Start Issue
This skill initiates a new issue tracking task, streamlining workflow and ensuring prompt attention to problems.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add start-issue npx -- -y @trustedskills/start-issue
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"start-issue": {
"command": "npx",
"args": [
"-y",
"@trustedskills/start-issue"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The start-issue skill allows AI agents to create new issues in a specified repository on GitHub. It can automatically populate issue titles and bodies with provided text, streamlining the process of reporting bugs or suggesting features. The agent can also specify labels to apply to the newly created issue.
When to use it
- When you need an AI agent to report a bug found during testing.
- To automate the creation of feature requests based on user feedback.
- For quickly logging issues identified by automated monitoring tools.
- When collaborating with developers and needing to consistently format issue submissions.
Key capabilities
- Creates new GitHub issues.
- Sets issue titles.
- Populates issue bodies (descriptions).
- Applies labels to the created issue.
Example prompts
- "Create a new issue in repository 'my-org/my-repo' with title 'Broken button on homepage' and body 'The submit button is not working.'"
- "Start an issue in 'user/project' labeled 'bug' with the title 'Incorrect calculation' and description 'The total amount is calculated incorrectly'."
- “Create a new feature request in ‘team/app’ titled ‘Dark Mode Support’."
Tips & gotchas
- Ensure the AI agent has appropriate permissions (write access) to create issues in the specified GitHub repository. The skill requires authentication with a GitHub token or similar credential.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.