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

dot-ai-process-feature-request

Skill336 starsChanged 10 months agoMITView on GitHub

Process a feature request or response from another dot-ai project. Reads from tmp directory, implements/integrates, and writes response if needed.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Read and process a feature request or response from another dot-ai project.

    line 9
  2. Very specific:

    Check for tmp/feature-request.md (incoming request from another project)

    line 13
  3. Very specific:

    If not found, check for tmp/feature-response.md (response to a request we made)

    line 14
  4. Distinctive:

    If neither exists, tell the user there's nothing pending

    line 15
  5. Distinctive:

    Write a response file to the requesting project (path specified in the request)

    line 20
  6. Distinctive:

    Delete the feature-request.md file: after implementation is complete

    line 21
  7. Distinctive:

    Read and present the response

    line 24
  8. Distinctive:

    Use the information to continue integrating the feature

    line 25
  9. Distinctive:

    Delete the feature-response.md file: after integration is complete

    line 26
  10. Distinctive:

    Read and understand the full request/response before proceeding

    line 52
  11. Distinctive:

    Write clear documentation in responses so the requesting project can integrate easily

    line 54

≈ “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

Process Feature Request/Response

Read and process a feature request or response from another dot-ai project.

Process

  1. Check for tmp/feature-request.md (incoming request from another project)
  2. If not found, check for tmp/feature-response.md (response to a request we made)
  3. If neither exists, tell the user there's nothing pending

For Incoming Request (feature-request.md)

  1. Present the request to the user and confirm they want to proceed
  2. Implement the requested feature
  3. Write a response file to the requesting project (path specified in the request)
  4. Delete the feature-request.md file after implementation is complete

For Response (feature-response.md)

  1. Read and present the response
  2. Use the information to continue integrating the feature
  3. Delete the feature-response.md file after integration is complete

Response File Format (for incoming requests only)

# Feature Response from [THIS_PROJECT]

## What Was Implemented

[Brief description of what was built]

## How to Use It

[API signatures, endpoints, types, parameters]

## Examples

[Code examples showing how to call/use the feature]

## Notes

[Any caveats, limitations, or additional context]

Guidelines

  1. Read and understand the full request/response before proceeding
  2. For requests: use your judgment on the best approach
  3. Write clear documentation in responses so the requesting project can integrate easily

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.