Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply Porter's Value Chain Analysis to identify competitive advantage sources within an organization's activities. Use this skill when the user needs to find where value is created or lost in their operations, analyze cost structure by activity, optimize internal processes, or identify outsourcing candidates — even if they say 'where do we make money' or 'which activities should we keep in-house'.
.claude/skills/asgard-ai-platform-biz-value-chain/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 18% | 0% |
Value Chain Analysis decomposes an organization into strategically relevant activities to understand where competitive advantage originates. Each activity either adds value (customer willingness to pay) or adds cost. The gap between total value created and total cost is the margin.
Trigger conditions:
When NOT to use:
IRON LAW: Primary + Support Activities Are a Complete Set
Analyze ALL nine categories. Skipping support activities (like HR or
technology development) misses critical advantage sources. Amazon's
competitive advantage comes more from Technology Development (support)
than from any single primary activity.Primary activities directly create and deliver value to the customer:
Support activities enable and improve primary activities:
For each of the 9 activities, evaluate:
Competitive advantage comes from:
For each activity:
markdown# Value Chain Analysis: {Company} ## Primary Activities | Activity | Key Processes | Value Contribution | Cost % | vs Competitors | |----------|-------------|-------------------|--------|----------------| | Inbound Logistics | {processes} | High/Med/Low | X% | Better/Same/Worse | | Operations | ... | ... | ... | ... | | Outbound Logistics | ... | ... | ... | ... | | Marketing & Sales | ... | ... | ... | ... | | Service | ... | ... | ... | ... | ## Support Activities | Activity | Key Processes | Value Contribution | Cost % | vs Competitors | |----------|-------------|-------------------|--------|----------------| | Infrastructure | {processes} | High/Med/Low | X% | Better/Same/Worse | | HR Management | ... | ... | ... | ... | | Technology Dev | ... | ... | ... | ... | | Procurement | ... | ... | ... | ... | ## Advantage Sources - **Cost advantage in**: {activities} - **Differentiation advantage in**: {activities} - **Key linkages**: {activity A ↔ activity B} ## Recommendations 1. **Strengthen**: {activity} — {why and how} 2. **Optimize**: {activity} — {specific improvement} 3. **Outsource**: {activity} — {rationale}
Scenario: Value Chain for a Taiwanese direct-to-consumer (DTC) skincare brand
| Activity | Advantage? | Analysis | |----------|-----------|----------| | Inbound Logistics | Same | Standard ingredient sourcing from OEM suppliers | | Operations | Differentiation ✓ | Proprietary formulation process co-developed with dermatologists | | Outbound Logistics | Same | Standard logistics via 黑貓/宅配通 | | Marketing & Sales | Differentiation ✓ | Strong KOL relationships and community-driven content on social media | | Service | Same | Standard customer service | | Technology Dev | Differentiation ✓ | Data-driven product development using customer feedback loops | | Procurement | Cost advantage ✓ | Long-term contracts with local ingredient suppliers at volume discounts |
Key linkage: Technology Development ↔ Marketing & Sales — customer data from social media directly feeds product R&D.
What went wrong:
references/framework-comparison.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 | 35,858 | 34,107 | -5% | 1 | 1 | 0% | 5,821 | 4,739 | -19% | 0 | 0 | — |
case-02 | fail→fail | 47,630 | 22,447 | -53% | 1 | 1 | 0% | 8,297 | 5,287 | -36% | 0 | 0 | — |
case-03 | fail→fail | 50,184 | 30,115 | -40% | 1 | 1 | 0% | 8,300 | 5,825 | -30% | 0 | 0 | — |
case-04 | pass→pass | 20,595 | 23,235 | +13% | 1 | 1 | 0% | 3,316 | 4,465 | +35% | 0 | 0 | — |
case-05 | pass→pass | 16,218 | 18,104 | +12% | 1 | 1 | 0% | 2,735 | 4,556 | +67% | 0 | 0 | — |
case-06 | pass→pass | 22,788 | 20,312 | -11% | 1 | 1 | 0% | 3,611 | 4,947 | +37% | 0 | 0 | — |
case-07 | pass→pass | 29,335 | 20,057 | -32% | 1 | 1 | 0% | 4,016 | 4,391 | +9% | 0 | 0 | — |
case-08 | pass→pass | 20,633 | 16,825 | -18% | 1 | 1 | 0% | 3,192 | 4,297 | +35% | 0 | 0 | — |
case-09 | pass→pass | 21,349 | 15,146 | -29% | 1 | 1 | 0% | 3,183 | 3,994 | +25% | 0 | 0 | — |
case-10 | fail→fail | 22,893 | 16,464 | -28% | 1 | 1 | 0% | 3,504 | 4,237 | +21% | 0 | 0 | — |
case-11 | fail→pass | 22,786 | 20,647 | -9% | 1 | 1 | 0% | 3,293 | 4,709 | +43% | 0 | 0 | — |
case-12 | fail→pass | 44,462 | 13,155 | -70% | 1 | 1 | 0% | 5,820 | 3,657 | -37% | 0 | 0 | — |
case-13 | fail→fail | 23,045 | 15,727 | -32% | 1 | 1 | 0% | 3,535 | 4,127 | +17% | 0 | 0 | — |
case-14 | fail→pass | 18,827 | 18,324 | -3% | 1 | 1 | 0% | 2,976 | 4,480 | +51% | 0 | 0 | — |
case-15 | fail→pass | 26,005 | 17,965 | -31% | 1 | 1 | 0% | 4,025 | 4,302 | +7% | 0 | 0 | — |
case-16 | fail→pass | 17,046 | 10,023 | -41% | 1 | 1 | 0% | 2,638 | 3,119 | +18% | 0 | 0 | — |
case-17 | fail→pass | 12,089 | 12,202 | +1% | 1 | 1 | 0% | 2,068 | 3,462 | +67% | 0 | 0 | — |
case-18 | pass→pass | 14,634 | 14,419 | -1% | 1 | 1 | 0% | 2,471 | 3,830 | +55% | 0 | 0 | — |
case-19 | pass→pass | 15,024 | 15,452 | +3% | 1 | 1 | 0% | 2,392 | 3,781 | +58% | 0 | 0 | — |
case-20 | pass→pass | 20,001 | 15,037 | -25% | 1 | 1 | 0% | 3,167 | 3,917 | +24% | 0 | 0 | — |
case-21 | fail→pass | 18,929 | 13,417 | -29% | 1 | 1 | 0% | 3,055 | 3,707 | +21% | 0 | 0 | — |
case-22 | pass→pass | 19,128 | 17,635 | -8% | 1 | 1 | 0% | 2,875 | 4,346 | +51% | 0 | 0 | — |
case-23 | pass→pass | 21,424 | 14,589 | -32% | 1 | 1 | 0% | 3,551 | 3,912 | +10% | 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 +30 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.
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.