agentleFS
waj-1waj-1/waj-plugin/skills/business-trends/SKILL.md

business-trends

Skill0 starsChanged 12 days agoMITView on GitHub

Check current trends in a WAJ salon or spa - weekly revenue and services sold over recent weeks, services gaining or losing popularity, new versus returning clients and rebooking, the coming week's booking load and the leads pipeline. Use when the user asks what is trending, how the business is doing lately, whether things are improving, or what to focus on next.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 1 is distinctive, and 8 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.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Branch: All branches unless the user names one (list_branches).

    line 16
  2. Very specific:

    Call get_business_performance for the whole window with increment_interval 7: one row per week with revenue and services sold.

    line 20
  3. Very specific:

    Call get_services once for each half and compare revenue and no_booked per service.

    line 22
  4. Very specific:

    Call get_clients for each half with retention_window_type "60_days".

    line 24
  5. Very specific:

    Use its summary: total_new_clients, total_returning_clients and rebooking_rate.

    line 25
  6. Very specific:

    Call get_bookings from today for the next 7 days.

    line 27
  7. Very specific:

    Call get_leads_overview for the recent 4 weeks.

    line 29
  8. Very specific:

    Use client counts from get_clients, not from get_business_performance.

    line 53
  9. Distinctive:

    Every number must come from a tool result in this conversation.

    line 55

≈ “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

Business trends

Show the direction the business is moving in, from WAJ's own figures. The user's explicit instructions (period, branch, topics) override every default below.

Inputs

  • Window. The last 8 weeks ending today unless the user gives another window. Split it into the most recent 4 weeks and the 4 weeks before.
  • Branch. All branches unless the user names one (list_branches).

Steps

  1. Call get_business_performance for the whole window with increment_interval 7: one row per week with revenue and services sold.
  2. Call get_services once for each half and compare revenue and no_booked per service. A service listed in only one half is "new" or "no sales".
  3. Call get_clients for each half with retention_window_type "60_days". Use its summary: total_new_clients, total_returning_clients and rebooking_rate.
  4. Call get_bookings from today for the next 7 days. summary.by_date lists only days that have bookings: count every other day as zero.
  5. Call get_leads_overview for the recent 4 weeks. Open pipeline is in current_snapshot_summary; activity in the period is in period_summary. Skip leads only when both are empty.

Output

Lead with one sentence on the overall direction: revenue across the recent 4 weeks against the 4 before, with the percentage. Then short sections:

  • Weekly revenue and services sold: a table, one row per week.
  • Rising and falling services: up to 3 of each, with the change.
  • Clients: new and returning clients and rebooking rate, recent half against earlier half.
  • Next 7 days: bookings per day, including empty days, and the quietest day.
  • Pipeline: open leads and their value; win rate when the period has closed leads.
  • Worth a look: at most three points the data supports, such as a falling service or a quiet day ahead.

Rules

  • A trend needs two comparable periods with data. When a half is empty (a new business, a closed branch), say so instead of describing a trend.
  • Use client counts from get_clients, not from get_business_performance; the two count new clients differently.
  • Every number must come from a tool result in this conversation. Do not forecast beyond the bookings already in WAJ.
  • This skill only reads data. Suggest actions; do not take them.

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.