agentleFS
etretr/groundwork/skills/select-project/SKILL.md

select-project

Skill45 starsChanged 4 days agoMITView on GitHub

This skill should be used when the user wants to switch between projects in a monorepo - lists projects from .groundwork.yml and sets the active project

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Very specific:

    Read .groundwork.yml from the repo root.

    line 15
  2. Very specific:

    Use AskUserQuestion to ask which project to work on.

    line 35
  3. Distinctive:

    After switching, show the project's spec status:

    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

Select Project Skill

Quick project switching within a configured monorepo.

Workflow

Step 1: Load Config

Read .groundwork.yml from the repo root.

If not found: "No .groundwork.yml found. Run /groundwork:setup-repo to configure your repository first."

Step 2: List Projects

Present available projects with their spec status:

## Available Projects

| # | Project | Path | Specs |
|---|---------|------|-------|
| 1 | web-app | apps/web-app | PRD, Architecture, Tasks |
| 2 | mobile-app | apps/mobile-app | PRD |
| 3 | api-server | services/api | (none) |

For each project, check if <path>/specs/ exists and what spec files are present.

Use AskUserQuestion to ask which project to work on.

Step 3: Set Context

Persist the selection and use the returned project/root values as the active context:

node ${CLAUDE_PLUGIN_ROOT}/lib/persist-project.js "<selected-name>"

The script resolves its own harness-specific selection scope internally — no env vars required.

Confirm: "Switched to project <name>. Specs at <path>/specs/."

Selection scope: in a terminal pane, the selection is pane-scoped, survives /clear, and other panes are unaffected. Where the harness has no pane identity (chat-window UIs), every selector invocation prints a groundwork-project-selection-v1 receipt; harnesses that deliver the tool response to the PostToolUse pin hook pin that receipt to the chat's own session snapshot, so concurrent chats keep independent selections. On targets without that hook payload support (manual runs, hookless exports), only a workspace-level default shared across chats exists — treat the selection as conversation-scoped: state the active project in your reply, and pass it explicitly on later invocations (--project <name> where plan-task, implement-task, and validate support it, or GROUNDWORK_PROJECT=<name> for lib scripts).

Step 4: Show Status

After switching, show the project's spec status:

  • PRD: exists / missing
  • Architecture: exists / missing
  • Tasks: exists / missing
  • Design System: exists / missing

Suggest next action based on what's available.

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.