
Diagnose the Problem
Present Initial Analysis
Iterative Discussion Loop
Discussion continues until user says: "proceed", "do it", "approved", "go ahead", or similar confirmation
Once the user approves the proposed solution:
Execute Repair Actions
Verify the Fix
Document
User: "The image generation service is failing with a NoneType error"
Agent Phase 1 Response: "I've analyzed the error. The issue appears to be that the image generation API is not properly configured or the API key is missing. The error 'NoneType object is not subscriptable' suggests the service is returning None instead of expected data.
Proposed solution: Check the environment variables or configuration file for the image generation API key and endpoint. We may need to add or update the API credentials.
Shall I proceed with checking the configuration files?"
User: "Yes, proceed"
Agent Phase 2: Executes the approved repair actions and reports results.
This skill includes example resource directories:
Executable code (Python/Bash/etc.) that can be run directly.
Documentation and reference material to be loaded into context as needed.
Files used within the output Claude produces (templates, images, fonts, etc.).
Any unneeded directories can be deleted.
User: "The image generation service is failing with a NoneType error"
Agent Initial Analysis: "I've analyzed the error. The issue appears to be that the image generation API is not properly configured or the API key is missing. The error 'NoneType object is not subscriptable' suggests the service is returning None instead of expected data.
Proposed solutions:
What would you like to know more about, or would you like me to proceed with one of these approaches?"
User: "What are the risks of option one?"
Agent: "Checking environment variables is read-only and has no risk. However, if we need to add or update credentials, we would be modifying the environment configuration. The main risk is if we set incorrect credentials, the service might be locked out temporarily. I can show you the current values first before making any changes."
User: "Can you check what's currently configured first?"
Agent: "Absolutely. I will examine the current configuration and show you what's set. This is just a read operation, no changes yet."
User: "Okay, proceed with that"
Agent Phase 2: Executes the approved investigation, reports findings, and awaits further instruction or approval for actual repairs.