Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply PESTEL framework to scan the macro-environment across Political, Economic, Social, Technological, Environmental, and Legal dimensions. Use this skill when the user needs to assess external macro factors affecting a business, industry, or market — especially before entering a new country, launching a product, or evaluating regulatory risk. Also use when the user mentions 'macro analysis', 'external environment', or 'what trends should we watch'.
.claude/skills/asgard-ai-platform-biz-pestel/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-15 | ✓→✓ | = Same ✓ | 93% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 27% | 0% |
PESTEL scans the macro-environment across six dimensions to identify external forces that could impact a business or industry. It operates at the macro level — broader than industry (Porter's Five Forces) or company (SWOT). Use it to surface trends and risks the organization cannot control but must respond to.
Trigger conditions:
When NOT to use:
IRON LAW: Macro-Level Only
PESTEL factors are MACRO-ENVIRONMENT forces — they affect all players in
a market, not just one company. "Our costs are rising" is not a PESTEL factor.
"Inflation is driving up input costs across the industry" is.
Test: "Does this factor affect ALL companies in this market?"
YES → Valid PESTEL factor
NO → It belongs in SWOT or Five Forces, not PESTELIRON LAW: Evidence-Based, Not Speculative
Every PESTEL factor must be grounded in observable data, trends, or events.
"Technology might change" is not a factor. "5G rollout reaching 70% coverage
by 2026 (GSMA data)" is a factor.For each of the six dimensions, identify 2-4 key factors with evidence:
P — Political: Government stability, trade policy, taxation policy, political risk, corruption, foreign investment rules
E — Economic: GDP growth, inflation, interest rates, exchange rates, unemployment, consumer spending power, commodity prices
S — Social: Demographics, cultural trends, consumer attitudes, lifestyle changes, education levels, urbanization, health consciousness
T — Technological: R&D activity, automation, digital infrastructure, emerging technologies, innovation rate, tech transfer
E — Environmental: Climate change, sustainability regulations, resource scarcity, carbon emissions rules, environmental awareness, natural disaster risk
L — Legal: Employment law, consumer protection, data privacy (GDPR, PDPA), industry-specific regulation, IP protection, antitrust
For each factor:
markdown# PESTEL Analysis: {Market/Country} for {Business Context} ## Scope - Market: ... - Perspective: ... - Time horizon: ... ## PESTEL Factors | Dimension | Factor | Evidence | Impact | Direction | |-----------|--------|----------|--------|-----------| | Political | ... | ... | H/M/L | +/− | | Economic | ... | ... | H/M/L | +/− | | Social | ... | ... | H/M/L | +/− | | Technological | ... | ... | H/M/L | +/− | | Environmental | ... | ... | H/M/L | +/− | | Legal | ... | ... | H/M/L | +/− | ### Political {Detailed analysis} ### Economic {Detailed analysis} ### Social {Detailed analysis} ### Technological {Detailed analysis} ### Environmental {Detailed analysis} ### Legal {Detailed analysis} ## Priority Factors 1. {Highest impact factor} — {required response} 2. ... 3. ... ## Cross-Dimensional Connections - {Factor A} → {Factor B} → {combined implication}
Scenario: PESTEL for Vietnam market, perspective of a Taiwanese food manufacturer (2025-2028)
