Case study

Skill EQ Dashboard

Purpose: turn learning activity into useful next steps. The implemented system read xAPI statements from an LRS, mapped that activity to the relevant skills and competencies, and used the resulting skill matrix to recommend what to do next.

Implemented system / xAPI activity, skill mapping, and next-step recommendations
A.J. Merlino / learning analytics system

Skill EQ Dashboard

Alex Rivera · Term 8 of 10 · Sample learning profile
74
Skill EQ
Learning Progress
74%
28 / 38 modules
Evidence Points
127
across all skills
Skills Tracked
48
7 domains
Avg Confidence
74%
weighted composite
Skill Domain Profile
Design Core Research Communication Collaboration Problem Solving Prof. Growth
Skill EQ Growth
100 75 50 25 T1 T2 T3 T4 T5 T6 T7 T8
Domain Scores
Evidence Distribution
Proficiency Weighting

Assessment feedback carries full weight (100%). Work products evaluated against clear rubrics carry 85%. External credentials carry 75%. Self-attested skills carry 45%.

Proficiency Levels
Evidence Weights
Select a Skill
Select a skill from the left panel
View the full evidence trail, rationale, rubric references, and weighted calculation for any tracked skill.
Skill Balance Analysis
Weakest Domain
📈 Professional Growth
69
Strongest Domain
🎨 Design Core
78
Domain spread (imbalance) 9 pts
Priority Distribution
Quick Wins — Fastest Path to a Balanced EQ

These high-impact, lower-effort actions would give you the most significant Skill EQ improvement in the shortest time.

Personalized Recommendations
Course Timeline (Standard Path)
Completion Summary
Completed
28
In Progress
2
Remaining
8
Exemplary
8
Areas of Study
Projected Growth

Based on current trajectory, your Skill EQ is projected to reach 82-88 at the end of the learning path.

Current
74
Projected
85
How Skill EQ Worked

The system read xAPI statements stored in a learning record store (LRS) to capture learning activity and evidence as it occurred.

It mapped each statement to the relevant skills and competencies, then assembled those mappings into an individual skill matrix.

The dashboard made that matrix visible so learners and staff could see current coverage, gaps, and the next opportunities to build capability.

From Activity to Next Step
// Activity is recorded
xAPI statement → LRS
// Activity is interpreted
statement → skill + competency mapping
// Learner state is assembled
mapped activity → skill matrix
// The next action is selected
skill gaps + learner context → recommendation
Evidence Sources
Just-in-Time Recommendations

The recommendation engine checked the learner's skill matrix for gaps and next eligible actions.

It surfaced a relevant next step at the point of need, giving learners a practical route to build the skills and competencies their activity had not yet covered.

For Instructors

Instructor view includes ability to submit assessment evidence, flag skills for review, adjust inferred proficiency levels, and view aggregate cohort analytics.