agentleFS
Sign inStart free
jumpstarter-devjumpstarter-dev/jumpstarter/.cursor/skills/propose-jep/SKILL.md

propose-jep

Skill233 starsChanged 37 days agoApache-2.0View on GitHub

Create a new Jumpstarter Enhancement Proposal (JEP)

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. Distinctive:

    Before writing the JEP, ask the user clarifying questions to understand:

    line 25
  2. Very specific:

    If the user provided a description in $ARGUMENTS, use it as a starting point but still ask about gaps.

    line 32
  3. Distinctive:

    All mandatory sections based on the information gathered

    line 44
  4. Very specific:

    Add the new JEP to the appropriate table in docs/source/contributing/jeps/index.md (Process, Standards Track, or Informational).

    line 49
  5. Very specific:

    Add the new JEP file to the {toctree} directive at the bottom of docs/source/contributing/jeps/index.md.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Propose a JEP

You are helping the user create a new Jumpstarter Enhancement Proposal (JEP).

Context

JEPs are design documents for substantial changes to the Jumpstarter project - changes that affect multiple components, alter public APIs or protocols, or require community consensus. Read .cursor/rules/jep-process.mdc for the full process definition.

JEP topic: $ARGUMENTS

Steps

1. Determine the next JEP number

List existing files in docs/source/contributing/jeps/ and pick the next available incrementing integer. JEP-0000 through JEP-0009 are reserved for process/meta-JEPs, so start from JEP-0010 for regular proposals.

2. Gather information

Before writing the JEP, ask the user clarifying questions to understand:

  • What problem does this solve? - The motivation section needs a concrete problem description.
  • Who is affected? - Which components, drivers, or user workflows are impacted?
  • What are the alternatives? - Each design decision needs at least two alternatives considered.
  • What are the compatibility implications? - Does this break existing APIs, protocols, or workflows?

If the user provided a description in $ARGUMENTS, use it as a starting point but still ask about gaps.

3. Create the JEP file

Copy the template from docs/source/contributing/jeps/JEP-NNNN-template.md and create a new file at docs/source/contributing/jeps/JEP-NNNN-short-title.md where:

  • NNNN is the zero-padded next number
  • short-title is a descriptive slug derived from the proposal title

Fill in:

  • The metadata table with the JEP number, title, author (ask the user), status Draft, type, and today's date
  • All mandatory sections based on the information gathered
  • Mark optional sections that need further input with TODO comments

4. Update the JEP index

Add the new JEP to the appropriate table in docs/source/contributing/jeps/index.md (Process, Standards Track, or Informational).

Add the new JEP file to the {toctree} directive at the bottom of docs/source/contributing/jeps/index.md.

5. Present the result

Show the user:

  • The file path of the new JEP
  • A summary of sections that are complete vs need further work
  • Remind them to set status to Discussion when the PR is ready for review
  • Remind them to apply the jep label to their pull request

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.

Check your setup, free