| Dimension | Factor | Evidence | Impact | Direction | |-----------|--------|----------|--------|-----------| | Political | Vietnam-Taiwan informal trade relations stable; no diplomatic friction | Bilateral trade volume growing YoY | Med | + | | Economic | Vietnam GDP growth 6.5% (2024), rising middle class | World Bank data, urban consumer spending up 12% | High | + | | Social | Young population (median age 31), increasing demand for packaged food | UN demographic data, urbanization rate 39% → projected 45% by 2030 | High | + | | Technological | Cold chain logistics still underdeveloped outside Ho Chi Minh and Hanoi | Only 30% of food supply chain has cold storage (VCCI report) | High | − | | Environmental | Government tightening plastic packaging regulations | Decree on solid waste management (2024) requiring recyclable packaging | Med | − | | Legal | Food safety registration (Decree 15/2018) requires 6-month approval cycle | Foreign food products need Certificate of Free Sale + lab testing in-country | High | − |
Scenario: Same Vietnam market analysis
What went wrong:
references/framework-comparison.mdreferences/data-sources.md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | pass→pass | 15,159 | 14,989 | -1% | 1 | 1 | 0% | 2,095 | 4,042 | +93% | 0 | 0 | — |
case-04 | pass→pass | 18,569 | 12,674 | -32% | 1 | 1 | 0% | 2,890 | 3,683 | +27% | 0 | 0 | — |
case-01 | fail→pass | 45,584 | 38,717 | -15% | 1 | 1 | 0% | 7,283 | 7,215 | -1% | 0 | 0 | — |
case-02 | fail→pass | 47,452 | 37,310 | -21% | 1 | 1 | 0% | 6,725 | 6,650 | -1% | 0 | 0 | — |
case-03 | pass→pass | 42,697 | 29,472 | -31% | 1 | 1 | 0% | 6,866 | 6,377 | -7% | 0 | 0 | — |
case-05 | pass→pass | 24,280 | 18,318 | -25% | 1 | 1 | 0% | 3,557 | 4,597 | +29% | 0 | 0 | — |
case-06 | pass→pass | 14,176 | 14,761 | +4% | 1 | 1 | 0% | 2,414 | 4,189 | +74% | 0 | 0 | — |
case-07 | pass→pass | 17,880 | 21,664 | +21% | 1 | 1 | 0% | 2,809 | 5,233 | +86% | 0 | 0 | — |
case-08 | pass→pass | 20,338 | 18,644 | -8% | 1 | 1 | 0% | 2,987 | 4,460 | +49% | 0 | 0 | — |
case-09 | pass→pass | 18,686 | 19,191 | +3% | 1 | 1 | 0% | 2,922 | 4,819 | +65% | 0 | 0 | — |
case-10 | pass→pass | 20,842 | 15,161 | -27% | 1 | 1 | 0% | 2,827 | 4,142 | +47% | 0 | 0 | — |
case-11 | pass→pass | 11,070 | 8,679 | -22% | 1 | 1 | 0% | 1,796 | 3,009 | +68% | 0 | 0 | — |
case-12 | fail→fail | 18,973 | 19,625 | +3% | 1 | 1 | 0% | 2,851 | 4,808 | +69% | 0 | 0 | — |
case-13 | pass→pass | 16,089 | 10,309 | -36% | 1 | 1 | 0% | 2,314 | 3,229 | +40% | 0 | 0 | — |
case-14 | pass→pass | 18,236 | 15,958 | -12% | 1 | 1 | 0% | 2,785 | 4,019 | +44% | 0 | 0 | — |
case-16 | pass→pass | 38,556 | 32,614 | -15% | 1 | 1 | 0% | 5,880 | 6,406 | +9% | 0 | 0 | — |
case-17 | fail→pass | 18,951 | 14,354 | -24% | 1 | 1 | 0% | 3,400 | 3,998 | +18% | 0 | 0 | — |
case-18 | pass→pass | 25,359 | 23,055 | -9% | 1 | 1 | 0% | 3,869 | 5,376 | +39% | 0 | 0 | — |
case-19 | pass→pass | 26,550 | 22,854 | -14% | 1 | 1 | 0% | 4,151 | 5,483 | +32% | 0 | 0 | — |
case-20 | pass→pass | 23,631 | 20,105 | -15% | 1 | 1 | 0% | 3,890 | 4,883 | +26% | 0 | 0 | — |
case-21 | pass→pass | 29,245 | 21,156 | -28% | 1 | 1 | 0% | 4,502 | 4,685 | +4% | 0 | 0 | — |
case-22 | pass→pass | 19,795 | 21,079 | +6% | 1 | 1 | 0% | 3,238 | 5,128 | +58% | 0 | 0 | — |
case-23 | pass→pass | 18,740 | 24,154 | +29% | 1 | 1 | 0% | 3,087 | 5,386 | +74% | 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 +13 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.