Free OpenClaw Skill for Test Prep and Tutoring Centers: Diagnostic and Score Coordinator Agent (Download)

What this skill does for your test prep and tutoring centers

• Drafts the free-diagnostic conversion cadence (24h, 7d, 14d) with the diagnostic score, the target score, and the realistic timeline pre-filled.
• Tracks each student's exam date, target score, mock exam scores week by week, surfaces students who are off-pace early.
• Runs the parent score update on a weekly or bi-weekly cadence with honest framing (no hype, no false reassurance) keyed to TutorBird or TutorCruncher data.
• Handles the Kaplan or Princeton Review price-comparison objection with the independent center's positioning: the same outcomes at 40-60% of the franchise price.
• Manages the tutor-student matching when a new student enrolls, with subject and personality fit notes from the diagnostic.

What's inside this OpenClaw skill

The full file you download, indexed below for search engines and for operators who want to read before they install.

---
name: test-prep-diagnostic-coordinator
description: Free diagnostic conversion funnel, SAT / ACT / ISEE / SSAT / GRE / GMAT / LSAT / MCAT / AP prep tracking, at-risk score detection, and Kaplan / Princeton Review competitive positioning for independent test prep and tutoring centers. Integrates with TutorBird, TutorCruncher, Oases.
version: 1.0.0
author: OpenClaw Consult (Adhiraj Hangal)
license: MIT
url: https://openclawconsult.com/skills/test-prep-tutoring-centers
---

# OpenClaw Skill: Test Prep Center Diagnostic and Score Coordinator

## Overview

This skill turns the OpenClaw agent into the Center Director's force multiplier
for an independent test prep and tutoring center. It owns the free-diagnostic
conversion funnel, multi-exam prep tracking, weekly score progression updates,
and the competitive positioning against Kaplan and Princeton Review.

Designed for independent centers running 20 to 300 students. Works with
TutorBird, TutorCruncher, Oases, and CSV-based legacy setups. Solo tutors
and multi-tutor centers both supported.

## What this skill does

1. Free diagnostic conversion cadence (24h, 7d, 14d) with realistic timeline
2. Multi-exam prep tracking: SAT, ACT, PSAT, ISEE, SSAT, GRE, GMAT, LSAT, MCAT, all APs
3. Weekly score progression updates with honest framing
4. At-risk score detection: students off-pace by week 4
5. Kaplan / Princeton Review competitive memo for shopping families
6. Tutor-student matching with subject and personality fit notes

## Triggers

```yaml
triggers:
  - type: heartbeat
    schedule: "0 9 * * 1"           # Mondays 9am
    action: weekly_score_progression_review

  - type: heartbeat
    schedule: "0 17 * * 0"          # Sundays 5pm
    action: weekly_parent_score_updates

  - type: heartbeat
    schedule: "0 7 * * 5"           # Fridays 7am
    action: diagnostic_conversion_funnel_review

  - type: on_event
    event: center.diagnostic_completed
    action: enter_diagnostic_conversion_cadence

  - type: on_event
    event: center.mock_exam_scored
    action: update_score_progression_memory

  - type: on_event
    event: center.exam_date_30d_out
    action: kickoff_test_day_logistics
```

## Workflow: free diagnostic conversion

When a prospect completes the free diagnostic, the agent:

1. Reads the scored diagnostic result by section
2. Pulls the student's college list, program goal, or score target from the intake form
3. Calculates the realistic improvement timeline: SAT 100-150 point improvements typically require 40-60 hours of structured prep over 8-12 weeks; ACT 3-4 composite point improvements similar; ISEE/SSAT improvements depend on entering grade
4. Drafts message 1 at 24 hours: scored diagnostic, target score, realistic timeline, recommended package
5. Drafts message 2 at day 7: package recommendation with tutor match
6. Drafts message 3 at day 14: competitive price memo (Kaplan and Princeton Review tiers) and honest comparison if the family is shopping

Conversion benchmark for independent centers running this cadence: 50-65% diagnostic-to-package conversion (vs. industry 35-45% baseline).

