Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply the Knowledge-Based View (Grant, 1996) and Nonaka and Takeuchi's SECI model to analyze how organizations create, transfer, and integrate knowledge for competitive advantage. Use this skill when the user needs to design knowledge management systems, understand why knowledge transfer fails across teams, evaluate knowledge creation processes, or when they ask 'how do we capture tacit knowledge', 'why does knowledge stay siloed', or 'how can we turn individual expertise into organizational cap
.claude/skills/asgard-ai-platform-grad-strat-kbv/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✓→✗ | ▼ Worse | 72% | 0% |
| case-01 | ✓→✓ | = Same ✓ | 4% | 0% |
| case-02 | ✓→✓ | = Same ✓ | -13% | 0% |
| case-03 | ✓→✓ | = Same ✓ | -30% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 25% | 0% |
The Knowledge-Based View (Grant, 1996) positions knowledge as the most strategically significant resource of the firm. The firm exists because it integrates specialized knowledge more efficiently than markets. Nonaka and Takeuchi (1995) complement this with the SECI model explaining how knowledge is created through conversion between tacit and explicit forms.
IRON LAW: Tacit knowledge cannot be directly transferred — it must
be CONVERTED. Any knowledge management strategy that assumes tacit
knowledge can be simply documented and distributed will fail.
Conversion requires interaction, practice, and socialization.Key assumptions:
| Type | Characteristics | Transfer Mechanism | Strategic Value | |------|----------------|-------------------|-----------------| | Tacit | Personal, context-specific, hard to articulate | Apprenticeship, mentoring, practice | High (hard to imitate) | | Explicit | Codified, systematic, easily communicated | Documents, databases, manuals | Lower (easy to copy) |
| Mode | From → To | Process | Example | |------|-----------|---------|---------| | Socialization | Tacit → Tacit | Shared experience, observation | Apprenticeship, job shadowing | | Externalization | Tacit → Explicit | Articulation through dialogue, metaphor | Writing best practices from expert intuition | | Combination | Explicit → Explicit | Systemizing and integrating codified knowledge | Database merging, report synthesis | | Internalization | Explicit → Tacit | Learning by doing from codified sources | Practicing from a manual until it becomes intuitive |
markdown## Knowledge Analysis: [Context] ### Knowledge Asset Map | Knowledge Domain | Type (Tacit/Explicit) | Owner | Strategic Value | Transfer Risk | |-----------------|----------------------|-------|-----------------|---------------| | [domain] | [type] | [who] | [H/M/L] | [H/M/L] | ### SECI Assessment | Mode | Current State | Bottleneck | Intervention | |------|--------------|-----------|--------------| | Socialization | [active/weak/absent] | ... | ... | | Externalization | ... | ... | ... | | Combination | ... | ... | ... | | Internalization | ... | ... | ... | ### Recommendations 1. [per SECI mode or integration mechanism]
A consulting firm losing knowledge when senior partners retire: strong combination (explicit knowledge databases) but weak socialization (junior staff lack mentoring time with partners). Recommendation: structured apprenticeship program to enable tacit-to-tacit transfer before externalization attempts.
Proposing a "knowledge management database" as the sole solution for capturing expert knowledge. This addresses only the combination mode and ignores the Iron Law — tacit knowledge must first be converted through socialization or externalization before it can be stored.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 24,184 | 42,301 | +75% | 1 | 1 | 0% | 3,538 | 3,676 | +4% | 0 | 0 | — |
case-02 | pass→pass | 25,803 | 16,504 | -36% | 1 | 1 | 0% | 4,195 | 3,664 | -13% | 0 | 0 | — |
case-03 | pass→pass | 31,090 | 16,207 | -48% | 1 | 1 | 0% | 5,217 | 3,644 | -30% | 0 | 0 | — |
case-04 | pass→pass | 18,292 | 15,279 | -16% | 1 | 1 | 0% | 2,767 | 3,457 | +25% | 0 | 0 | — |
case-05 | pass→pass | 15,465 | 12,896 | -17% | 1 | 1 | 0% | 2,253 | 3,120 | +38% | 0 | 0 | — |
case-06 | pass→pass | 4,697 | 5,991 | +28% | 1 | 1 | 0% | 748 | 2,020 | +170% | 0 | 0 | — |
case-07 | pass→pass | 4,256 | 3,877 | -9% | 1 | 1 | 0% | 658 | 1,770 | +169% | 0 | 0 | — |
case-08 | pass→pass | 7,030 | 4,575 | -35% | 1 | 1 | 0% | 1,052 | 1,837 | +75% | 0 | 0 | — |
case-09 | pass→pass | 4,096 | 3,916 | -4% | 1 | 1 | 0% | 657 | 1,776 | +170% | 0 | 0 | — |
case-10 | pass→pass | 7,219 | 5,690 | -21% | 1 | 1 | 0% | 971 | 2,002 | +106% | 0 | 0 | — |
case-11 | pass→pass | 16,673 | 15,654 | -6% | 1 | 1 | 0% | 2,559 | 3,442 | +35% | 0 | 0 | — |
case-12 | pass→pass | 16,633 | 13,677 | -18% | 1 | 1 | 0% | 2,581 | 3,034 | +18% | 0 | 0 | — |
case-13 | pass→pass | 18,217 | 19,942 | +9% | 1 | 1 | 0% | 2,740 | 4,255 | +55% | 0 | 0 | — |
case-14 | pass→pass | 10,034 | 13,397 | +34% | 1 | 1 | 0% | 1,507 | 3,314 | +120% | 0 | 0 | — |
case-15 | pass→pass | 16,940 | 16,551 | -2% | 1 | 1 | 0% | 2,296 | 3,757 | +64% | 0 | 0 | — |
case-16 | pass→pass | 14,414 | 3,210 | -78% | 1 | 1 | 0% | 701 | 1,534 | +119% | 0 | 0 | — |
case-17 | pass→pass | 18,704 | 17,652 | -6% | 1 | 1 | 0% | 2,718 | 3,700 | +36% | 0 | 0 | — |
case-18 | pass→pass | 28,170 | 26,243 | -7% | 1 | 1 | 0% | 3,673 | 4,732 | +29% | 0 | 0 | — |
case-19 | pass→pass | 17,989 | 23,499 | +31% | 1 | 1 | 0% | 2,676 | 4,290 | +60% | 0 | 0 | — |
case-20 | pass→fail | 19,941 | 29,313 | +47% | 1 | 1 | 0% | 3,133 | 5,381 | +72% | 0 | 0 | — |
case-21 | pass→pass | 16,416 | 15,108 | -8% | 1 | 1 | 0% | 2,594 | 3,494 | +35% | 0 | 0 | — |
case-22 | pass→pass | 12,749 | 11,999 | -6% | 1 | 1 | 0% | 1,973 | 2,756 | +40% | 0 | 0 | — |
case-23 | pass→pass | 8,944 | 5,192 | -42% | 1 | 1 | 0% | 1,154 | 1,942 | +68% | 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. 23 cases were attempted. The headline lift of -100 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Other measured skills in the registry, with their headline benchmark lift.