skills/environmental-scanning-foresight/SKILL.md
Monitors external trends across PESTLE dimensions, detects weak signals of emerging change, develops scenario-based futures, and sets adaptive signposts for early warning. Use when scanning external trends for strategic planning, detecting early indicators of change, planning scenarios for multiple futures, setting signposts and indicators for early warning, or when user mentions environmental scanning, horizon scanning, trend analysis, scenario planning, strategic foresight, or futures thinking.
npx skillsauth add lyndonkl/claude environmental-scanning-foresightInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Copy this checklist and track your progress:
Environmental Scanning Progress:
- [ ] Step 1: Define scope and focus areas
- [ ] Step 2: Scan PESTLE forces and trends
- [ ] Step 3: Detect and validate weak signals
- [ ] Step 4: Assess cross-impacts and interactions
- [ ] Step 5: Develop scenarios for plausible futures
- [ ] Step 6: Set signposts and adaptive triggers
Step 1: Define scope and focus areas
Clarify scanning theme (technology disruption, market evolution, regulatory shift), geographic scope (global, regional, local), time horizon (short 1-2yr, medium 3-5yr, long 5-10yr+), and key uncertainties to explore. See resources/template.md for scoping framework.
Step 2: Scan PESTLE forces and trends
Systematically collect trends across Political, Economic, Social, Technological, Legal, Environmental dimensions. Identify drivers of change (demographics, technology, policy), assess magnitude and direction, and track sources (reports, data, news, expert views). See resources/template.md for structured scanning.
Step 3: Detect and validate weak signals
Identify early indicators that diverge from mainstream expectations—anomalies, edge cases, emergent behaviors. Validate signal credibility (source quality, supporting evidence, plausibility) and assess potential impact if signal amplifies. See resources/methodology.md for detection techniques.
Step 4: Assess cross-impacts and interactions
Map how trends interact (reinforcing, offsetting, cascading). Identify critical uncertainties (high impact + high uncertainty) and predetermined elements (high impact + low uncertainty). See resources/methodology.md for interaction mapping.
Step 5: Develop scenarios for plausible futures
Create 3-4 distinct, internally consistent scenarios spanning range of outcomes. Build scenarios around critical uncertainties (axes with most impact), develop narrative logic, and test strategies against each scenario. See resources/template.md for scenario structure.
Step 6: Set signposts and adaptive triggers
Define leading indicators to monitor, set thresholds that trigger strategy adjustment, and establish monitoring cadence (monthly, quarterly, annual). Validate using resources/evaluators/rubric_environmental_scanning_foresight.json. Minimum standard: Average score ≥ 3.5.
Pattern 1: Industry Disruption Scanning
Pattern 2: Regulatory & Policy Foresight
Pattern 3: Market Evolution & Consumer Trends
Pattern 4: Geopolitical & Macro Risk Monitoring
Pattern 5: Climate & Sustainability Foresight
Key requirements:
Scan systematically across all PESTLE dimensions: Cover Political, Economic, Social, Technological, Legal, Environmental even if some seem less relevant. Selective scanning creates blind spots, and weak signals often appear in unexpected domains.
Distinguish weak signals from noise: Weak signals are early indicators with potential impact, not every random anomaly. Validate each signal: Does the source have credibility? Is there supporting evidence? Is amplification plausible? Would the impact be significant if it scales?
Scenarios should be plausible, not preferred or feared: Scenarios are not predictions or wish fulfillment. They should span the range of outcomes based on critical uncertainties, be internally consistent, and challenge current assumptions. Avoid creating only optimistic scenarios or dystopian extremes.
Focus scenario-building on critical uncertainties: These have both high impact and high uncertainty. High impact + low uncertainty = predetermined elements (plan for them). High impact + high uncertainty = critical uncertainties (build scenarios around). Low impact = context (note but do not build scenarios around).
Map cross-impacts between trends: Trends interact: reinforcing trends accelerate (renewable cost decline + climate policy + corporate commitments), offsetting trends create tension (privacy vs personalization), cascading trends trigger others (pandemic to remote work to office demand collapse). Treat trends as interconnected rather than isolated.
Make signposts observable and leading: Signposts trigger adaptation before the full trend materializes. Leading indicators precede outcomes (building permits before housing prices). Lagging indicators confirm but arrive too late (GDP growth rate). Thresholds should be specific (">20% market share" not "significant adoption") and monitorable (data exists, update frequency known).
Foresight informs strategy without dictating it: Scenarios reveal possibilities and test strategy robustness, but do not automatically prescribe action. Use scenarios to stress-test plans ("does our strategy work in scenarios A, B, C?") and identify no-regrets moves (work in all scenarios) vs hedges (work in some).
Update scans regularly: Environmental conditions change. Set scanning cadence (quarterly PESTLE review, monthly weak signal scan, annual scenario update). Foresight is continuous monitoring, not a one-time exercise.
Common pitfalls:
Key resources:
PESTLE Dimensions:
Time Horizons:
Scenario Archetypes:
Typical workflow time:
When to escalate:
Inputs required:
Outputs produced:
environmental-scanning-foresight.md: PESTLE scan results, weak signals identified, cross-impact analysis, scenarios developed, signposts defined, strategic implicationstesting
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.