agentleFS
Sign inStart free
lepresklepresk/groundwork/.claude/skills/new-module/SKILL.md

new-module

Skill0 starsChanged 50 days agoMITView on GitHub

Create a new feature module (database table, shared contracts, API endpoints, integration tests) with the repository generator. Use when the user asks for a new resource, entity, or feature area such as "add invoices" or "we need projects".

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never hand-write a module skeleton.

    line 8
  2. Very specific:

    Run pnpm gen module <name> and read the list of created and updated files.

    line 11
  3. Distinctive:

    Add new error codes the usual way (shared registry, API catalog, web copy).

    line 19
  4. Very specific:

    Run the verify skill.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

New feature module

Never hand-write a module skeleton. The generator produces code that already passes lint, types, and tests.

  1. Pick the singular kebab-case name (invoice, api-key). Irregular plural: pass --plural.
  2. Run pnpm gen module <name> and read the list of created and updated files.
  3. Rebuild contracts: pnpm --filter @groundwork/db --filter @groundwork/shared build.
  4. Replace the placeholder name column with the real fields, in this order, keeping them consistent:
    • packages/db/src/schema/<plural>.ts (columns, indexes, foreign keys with explicit onDelete)
    • packages/shared/src/<plural>.ts (response strictObject, request schema with normalization)
    • apps/api/src/modules/<plural>/<plural>.mappers.ts and the repository create input
    • apps/api/test/integration/<plural>.test.ts (extend, never delete, the generated cases)
  5. Generate the migration: pnpm db:generate --name add_<plural>, review the SQL, then pnpm db:migrate.
  6. Add new error codes the usual way (shared registry, API catalog, web copy). Compile errors list the missing entries.
  7. Run the verify skill.

Report the endpoints created and the migration name.

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