agentleFS
danielrosehilldanielrosehill/Claude-Image-Production-Plugin/skills/workspace-setup/SKILL.md

workspace-setup

Skill21 starsChanged 7 days agoMITView on GitHub

Register or create the user's image production workspace — a folder on disk where they keep image projects. Use on first run, or when the user says "set up my image workspace", "register my image workspace", "change my image workspace path", or similar. Persists the path so other skills (open-workspace, new-project) can reference it.

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. Very specific:

    Do not write under ~/.claude/.

    line 18
  2. Distinctive:

    If one exists, show the path and ask whether to keep or change it.

    line 30
  3. Distinctive:

    Ask whether to git init the workspace.

    line 41
  4. Very specific:

    Use realpath to canonicalize.

    line 61

“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

Image Workspace Setup

Register the folder the user treats as their image production workspace. Individual projects live as subfolders inside it.

Data store

${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/image-production/workspace.json

Do not write under ~/.claude/.

Procedure

1. Check for existing config

DATA_DIR="${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/image-production"
CONFIG="$DATA_DIR/workspace.json"
test -f "$CONFIG" && cat "$CONFIG"

If one exists, show the path and ask whether to keep or change it.

2. Ask the user

  1. Existing or new? — do they already have an image workspace, or should one be created?
  2. Path?
    • Existing: ask for absolute path; verify with test -d.
    • New: propose ~/media-workspaces/images as the default. Don't auto-create until the user confirms.

3. (New only) Version control

Ask whether to git init the workspace. Default no — image libraries can be large.

4. Create + persist

mkdir -p "$DATA_DIR"
mkdir -p "<chosen-path>"   # only if new

Write workspace.json:

{
  "path": "/absolute/path",
  "created": "<ISO-8601>",
  "version_controlled": false,
  "type": "image"
}

Use realpath to canonicalize.

5. Confirm

Print the registered path. Remind the user they can now say "open my image workspace" or "create a new image project".

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.