Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply the TPACK framework to evaluate and design technology-integrated instruction at the intersection of technological, pedagogical, and content knowledge. Use this skill when the user needs to assess teacher readiness for technology integration, design professional development for ed-tech, or evaluate whether technology use is pedagogically grounded — even if they say 'how to integrate technology in teaching', 'ed-tech evaluation', or 'teacher technology competency'.
.claude/skills/asgard-ai-platform-grad-tpack/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 33% | 0% |
TPACK (Technological Pedagogical Content Knowledge) describes the knowledge teachers need for effective technology integration. It identifies seven knowledge domains formed by the intersections of Technology (TK), Pedagogy (PK), and Content (CK) knowledge, arguing that effective integration requires understanding all three simultaneously.
Trigger conditions:
When NOT to use:
IRON LAW: Effective Technology Integration Requires ALL THREE Knowledge Types
Technology without pedagogy or content is just a tool, not instruction.
The seven domains:
TK — Technology Knowledge (how tools work)
PK — Pedagogical Knowledge (how to teach)
CK — Content Knowledge (what to teach)
TPK — How technology enables pedagogical strategies
TCK — How technology represents content
PCK — How to teach specific content (Shulman)
TPACK — The intersection of ALL three: the sweet spot
Weakness in ANY domain degrades technology integration quality.Assess the current state of each knowledge domain (TK, PK, CK) and their intersections for the instructor or instructional context.
Find where technology can genuinely enhance pedagogy for specific content. Ask: "What can students do WITH technology that they couldn't do WITHOUT it?"
Create learning activities where technology choice is driven by pedagogical purpose AND content requirements, not technology novelty.
Assess whether the technology integration achieved learning goals. Check: Did technology serve the pedagogy? Did it represent content accurately? Was it accessible?
markdown# TPACK Analysis: {Context/Course} ## Knowledge Domain Assessment | Domain | Current State | Evidence | Gap | |--------|-------------|----------|-----| | TK | ... | ... | ... | | PK | ... | ... | ... | | CK | ... | ... | ... | | TPK | ... | ... | ... | | TCK | ... | ... | ... | | PCK | ... | ... | ... | | TPACK | ... | ... | ... | ## Technology Integration Design - Content goal: {what students should learn} - Pedagogical strategy: {how they will learn it} - Technology role: {why this technology, specifically} - TPACK alignment: {how all three intersect} ## Recommendations {Targeted development for weakest domains}
references/tpack-instruments.mdreferences/lesson-design.md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 24,549 | 27,131 | +11% | 1 | 1 | 0% | 3,760 | 3,768 | +0% | 0 | 0 | — |
case-02 | fail→pass | 17,112 | 14,283 | -17% | 1 | 1 | 0% | 2,616 | 3,234 | +24% | 0 | 0 | — |
case-03 | fail→pass | 25,515 | 15,000 | -41% | 1 | 1 | 0% | 3,904 | 3,158 | -19% | 0 | 0 | — |
case-04 | pass→pass | 11,921 | 12,024 | +1% | 1 | 1 | 0% | 2,017 | 2,937 | +46% | 0 | 0 | — |
case-05 | pass→pass | 18,248 | 19,173 | +5% | 1 | 1 | 0% | 3,067 | 4,197 | +37% | 0 | 0 | — |
case-06 | pass→pass | 19,020 | 18,899 | -1% | 1 | 1 | 0% | 3,241 | 4,267 | +32% | 0 | 0 | — |
case-07 | pass→pass | 14,612 | 19,641 | +34% | 1 | 1 | 0% | 2,343 | 3,508 | +50% | 0 | 0 | — |
case-08 | fail→pass | 12,793 | 12,969 | +1% | 1 | 1 | 0% | 1,884 | 2,889 | +53% | 0 | 0 | — |
case-09 | pass→pass | 14,615 | 11,935 | -18% | 1 | 1 | 0% | 2,145 | 2,779 | +30% | 0 | 0 | — |
case-10 | fail→pass | 14,160 | 15,184 | +7% | 1 | 1 | 0% | 2,292 | 3,153 | +38% | 0 | 0 | — |
case-11 | fail→fail | 13,314 | 16,809 | +26% | 1 | 1 | 0% | 1,941 | 3,400 | +75% | 0 | 0 | — |
case-12 | pass→pass | 12,935 | 11,108 | -14% | 1 | 1 | 0% | 1,992 | 2,426 | +22% | 0 | 0 | — |
case-13 | fail→pass | 9,457 | 6,451 | -32% | 1 | 1 | 0% | 1,424 | 1,890 | +33% | 0 | 0 | — |
case-14 | fail→pass | 24,540 | 14,885 | -39% | 1 | 1 | 0% | 3,423 | 3,150 | -8% | 0 | 0 | — |
case-15 | fail→pass | 14,648 | 13,857 | -5% | 1 | 1 | 0% | 2,218 | 2,610 | +18% | 0 | 0 | — |
case-16 | fail→pass | 17,783 | 8,783 | -51% | 1 | 1 | 0% | 2,679 | 2,119 | -21% | 0 | 0 | — |
case-17 | pass→pass | 9,510 | 6,614 | -30% | 1 | 1 | 0% | 1,303 | 1,823 | +40% | 0 | 0 | — |
case-18 | pass→pass | 9,604 | 7,051 | -27% | 1 | 1 | 0% | 1,403 | 2,030 | +45% | 0 | 0 | — |
case-19 | pass→pass | 4,184 | 4,513 | +8% | 1 | 1 | 0% | 557 | 1,470 | +164% | 0 | 0 | — |
case-20 | fail→pass | 20,014 | 21,116 | +6% | 1 | 1 | 0% | 2,619 | 3,694 | +41% | 0 | 0 | — |
case-21 | pass→pass | 15,803 | 15,779 | -0% | 1 | 1 | 0% | 2,450 | 3,039 | +24% | 0 | 0 | — |
case-22 | pass→pass | 18,628 | 12,415 | -33% | 1 | 1 | 0% | 2,237 | 2,725 | +22% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +41 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.