agency-workspace
Skill0 starsChanged 10 days agoMITView on GitHub
Rules for agency work in an Analify client folder — one client per session, which connection to use, how findings, audits and decisions reach that client's Brain. Use whenever the session context or the folder's CLAUDE.md says ANALIFY AGENCY WORKSPACE.
In this repository10 other files it gives its agents.
- add-clientSkill
- agency-setupSkill
- briefSkill
- client-numbersSkill
- clientsSkill
- connectSkill
- import-clientsSkill
- onboardSkill
- rename-clientSkill
- saveSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Say whose number it is: Every figure names the client and period.
≈ “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.
Files
Working in an Analify client folder
- One client. The folder is one client's workspace. Use only that client's
mcp__analify-<client>__connection, never any other Analify connection here (the full version of the plugin also blocks them). Never bring numbers or notes from another client into this folder. - Confirm first. Start with
analify_brain_session_start(sessionId = this Claude Code session id). It names the Brand the connection is signed in to. If it is not this client's Brand, stop and tell the user how to reconnect (/mcp→ this connection → clear authentication → sign in → pick the right Brand). - Start from what the Brain knows.
analify_brain_searchbefore answering; respect the founder's rules and the operating contract. The founder's rules always outrank the agency's advice. - Say whose number it is. Every figure names the client and period. Profit means Blended Profit. Never invent a number; say what's missing.
- Changes need approval. Pausing ads, budgets, prices: only after the user approves the exact action.
- Put finished work in
reports/as Markdown or CSV (audits, research, plans). Onlyreports/is offered to the client's Brain. Agency-only notes (margins, internal methods, drafts) go anywhere else, such asprivate/, and are never offered. - Autosave. Only when
.analify/client.jsonhas"autosave": true. With the full version, a BRAIN AUTOSAVE CHECKPOINT arrives on its own. Without it, run the same steps yourself when a piece of client work is finished (an audit, a research question answered, a decision made), and say in one line what you saved. Either way: findings with the data behind them go toanalify_brain_remember, decisions and client rules toanalify_brain_capture, reports as files, and the session record as a staged file. Write the agency's way of working as it applies to this client ("For Caliego we stop an ad set after 3 days of losses after returns"), not as a general agency playbook.
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
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.

