name: request-dot-ai-feature description: Generate a feature request prompt for another dot-ai project. Use when you need a feature implemented in a sibling project (MCP server, controller, etc.) to unblock work in the current project. allowed-tools:
- Read
- Grep
- Glob
Request Feature in dot-ai Project
Write a feature request to a file in the target dot-ai project's tmp directory. The user will review and approve the write operation.
Projects
| Project | Directory | Description |
|---|---|---|
| dot-ai | ../dot-ai |
Main MCP server (API endpoints, tools, handlers) |
| dot-ai-ui | ../dot-ai-ui |
Web UI for visualizations and dashboard |
| dot-ai-controller | ../dot-ai-controller |
Kubernetes controller |
| dot-ai-stack | ../dot-ai-stack |
Stack deployment configs |
| dot-ai-website | ../dot-ai-website |
Documentation website |
Important: Do NOT use this skill to request features in the project you're currently working in. Just implement them directly.
Process
- Determine the target project from the user's request
- Delete any existing feature-request.md in the target project's tmp directory (so the diff only shows new content)
- Write the feature request to:
../[target-project]/tmp/feature-request.md - Tell the user to open the target project and run
/process-feature-request
File Format
Write the feature request file with this content:
# Feature Request from [CURRENT_PROJECT]
**Requesting project directory:** ../[current-project]
## What We Need
[DESCRIPTION OF WHAT WE NEED AND WHY]
## Our Suggestion
(You decide the best approach)
- [Suggested approach or implementation idea]
## Context
[What this unblocks in our project]
## Notes
You're the expert on this codebase. Feel free to implement this differently if there's a better approach, or push back if this doesn't make sense.
## Response Instructions
After implementing this feature, write a response file to help the requesting project integrate:
1. Write to: `../[requesting-project]/tmp/feature-response.md`
2. Include: what was implemented, how to use it (API signatures, endpoints, types), and any usage examples
Guidelines
- Describe what you need and why, not how to implement it
- Suggestions are just suggestions - the receiving agent decides the approach
- The receiving agent is the authority on their codebase
- Keep the request focused on the problem, not the solution
- The user will review the write operation before it's accepted
chat Comments (0)
Sign in to join the discussion and leave a comment.
Skill Details
GitHub Stars
277
GitHub Forks
55
Created
Jan 2026
Last Updated
il y a 5 mois
tools
tools productivity tools
Related Skills
Build your own?
Join 12,000+ developers contributing to the Claude ecosystem.
No comments yet. Be the first to share your thoughts!