agentleFS
waj-1waj-1/waj-plugin/skills/client-retention/SKILL.md

client-retention

Skill0 starsChanged 10 days agoMITView on GitHub

Analyze client retention in a WAJ salon or spa - new versus returning clients, how monthly groups of new clients hold up, first-visit drop-off and repeat rates per staff member, top clients and clients at risk - and, only when the user asks, set up a win-back audience or workflow. Use when the user asks about returning clients, churn, loyalty, lapsed or lost clients, or how to bring clients back.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are 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.

  • 3

    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 18
  2. Very specific:

    Call get_clients for the recent period with the retention window.

    line 22
  3. Very specific:

    Call get_retention_analytics for the 12 months.

    line 27
  4. Distinctive:

    Only if the user asks to act on the result:

    line 36
  5. Distinctive:

    Do not show client phone numbers or emails unless the user asks for them.

    line 59
  6. Distinctive:

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

    line 60
  7. Distinctive:

    Never send messages to clients from this skill.

    line 66

≈ “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 retention

Explain who comes back and who does not, from WAJ's own figures. The user's explicit instructions override every default below.

Inputs

  • Recent period. The last 90 days ending today unless the user gives one.
  • History. The last 12 months for cohorts and per-staff retention; shorter periods hold too few returning clients for those.
  • Retention window. 60 days unless the user says otherwise ("30_days", "60_days" or "90_days" in get_clients).
  • Branch. All branches unless the user names one (list_branches).

Steps

  1. Call get_clients for the recent period with the retention window. Use its summary (total_new_clients, total_returning_clients, total_retained_clients, rebooking_rate) and its clients list (is_new_client, is_retained, total_revenue, total_completed_bookings).
  2. Call get_retention_analytics for the 12 months. It counts a client as lost after churn_window_days without a visit: the business's setting (60 days unless changed), or churn_window_days when the user names a window.
    • cohort_analysis: per month, cohort_size new clients, how many are still_active and still_active_pct.
    • staff_retention: per staff member, first_time_customers, same_staff_repeat_pct, shop_repeat_pct and kill_rate_pct.
    • revenue_split: first-time versus repeat revenue per month.
  3. Only if the user asks to act on the result:
    • create_audience to save lapsed clients as an audience, with filters the user agrees to (for example visited_to set to 60 days ago).
    • create_workflow for a win-back sequence using the user's audience, message templates and timing. It is saved switched off unless the user explicitly asks to switch it on.

Output

  • Retention in one sentence: returning clients and rebooking rate for the recent period.
  • Cohorts: a table per month with new clients, still active, and the share still active (still_active_pct).
  • Per staff member: repeat rate (same_staff_repeat_pct) and kill rate (kill_rate_pct, lost after the first visit among clients old enough to tell). Skip anyone with fewer than 5 first-time clients and say why.
  • Top 10 clients by revenue (name, visits, revenue), only when asked. Leave out the row without a client name; it collects walk-in sales.
  • Up to three suggestions the numbers support, such as a follow-up after the first visit where drop-off is high.

Rules

  • Do not show client phone numbers or emails unless the user asks for them.
  • Every number must come from a tool result in this conversation; compute shares only from the fields named above.
  • Creating an audience or a workflow changes the business's account: do it only when the user asks. Customer-facing changes wait for the owner's approval in the WAJ app; tell the user when a tool returns "awaiting_approval".
  • Never send messages to clients from this skill.

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.