agentleFS
waj-1waj-1/waj-plugin/skills/staff-performance/SKILL.md

staff-performance

Skill0 starsChanged 10 days agoMITView on GitHub

Review a WAJ salon or spa team's performance - revenue, bookings, completed services, booked versus scheduled hours, unique clients and client retention per staff member, ranked and compared with the previous period. Use when the user asks who performed best, how a staff member is doing, which staff are under-booked, or wants a team performance review.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Period: Use the dates the user gives.

    line 13
  2. Very specific:

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

    line 18
  3. Very specific:

    Call get_staff_performance for the period and for the comparison period.

    line 22
  4. Very specific:

    When the user asks about a named person's hours, call get_staff_schedule for them and add up the weekly hours from week (a day reads like …

    line 30
  5. Very specific:

    Call get_staff_payroll only when the user asks about pay or commission.

    line 33
  6. Distinctive:

    Leave out staff with no revenue and no bookings in both periods.

    line 46
  7. Distinctive:

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

    line 60

≈ “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

Staff performance

Compare staff on WAJ's own figures. The user's explicit instructions (period, branch, staff members, metrics) override every default below.

Inputs

  • Period. Use the dates the user gives; without one, the last 30 days ending today, and say so. Compare with the period of the same length just before it.
  • Staff. Everyone unless the user names people. Resolve names with list_staff; if a name matches more than one person, ask which one.
  • Branch. All branches unless the user names one (list_branches).

Steps

  1. Call get_staff_performance for the period and for the comparison period. Each row has revenue_generated, no_bookings_booked, no_bookings_checkedout (completed), services_count, no_hours_booked, no_hours_worked (scheduled hours) and unique_clients_count.
  2. For client retention, call get_retention_analytics for the last 12 months (shorter periods hold too few returning clients). Use staff_retention: first_time_customers, same_staff_repeat_pct and kill_rate_pct per staff member.
  3. When the user asks about a named person's hours, call get_staff_schedule for them and add up the weekly hours from week (a day reads like "09:00–18:00" or "Day off").
  4. Call get_staff_payroll only when the user asks about pay or commission. Salary-plan pay is in staff_payroll; commission is in commission.by_staff (commission, paid, pending, per earning period) and, for the current month so far, commission.in_progress (commission_so_far). If it is refused for the user's role or returns nothing, say so.

Output

  • A table with one row per staff member: revenue, bookings, completed, booked hours, scheduled hours, utilisation (booked ÷ scheduled hours), revenue per booked hour, unique clients, and the change in revenue against the comparison period. Sort by revenue unless the user asks otherwise. Leave out staff with no revenue and no bookings in both periods.
  • The top performer and the biggest drop, each with the figures behind it.
  • Retention per staff member over the 12 months: repeat rate (same_staff_repeat_pct) and kill rate (kill_rate_pct, clients lost after the first visit, leaving out those too recent to tell). Skip anyone with fewer than 5 first-time clients and say why.
  • Commission per staff member, only when the user asked about pay or commission: earned and still pending for the period, and this month so far when the period includes today.
  • Staff with low utilisation, as candidates for promotion or schedule changes, only when the numbers show it.

Rules

  • Every number must come from a tool result in this conversation; compute ratios only from the fields named above, and do not invent reasons for a change.
  • Present performance factually. Do not label anyone a poor performer or recommend discipline; leave judgements about people to the user.
  • Staff names and pay are internal business data: show them only in answer to the user's question.
  • This skill only reads data. It never changes schedules, pay plans or staff.

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.