Systematically analyze societal impacts of technologies using McLuhan's Tetrad of Media Effects. Use when evaluating new technology, planning technology adoption, or analyzing technology policy.
npx skills add https://github.com/jwynia/agent-skills --skill technology-impact
Systematically analyze the societal impacts of technologies using McLuhan's Tetrad of Media Effects. Examines what technology enhances, obsoletes, retrieves, and reverses to reveal non-obvious consequences.
Every technology simultaneously has four effects:
| Effect | Question | What It Reveals |
|--------|----------|-----------------|
| Enhancement | What does it amplify? | Primary capabilities increased |
| Obsolescence | What does it displace? | What becomes less relevant |
| Retrieval | What does it bring back? | Historical patterns revived |
| Reversal | What does it become when pushed to extreme? | Paradoxical consequences |
Examine each societal domain:
Economic
Social
Political
Educational
Healthcare
Environmental
For each effect, examine impact on:
Demographics
Power Structures
Vulnerable Populations
Time Horizons
Development Patterns
Historical Parallels
Cross-Domain Effects
Equilibrium Shifts
Power Dynamics
Enhancement:
What it amplifies:
-
-
Obsolescence:
What it displaces:
-
-
Retrieval:
What it brings back:
-
-
Reversal:
What it becomes at extreme:
-
-
| Domain | Enhancement | Obsolescence | Retrieval | Reversal |
|--------|-------------|--------------|-----------|----------|
| Economic | | | | |
| Social | | | | |
| Political | | | | |
| Educational | | | | |
| Healthcare | | | | |
| Environmental | | | | |
| Group | Positive Effects | Negative Effects | Net Assessment |
|-------|------------------|------------------|----------------|
| | | | |
| Timeframe | Most Likely Effects |
|-----------|---------------------|
| Immediate | |
| Short-term | |
| Medium-term | |
| Long-term | |
1.
2.
3.
Enhancement:
Obsolescence:
Retrieval:
Reversal:
Pattern: Only analyzing enhancement effects. Focusing on what technology enables while ignoring what it destroys, retrieves, or reverses.
Why it fails: Creates incomplete analysis that misses critical consequences. Every enhancement has a shadow—ignoring it leads to surprised stakeholders.
Fix: Force yourself through all four quadrants. The reversal quadrant is especially important for identifying unintended consequences.
Pattern: Identifying immediate effects without tracing systemic implications. "Social media enhances connection" without examining what connection means at scale.
Why it fails: First-order effects are obvious; value comes from second and third-order analysis. Surface analysis tells stakeholders nothing they don't already know.
Fix: For each effect, ask "and then what?" at least twice. Map cross-domain cascades. Identify feedback loops.
Pattern: Analyzing technology in isolation without examining historical parallels. Missing that we've seen similar patterns before.
Why it fails: History reveals patterns that inform projections. The printing press, telegraph, and telephone all have lessons for digital technology.
Fix: Explicitly identify 2-3 historical analogs. What was enhanced, obsolesced, retrieved, reversed then? What patterns persist?
Pattern: Treating all stakeholders as homogeneous. "Users will experience..." without differentiating who wins and who loses.
Why it fails: Technology redistributes power unevenly. Analysis that ignores differential impact misses the most important political dimensions.
Fix: Segment stakeholders by power position, access, and capability. Analyze each quadrant for each stakeholder class.
Pattern: Mixing immediate and long-term effects without distinguishing timelines. "This will obsolete X" without specifying when or under what conditions.
Why it fails: Timelines matter for planning. Something that becomes obsolete in 20 years requires different strategy than something obsolete next year.
Fix: Separate effects by timeframe: immediate (0-2 years), short-term (2-5), medium-term (5-10), long-term (10+).
Inbound:
Outbound:
Complementary:
media-meta-analysis: For analyzing discourse about technologyGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take jwynia/technology-impact from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.