ReddRadar
Agent skill
cognitive-fallacies-guard
Use when detecting and preventing visual misleads, cognitive biases, and design failures in data visualizations, dashboards, reports, or presentations. Invoke when user mentions chartjunk, misleading chart, truncated axis, data integrity, visual deception, 3D chart problems, cherry-picking data, or needs to audit visualizations for honesty and accuracy.
Install this agent skill to your Project
npx add-skill https://github.com/lyndonkl/claude/tree/main/skills/cognitive-fallacies-guard
SKILL.md
Cognitive Fallacies Guard
Table of Contents
- Read This First
- Fallacy Audit Workflow
- Path Selection Menu
- Path 1: Visual Misleads Scan
- Path 2: Cognitive Bias Check
- Path 3: Data Integrity Verification
- Quick Reference
- Guardrails
Read This First
What This Skill Does
This skill helps you detect and prevent visual misleads, cognitive biases, and data integrity violations in visualizations, dashboards, reports, and presentations.
Core principle: Visualizations are persuasive — designers have an ethical obligation to communicate honestly. Common mistakes aren't just aesthetic failures; they cause systematic misinterpretation.
Why It Matters
Problems caused by fallacies:
- Chartjunk consumes working memory without conveying data
- Truncated axes exaggerate differences and mislead comparisons
- 3D effects distort perception through volume illusions
- Cherry-picking misleads by omitting contradictory context
- Spurious correlations imply false causation
Why designers commit fallacies:
- Aesthetic appeal prioritized over clarity
- Unaware of cognitive impacts
- Following bad examples
- Intentional manipulation (sometimes)
When to Use This Skill
Use this skill when:
- ✓ Auditing visualizations for honesty before publication
- ✓ Reviewing charts and dashboards for misleading patterns
- ✓ Diagnosing why users misinterpret data
- ✓ Preventing common visualization mistakes during design
- ✓ Verifying data integrity in reports and presentations
Do NOT use for:
- ✗ General design evaluation (use
design-evaluation-audit) - ✗ Learning cognitive foundations (use
cognitive-design) - ✗ Creating new visualizations (use
d3-visualization) - ✗ Building data stories (use
visual-storytelling-design)
Fallacy Audit Workflow
Time: 15-30 minutes
Copy this checklist and track your progress:
Fallacy Audit Progress:
- [ ] Step 1: Scan for Visual Misleads
- [ ] Step 2: Check for Cognitive Biases
- [ ] Step 3: Verify Data Integrity
Step 1: Scan for Visual Misleads
Check for chartjunk, 3D effects, truncated axes, volume illusions, and inappropriate chart types. These are the most common and visible fallacies.
Resource: Fallacies Catalog — Sections 1-2 (Visual Noise, Perceptual Distortion)
Step 2: Check for Cognitive Biases
Look for confirmation bias reinforcement, anchoring effects, and framing manipulation. These are subtler but can significantly influence interpretation.
Resource: Fallacies Catalog — Section 3 (Cognitive Bias Exploitation)
Step 3: Verify Data Integrity
Confirm honest axes, complete data, fair comparisons, proper context, and no spurious correlations. This is the most critical layer.
Resource: Detection Patterns — Integrity Principles and Quick Scan Checklist
Path Selection Menu
Path 1: Visual Misleads Scan
Choose this when: Checking for chartjunk, 3D effects, truncated axes, and encoding problems.
→ Go to Fallacies Catalog — Sections 1-2
Path 2: Cognitive Bias Check
Choose this when: Looking for bias reinforcement in dashboard design, presentation framing, or data selection.
→ Go to Fallacies Catalog — Section 3
Path 3: Data Integrity Verification
Choose this when: Verifying completeness, honesty, and context of data presentation.
→ Go to Detection Patterns
Quick Reference
5 Integrity Principles
- Honest Axes — Bar charts start at zero; uniform scale intervals; clear labels
- Fair Comparisons — Same scale for compared items; no dual-axis manipulation
- Complete Context — Full time period shown; baselines provided; denominators clarified
- Accurate Encoding — Visual proportional to numerical; no volume illusions; 2D design
- Transparency — Data sources cited; limitations acknowledged; methodology stated
Quick Severity Guide
- CRITICAL: Integrity violations (truncated bars without disclosure, cherry-picked data, implied causation)
- HIGH: Perceptual distortions (3D effects, volume illusions, missing denominators)
- MEDIUM: Bias reinforcement (one-sided framing, anchoring order, confirmation bias layout)
- LOW: Visual noise (excessive gridlines, decorative elements, ornamental borders)
Guardrails
This skill does NOT: Create designs, evaluate general usability, teach cognitive theory, or assess aesthetic quality.
This skill DOES: Detect visual misleads, identify cognitive bias exploitation, verify data integrity, and provide specific fixes for each fallacy found.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
lyndonkl/claude
synthesis-and-analogy
Use when synthesizing information from multiple sources (literature review, stakeholder feedback, research findings, data from different systems), creating or evaluating analogies for explanation or problem-solving (cross-domain transfer, "X is like Y", structural mapping), combining conflicting viewpoints into unified framework, identifying patterns across disparate sources, finding creative solutions by transferring principles from one domain to another, testing whether analogies hold (surface vs deep similarities), or when user mentions "synthesize", "combine sources", "analogy", "like", "similar to", "transfer from", "integrate findings", "what's it analogous to".
lyndonkl/claude
socratic-teaching-scaffolds
Use when teaching complex concepts (technical, scientific, philosophical), helping learners discover insights through guided questioning rather than direct explanation, correcting misconceptions by revealing contradictions, onboarding new team members through scaffolded learning, mentoring through problem-solving question frameworks, designing self-paced learning materials, or when user mentions "teach me", "help me understand", "explain like I'm", "learning path", "guided discovery", or "Socratic method".
lyndonkl/claude
environmental-scanning-foresight
Use when scanning external trends for strategic planning, monitoring PESTLE forces (Political, Economic, Social, Technological, Legal, Environmental), detecting weak signals (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, futures thinking, or emerging issues monitoring.
lyndonkl/claude
embedding-fusion-strategy
Use when designing embedding strategies that fuse semantic and structural information for knowledge graphs. Invoke when user mentions node embeddings, structural embeddings, semantic embeddings, contrastive alignment, embedding fusion, vector representations for graphs, or combining text and graph signals. Provides embedding selection, fusion design, and implementation guidance.
lyndonkl/claude
constraint-based-creativity
Use when brainstorming feels stuck or generates obvious ideas, need to break creative patterns, working with limited resources (budget/time/tools/materials), want unconventional solutions, designing with specific limitations, user mentions "think outside the box", "we're stuck", "same old ideas", "tight constraints", "limited budget/time", or seeking innovation through limitation rather than abundance.
lyndonkl/claude
symmetry-group-identifier
Use when you've identified candidate symmetries and need to map them to mathematical groups for architecture design. Invoke when user mentions cyclic groups, dihedral groups, Lie groups, SO(3), SE(3), permutation groups, or needs to formalize symmetries into group theory language. Provides taxonomy and mathematical foundations from Visual Group Theory principles.
Didn't find tool you were looking for?