Create GitHub Issues from Unstructured Data

GitHub Issue Creator transforms messy input - error logs, voice notes, screenshots - into clean, actionable GitHub issues following a fixed template:

### Summary
[One-line description of the issue]

### Environment
- **Product/Service**: 
- **Region/Version**: 
- **Browser/OS**: (if relevant)

### Reproduction Steps
1. [Step]
2. [Step]
3. [Step]

### Expected Behavior
[What should happen]

### Actual Behavior
[What actually happens]

### Error Details

[Error message/code if applicable]

### Visual Evidence
[Reference to attached screenshots/GIFs]

### Impact
[Severity: Critical/High/Medium/Low + brief explanation]

### Additional Context
[Any other relevant details]

Issues are written as markdown files in an /issues/ directory at the repo root, named YYYY-MM-DD-short-description.md.

Use this skill when you have unstructured bug input - pasted errors, support notes, screenshots, or voice dictation - and need to turn it into a clean GitHub issue with a summary, reproduction steps, expected-versus-actual behavior, impact, and attachment references. Its guidelines: be crisp with no fluff, extract structure from chaos since voice dictation and raw notes often bury facts in casual language, infer missing context from the conversation when the user references "same project" or "the dashboard," and placeholder any potentially sensitive data ([PROJECT_NAME], [USER_ID], etc.) rather than including it directly. Severity is matched to impact using a fixed scale: Critical for service-down, data-loss, or security issues, High for a major feature broken with no workaround, Medium for an impaired feature with a workaround, Low for a minor or cosmetic issue.

Input is unstructured bug reports - voice dictation, pasted error text, screenshots; output is a markdown issue file following the fixed template, saved to /issues/YYYY-MM-DD-short-description.md. A worked example turns a rambling voice note about a silently-failing agent deployment into a structured issue naming the product (Azure AI Foundry), region (westus2), reproduction steps, and a High-severity impact rating; another turns a raw error paste ("PERMISSION_DENIED... Code: 403... Was working yesterday") into an issue that preserves the exact error code and flags the "was working yesterday" detail as a possible regression.

Developers and support staff who receive bug reports as voice notes, raw error pastes, or scattered notes and need them turned into properly structured, severity-rated GitHub issues rather than filing unstructured or incomplete tickets. Image and GIF references are handled inline in the same template rather than as a separate attachment step, and sensitive values are placeholdered rather than typed out verbatim, so the resulting issue file is safe to commit into the repository's own /issues/ directory alongside the codebase it describes.