agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/client-workspace-scaffolder/SKILL.md

client-workspace-scaffolder

Skill3 starsChanged 6 months agoMITView on GitHub

Scaffold a complete client project folder from your own reusable structure template, with a filled-in brief file and feedback log. Never overwrites existing work. Use when the user says "new client", "set up a client folder", "onboard this client", or "create a project workspace for".

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every client engagement starts with the same folder dance.

    line 8
  2. Very specific:

    Look for a client-workspace.template.md file in the project root.

    line 12
  3. Distinctive:

    Never overwrite anything that exists.

    line 49
  4. Distinctive:

    Never invent client details to fill template fields.

    line 50
  5. Distinctive:

    No em dashes in any generated content.

    line 51

≈ “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

Client Workspace Scaffolder

Every client engagement starts with the same folder dance. This skill does it once, correctly, from a structure you define one time and reuse forever.

Step 0: Load the workspace template (once)

Look for a client-workspace.template.md file in the project root. If it does not exist, ask the user how they structure a client project, then offer to save the answers. The template defines:

CLIENTS_ROOT    The parent folder where client folders live
FOLDERS         The subfolders every client gets, e.g. Assets, Context, Strategy, Website
BRIEF_TEMPLATE  The markdown skeleton for the brief file (status, scope checklist, references, billing section)
EXTRA_FILES     Other starter files, e.g. Feedback.md with a feedback-round table

A sensible default when the user has no opinion yet:

CLIENTS_ROOT: ./Clients
FOLDERS: 01_Assets, 02_Context, Strategy
BRIEF_TEMPLATE: title, Status (Active/Completed/On hold), Started date,
  Brief paragraph, Scope checklist, References, Files note, Billing section
EXTRA_FILES: Feedback.md with a Date/Round/Notes table

Step 1: Collect the essentials

From the user's message: client name (required) and project scope. Anything else they volunteer (industry, contact, deadline) goes into the brief. Ask at most one short round of questions.

Step 2: Check for collisions

List CLIENTS_ROOT first. If a folder with the same or a very similar name exists, stop and ask whether to use it or create a variant. Never overwrite an existing client folder or brief.

Step 3: Scaffold

Create the folder tree from FOLDERS, write the brief from BRIEF_TEMPLATE with everything known filled in (status Active, started today, scope boxes ticked), and create EXTRA_FILES. Leave unknowns as visible placeholders rather than fabricated values. Empty folders are correct; do not create filler files inside them.

Step 4: Report

Show the created tree and the brief contents. Mention the natural next step if the brief has gaps (a discovery conversation or intake questionnaire).

Rules

  • Never overwrite anything that exists.
  • Never invent client details to fill template fields.
  • No em dashes in any generated content.

Output

A ready client folder under CLIENTS_ROOT with a filled brief, a feedback log, and the standard subfolders.

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.