## Workflow: exam prep tracking

The skill maintains per-student memory of:

- Target exam and exam date
- Diagnostic baseline score
- Target score
- Tutoring hours used vs. recommended
- Weekly mock exam scores
- Section-by-section strength and weakness

For each exam:

```yaml
exam_tracks:
  digital_sat:
    sections: [reading_writing, math]
    scoring: 400-1600
    typical_improvement_8_weeks: 80-150_points
    test_dates_per_year: 7
  act:
    sections: [english, math, reading, science, writing_optional]
    scoring: 1-36_composite
    typical_improvement_8_weeks: 2-4_points
  isee:
    levels: [lower, middle, upper]
    scoring: percentile_and_stanine
  ssat:
    levels: [elementary, middle, upper]
    scoring: percentile_and_scaled
  gre:
    sections: [verbal, quantitative, analytical_writing]
    scoring: 130-170_per_section
  gmat:
    sections: [data_insights, verbal, quantitative]
    scoring: 205-805
  lsat:
    sections: [logical_reasoning, reading_comp, logic_games_phasing_out]
    scoring: 120-180
  mcat:
    sections: [chem_phys, cars, bio_biochem, psych_soc]
    scoring: 472-528
  ap:
    scoring: 1-5
    rolling_exam_schedule_may
```

## Workflow: weekly score progression

Every Sunday at 5pm the agent compiles per-family score progression updates:

- Last week's mock score by section
- Trend versus baseline (improving, plateau, regression)
- Hours of tutoring used this week
- Suggested focus for the coming week
- Honest framing: no false reassurance, no hype

The Center Director approves before send.

## Workflow: at-risk score detection

Every Monday at 9am the agent reviews the active roster:

- Students more than 10 percentile points off-pace at the four-week mark are flagged
- The flag includes a recommended action: extend timeline, swap tutors, drop a subject section, reduce target score realistically, or shift to a later test date
- The Center Director reviews and chooses

This workflow alone typically saves centers from the worst outcome: a student paying for the full package, scoring well below target on test day, and souring on the center's referral pipeline.

## Workflow: Kaplan / Princeton Review competitive positioning

For prospects shopping Kaplan or Princeton Review, the skill drafts an honest memo:

- The named Kaplan or Princeton Review tier the family is comparing (Kaplan Premier, Self-Paced, Live Online; Princeton Review Ultimate, Self-Paced, In-Person)
- The center's package: typically 1:1 tutoring, smaller hours-per-week, individualized to the diagnostic
- The price comparison: independent centers typically come in at 40-60% of franchise tier pricing for comparable hours
- The outcome positioning: 1:1 tutoring with a matched tutor typically delivers stronger improvement than a 20:1 class for the same student, particularly for students with section-specific weakness

The skill never makes a guaranteed-score claim. It frames trade-offs honestly.

## Workflow: tutor-student matching

When a new student enrolls, the skill:

1. Reads the diagnostic by section
2. Reads the student's age, school, and intake notes (introvert vs. extrovert, prefers structure vs. flexibility, etc.)
3. Recommends 2-3 tutors from the roster based on subject expertise and personality fit
4. Routes to the Center Director for final match

## Message templates

```yaml
templates:
  diagnostic_followup_24h:
    body: |
      Hi {parent_first_name},

      Thanks for bringing {student_first_name} in for the diagnostic. Here is
      what we found:

      Diagnostic score: {diagnostic_score}
      Target score: {target_score}
      Gap: {score_gap}

      Honest read on timeline: to hit {target_score} from {diagnostic_score}
      typically takes {realistic_hours} hours of structured 1:1 prep over
      {realistic_weeks} weeks. {student_first_name}'s test date on
      {exam_date} gives us {weeks_available} weeks, which is
      {timeline_assessment}.

      Recommended package: {recommended_package}
      Recommended tutor match: {recommended_tutor_with_rationale}

      Want to walk through it on the phone tomorrow?

      {director_first_name}

  weekly_score_update:
    subject: "{student_first_name}'s week {week_number} score update"
    body: |
      Hi {parent_first_name},

      Quick update on {student_first_name}'s prep this week:

      - Mock {section_name}: {section_score} ({trend})
      - Mock {section_name}: {section_score} ({trend})
      - Hours used this week: {hours_used} of {hours_recommended}

      Honest read: {honest_assessment_no_hype}

      Focus for next week: {focus_for_next_week}

      {tutor_first_name}

  at_risk_director_alert:
    channel: slack
    body: |
      AT RISK SCORE
      Student: {student_first_name} {student_last_name}
      Target exam: {exam_name} on {exam_date}
      Target score: {target_score}
      Current pace: {current_pace_score} ({percentile_off_pace} points off-pace)
      Recommended action: {recommended_action}

  kaplan_competitive_memo:
    body: |
      Hi {parent_first_name},

      You mentioned comparing with Kaplan. Here is an honest read:

      Kaplan {kaplan_tier}: {kaplan_pricing}, {kaplan_format} ({kaplan_hours_or_format_note})

      Our package: {our_package_name}, {our_pricing}, 1:1 tutoring with
      {recommended_tutor_first_name} who specializes in {tutor_specialty}.

      The 1:1 format typically delivers stronger improvement for students who
      need targeted work on specific sections (which is most students). The
      class format works for students who self-direct well and are within
      10-15% of target.

      No pressure either way. Happy to walk through it.

      {director_first_name}
```

