agentleFS
Sign inStart free
CalebAnderson-CoderCalebAnderson-Coder/ai-agency-os-starter/skills/clients/client-workspace/SKILL.md

client-workspace

Skill0 starsChanged 21 days agoMITView on GitHub

Create and maintain an isolated workspace per client, with a client CLAUDE.md holding brand voice, rules, banned claims, contacts, access map, and logs. Use when adding a client, switching clients, or when Claude must "act as" a specific client.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every client lives in its own folder so voice, rules and context never leak between clients.

    line 8
  2. Very specific:

    Start every client task with cd clients/<slug> (or open Claude Code there) so the client CLAUDE.md loads on top of the agency CLAUDE.md.

    line 37
  3. Distinctive:

    Never reuse one client's copy, data or assets for another.

    line 38

≈ “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

Client Workspace

Every client lives in its own folder so voice, rules and context never leak between clients.

Layout

clients/
  _template/                 copy this for each new client
  <client-slug>/
    CLAUDE.md                client rules (loaded when you work inside this folder)
    brand/voice.md           tone, vocabulary, 3-5 approved writing samples
    brand/claims.md          approved claims + sources; banned claims
    BRIEF.md                 goals, KPIs, scope (from client-onboarding)
    SCOPE.md                 contracted deliverables (from proposal-sow)
    LOG.md                   dated log of work + decisions
    CHANGES.md               change requests (from scope-guard)
    reports/  drafts/  meetings/  assets/

Client CLAUDE.md template

# Client: [Client Name]  (slug: [slug])
- Industry / ICP:
- Voice: (3 adjectives) — see brand/voice.md. Never: (words/phrases)
- Approved claims only from brand/claims.md. No invented stats or testimonials.
- Contacts: decision-maker [role], day-to-day [role] (names live in your CRM, not here)
- Access: where each credential lives (password manager entry names). NEVER store secrets here.
- Approval rules: what needs client sign-off (copy, spend, deploy, publishing)
- Reporting: cadence, KPIs, data sources (GA4 property, Search Console site, ad accounts as env var names)
- Out of scope: see SCOPE.md

Rules

  1. Start every client task with cd clients/<slug> (or open Claude Code there) so the client CLAUDE.md loads on top of the agency CLAUDE.md.
  2. Never reuse one client's copy, data or assets for another. When asked to "reuse", genericize first.
  3. Append a line to LOG.md after each work session: date, what, decisions, next step.
  4. /client-switch <slug>: summarize the client's CLAUDE.md, last 5 LOG entries and open CHANGES before doing anything.

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