github-issue-creator — Claude Code skill: what it does
Converts voice notes, raw logs, and screenshots into structured GitHub-flavored markdown issue reports. Saves them directly to /issues/ in your repository.
npx skills add microsoft/skills --skill github-issue-creator -a claude-codeWhat github-issue-creator does
This skill turns messy input into structured bug reports. It takes informal voice dictation, pasted error stacks, or references to screenshots and extracts actionable steps. Output goes to the /issues/ directory at the repo root, following the YYYY-MM-DD-short-description.md naming convention.
The prompt template enforces clean separation: summary, environment details, reproduction steps, expected versus actual behavior, and visual attachments. Sensitive parameters get masked with placeholders like [PROJECT_NAME] or [USER_ID]. Severity levels map strictly from Critical for service outages down to Low for cosmetic glitches.
Install this if you regularly test features and capture bugs as unstructured notes. Skip it if you need direct API integration that posts issues straight to remote trackers instead of local markdown files.
What it helps with
- extract reproduction steps from voice dictation and informal notes
- turn terminal error dumps into structured markdown issue templates
- sanitize sensitive project data with standardized placeholders
- categorize defect impact into Critical, High, Medium, or Low severity
- generate organized markdown files inside the local
/issues/folder
Example prompts for the agent
- Convert this voice note into an issue: tried to deploy the agent, it failed silently and disappeared from the list
- Create an issue file from this 403 PERMISSION_DENIED error when publishing to Teams
- Generate a bug report for this broken dashboard layout with screenshot attachment-1.png
How to install github-issue-creator
1Skills CLI (Vercel)
npx skills add microsoft/skills --skill github-issue-creator -a claude-code2Manually: put the files in place
~/.claude/skills/github-issue-creator/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/github-issue-creator/
Manually: put the files in place
.agents/skills/github-issue-creator/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/github-issue-creator/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/skills github-issue-creator2Manually: put the files in place
.github/skills/github-issue-creator/SKILL.mdPlatform CLI
gemini skills install https://github.com/microsoft/skills --path .github/skills/github-issue-creatorManually: put the files in place
.devin/skills/github-issue-creator/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set18
The whole set →Similar
Questions about github-issue-creator
How do I install github-issue-creator in Claude Code?
Run npx skills add microsoft/skills --skill github-issue-creator -a claude-code. Alternatively, copy the prompt file to ~/.claude/skills/github-issue-creator/SKILL.md.
Where does the skill store generated issues?
It writes markdown files into the /issues/ folder at your repository root using the date-stamped pattern YYYY-MM-DD-short-description.md.
How does it evaluate issue severity?
Severity is assigned based on impact: Critical covers outages and data loss, High handles broken core features without workarounds, Medium covers impaired features with workarounds, and Low handles cosmetic flaws.
Source text
SKILL.md · MIT
--- name: github-issue-creator description: Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images/GIFs for visual evidence. --- # GitHub Issue Creator Transform messy input (error logs, voice notes, screenshots) into clean, actionable GitHub issues. ## Output Template ```markdown ## 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] ``` ## Output Location **Create issues as markdown files** in `/issues/` directory at the repo root. Use naming convention: `YYYY-MM-DD-short-description.md` ## Guidelines **Be crisp**: No fluff. Every word should add value. **Extract structure from chaos**: Voice dictation and raw notes often contain the facts buried in casual language. Pull them out. **Infer missing context**: If user mentions "same project" or "the dashboard", use context from conversation or memory to fill in specifics. **Placeholder sensitive data**: Use `[PROJECT_NAME]`, `[USER_ID]`, etc. for anything that might be sensitive. **Match severity to impact**: - Critical: Service down, data loss, security issue - High: Major feature broken, no workaround - Medium: Feature impaired, workaround exists - Low: Minor inconvenience, cosmetic **Image/GIF handling**: Reference attachments inline. Format: `` ## Examples **Input (voice dictation)**: > so I was trying to deploy the agent and it just failed silently no error nothing the workflow ran but then poof gone from the list had to refresh and try again three times **Output**: ```markdown ## Summary Agent deployment fails silently - no error displayed, agent disappears from list ## Environment - **Product/Service**: Azure AI Foundry - **Region/Version**: westus2 ## Reproduction Steps 1. Navigate to agent deployment 2. Configure and deploy agent 3. Observe workflow completes 4. Check agent list ## Expected Behavior Agent appears in list with deployment status, errors shown if deployment fails ## Actual Behavior Agent disappears from list. No error message. Requires page refresh and retry. ## Impact **High** - Blocks agent deployment workflow, no feedback on failure cause ## Additional Context Required 3 retry attempts before successful deployment ``` --- **Input (error paste)**: > Error: PERMISSION_DENIED when publishing to Teams channel. Code: 403. Was working yesterday. **Output**: ```markdown ## Summary 403 PERMISSION_DENIED error when publishing to Teams channel ## Environment - **Product/Service**: Copilot Studio → Teams integration - **Region/Version**: [REGION] ## Reproduction Steps 1. Configure agent for Teams channel 2. Attempt to publish ## Expected Behavior Agent publishes successfully to Teams channel ## Actual Behavior Returns `PERMISSION_DENIED` with code 403 ## Error Details ``` Error: PERMISSION_DENIED Code: 403 ``` ## Impact **High** - Blocks Teams integration, regression from previous working state ## Additional Context Was working yesterday - possible permission/config change or service regression ```
© microsoft · MIT · microsoft/skills