## Memory keys

```yaml
memory:
  - key: center.student_profile[{student_id}]
    description: Student exam, target, baseline, enrollment status
    schema: { exam: string, exam_date: date, target_score: number, baseline_score: number, college_list: [string] }

  - key: center.score_progression[{student_id}]
    description: Weekly mock scores per section
    schema: { mocks: [{week, section, score, percentile}] }

  - key: center.at_risk_state[{student_id}]
    description: At-risk detection flag and recommended action
    schema: { off_pace_pct: number, weeks_remaining: int, recommended_action: string }

  - key: center.diagnostic_pipeline[{prospect_id}]
    description: Diagnostic conversion funnel stage
    values: [diagnostic_taken, day_1_sent, day_7_sent, day_14_sent, converted, lost, reactivation]

  - key: center.tutor_match[{student_id}]
    description: Active tutor assignment with rationale
```

## Required integrations

| Integration              | Purpose                                       | Read | Write    |
|--------------------------|-----------------------------------------------|------|----------|
| TutorBird                | Student roster, scheduling, billing           | yes  | optional |
| TutorCruncher            | Roster, scheduling, billing, tutor data       | yes  | optional |
| Oases                    | Roster and scheduling                         | yes  | optional |
| Diagnostic scoring tool  | Sectional scored diagnostic input             | yes  | no       |
| Twilio (or similar)      | SMS                                           | no   | yes      |
| Email provider           | Outbound email                                | no   | yes      |
| Slack                    | Director alerts for at-risk students          | no   | yes      |
| OpenClaw Memory          | Cross-run state                               | yes  | yes      |
| OpenClaw Heartbeat       | Scheduled cadences                            | yes  | yes      |

Write-back to your roster system starts disabled. Most centers prefer the
Director to commit package changes manually.

## Compliance notes

For students under 18, parent or guardian consent governs outbound. The skill
defaults to parent-primary communication for K-12 students and student-primary
for college-and-up exams (GRE, GMAT, LSAT, MCAT).

For FERPA: while test prep centers are not subject to FERPA the same way
schools are, the skill respects the same boundary: scored diagnostic detail
stays inside the center's secure communication, not broadcast.

For test administrator policies: the skill does not script exam-day cheating,
exam content sharing, or proctor-bypass tactics. The competitive positioning
is honest comparison of legitimate prep packages.

## Configuration

```yaml
config:
  center_name: "Your Center Name"
  director_first_name: "Alex"
  approval_mode: director_approves_all   # or "autonomous_after_2_weeks"
  exams_supported:
    - digital_sat
    - act
    - isee
    - ssat
    - gre
    - gmat
    - lsat
    - mcat
    - ap
  diagnostic_format: in_house_3h         # or "ondemand_scored", "third_party"
  competitive_positioning:
    - kaplan
    - princeton_review
  package_tiers:
    - basic_20h
    - standard_40h
    - intensive_60h_plus
  at_risk_threshold_off_pace_pct: 10
  cadences:
    diagnostic_followup: [24h, 7d, 14d, 30d_reactivation]
    weekly_score_update: sunday_5pm
    score_progression_review: monday_9am
```

## Quick install

```bash
mkdir -p ~/.claude/skills
mv test-prep-tutoring-centers.md ~/.claude/skills/test-prep-diagnostic-coordinator.md
# Edit the config block to match your center
```

Launch OpenClaw and the skill is live. Run `review diagnostic conversion funnel`
or `compile at-risk score report` to invoke it on demand, or wait for Heartbeat.

## Want it wired to your stack?

This SKILL.md is the starting point. If you want it plugged into your specific
roster system, your diagnostic format, your exam coverage, and your center's
voice on a fixed-price two-week clock, the door is at
https://www.adhirajhangal.com/work

Install in 60 seconds

1. 1

   Drop the file into your OpenClaw skills directory

   Save the downloaded test-prep-tutoring-centers.md as ~/.claude/skills/test-prep-diagnostic-coordinator.md. OpenClaw picks up new skill files on next agent launch.

2. 2

   Connect TutorBird, TutorCruncher, or your roster

   Edit the integrations block to point at TutorBird, TutorCruncher, Oases, or your CSV export. Read-only is enough to start. The skill ships prompts that translate your weekly tutoring schedule and student diagnostic data into the agent's working memory.

3. 3

   Launch in approval mode, validate, then flip to autonomous

   Start with the Center Director approving every parent-facing message for two weeks. The skill defaults route anything that touches a real score conversation, a tutor swap, or a billing dispute to a human. After validation, flip the standard diagnostic follow-up and weekly score update templates to autonomous.

Example conversation

Common questions

Related free skills