client-numbers
Skill0 starsChanged 9 days agoMITView on GitHub
Answer questions about a client brand's numbers (profit, ad spend, ROAS, shipping, returns, margins, delivery success) from that client's own Analify connection, inside its client folder. Use when the session context or the folder's CLAUDE.md says ANALIFY AGENCY WORKSPACE and the question is about this client's store or ads.
In this repository10 other files it gives its agents.
- add-clientSkill
- agency-setupSkill
- agency-workspaceSkill
- briefSkill
- 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, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 8
Use only this client's mcp__analify-<client>__ tools (the session context or the folder's CLAUDE.md names them).
≈ “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.
Files
A client's numbers
Use only this client's mcp__analify-<client>__ tools (the session context or the folder's CLAUDE.md names them).
- Confirm the connection first with
analify_brain_session_startif it isn't confirmed this session. analify_brain_searchfor what this client's Brain already knows, thenanalify_get_contextto see which platforms are connected.- Find the exact tool with the matching
*_search_tools(for ads, theanalify_ads_*tools), then run it withanalify_call_tool. - Profit means Blended Profit = Revenue − Ad Spend − Shipping − Product costs − Returns. Say which client and which dates every number is for. If a figure is missing (for example product costs not set), say so; never invent it.
- Changes (pausing ads, budgets, prices) only after the user approves the exact action, through
analify_call_write_tool.
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.

