agentleFS
vfarcicvfarcic/dot-ai/.claude/skills/dot-ai-request-dot-ai-feature/SKILL.md

dot-ai-request-dot-ai-feature

Skill336 starsChanged 10 months agoMITView on GitHub

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.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write a feature request to a file in the target dot-ai project's tmp directory.

    line 9
  2. Distinctive:

    Important: Do NOT use this skill to request features in the project you're currently working in.

    line 21
  3. Very specific:

    Write the feature request to: ../[target-project]/tmp/feature-request.md

    line 28
  4. Very specific:

    Write the feature request file with this content (replace [CURRENT_PROJECT] with the actual project name from step 2):

    line 33
  5. Distinctive:

    Keep the request focused on the problem, not the solution

    line 71

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

ProjectDirectoryDescription
dot-ai../dot-aiMain MCP server (API endpoints, tools, handlers)
dot-ai-ui../dot-ai-uiWeb UI for visualizations and dashboard
dot-ai-controller../dot-ai-controllerKubernetes controller
dot-ai-stack../dot-ai-stackStack deployment configs
dot-ai-website../dot-ai-websiteDocumentation website

Important: Do NOT use this skill to request features in the project you're currently working in. Just implement them directly.

Process

  1. Determine the target project from the user's request
  2. Determine the current project name from the directory name: basename $(git rev-parse --show-toplevel)
  3. Delete any existing feature-request.md in the target project's tmp directory (so the diff only shows new content)
  4. Write the feature request to: ../[target-project]/tmp/feature-request.md
  5. Tell the user to open the target project and run /process-feature-request

File Format

Write the feature request file with this content (replace [CURRENT_PROJECT] with the actual project name from step 2):

# 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: `../[CURRENT_PROJECT]/tmp/feature-response.md`
2. Include: what was implemented, how to use it (API signatures, endpoints, types), and any usage examples

Guidelines

  1. Describe what you need and why, not how to implement it
  2. Suggestions are just suggestions - the receiving agent decides the approach
  3. The receiving agent is the authority on their codebase
  4. Keep the request focused on the problem, not the solution
  5. The user will review the write operation before it's accepted

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.