cognitive-fallacies-guard
$
npx mdskill add lyndonkl/claude/cognitive-fallacies-guardPrevents visual deception and data integrity violations in charts.
- Detects chartjunk, truncated axes, and cognitive bias exploitation.
- Integrates with visualization engines to audit dashboard accuracy.
- Diagnoses misinterpretation causes and suggests specific chart fixes.
- Delivers actionable corrections to ensure honest data presentation.
SKILL.md
.github/skills/cognitive-fallacies-guardView on GitHub ↗
--- name: cognitive-fallacies-guard description: Detects and prevents visual misleads, cognitive biases, and data integrity violations in visualizations, dashboards, reports, and presentations. Audits charts for honesty, diagnoses misinterpretation causes, and provides specific fixes. 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 accuracy. For general design evaluation, use `design-evaluation-audit`. For cognitive foundations, use `cognitive-design`. --- # Cognitive Fallacies Guard ## Table of Contents - [Overview](#overview) - [Fallacy Audit Workflow](#fallacy-audit-workflow) - [Path Selection Menu](#path-selection-menu) - [Path 1: Visual Misleads Scan](#path-1-visual-misleads-scan) - [Path 2: Cognitive Bias Check](#path-2-cognitive-bias-check) - [Path 3: Data Integrity Verification](#path-3-data-integrity-verification) - [Quick Reference](#quick-reference) - [Guardrails](#guardrails) --- ## Overview Visualizations are persuasive — common mistakes cause systematic misinterpretation, not just aesthetic failures. This skill scans for visual misleads (chartjunk, truncated axes, 3D distortion), checks for cognitive bias exploitation (confirmation bias reinforcement, anchoring, framing manipulation), and verifies data integrity (honest axes, complete data, fair comparisons). **Related skills:** `design-evaluation-audit` for general design evaluation, `cognitive-design` for cognitive foundations, `d3-visualization` for creating visualizations, `visual-storytelling-design` for data stories. --- ## 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](resources/fallacies-catalog.md) — 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](resources/fallacies-catalog.md) — 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](resources/detection-patterns.md) — 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](resources/fallacies-catalog.md) — 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](resources/fallacies-catalog.md) — Section 3** --- ### Path 3: Data Integrity Verification **Choose this when:** Verifying completeness, honesty, and context of data presentation. **→ [Go to Detection Patterns](resources/detection-patterns.md)** --- ## Quick Reference ### 5 Integrity Principles 1. **Honest Axes** — Bar charts start at zero; uniform scale intervals; clear labels 2. **Fair Comparisons** — Same scale for compared items; no dual-axis manipulation 3. **Complete Context** — Full time period shown; baselines provided; denominators clarified 4. **Accurate Encoding** — Visual proportional to numerical; no volume illusions; 2D design 5. **Transparency** — Data sources cited; limitations acknowledged; methodology stated ### Quick Severity Guide - **Severity: High** — 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 **Scope boundaries:** This skill detects visual misleads, identifies cognitive bias exploitation, verifies data integrity, and provides specific fixes for each fallacy found. It does not create designs, evaluate general usability, teach cognitive theory, or assess aesthetic quality.
More from lyndonkl/claude
- abstraction-concrete-examplesBuilds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
- academic-letter-architectGuides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
- adr-architectureDocuments significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
- adverse-selection-priorProduces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
- alignment-values-north-starCreates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.
- analogy-weight-checkFor every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reused analogy, catalog check, metaphor check.
- answer-uncomfortable-questionTakes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
- attribute-performanceFor each substacker post that materially over- or under-performs the rolling baseline (|z| ≥ 1.0), produces a plain-English attribution paragraph with calibrated confidence (high / medium / low / unexplained). Considers subject-line effect, topic zeitgeist, external share, day-of-week, length effect, and audience-notes signals. Labels unexplained outliers explicitly rather than fabricating a story. Use after compute-baseline when outlier posts exist. Trigger keywords: attribution, why did this post work, outlier explanation, performance analysis.
- auction-first-price-shadingComputes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
- auction-winners-curse-haircutApplies a Bayesian haircut to a bid valuation for common-value auctions where winning is itself evidence the bidder over-estimated. Takes a raw valuation, a value-type classification (common_value / private_value / mixed), the number of informed bidders N, and a signal-dispersion estimate, and returns an adjusted valuation. Domain-neutral and reusable across fantasy FAAB, prediction markets, M&A bids, ad-auction budgets, and any generic bidding context. Use when user mentions "winner's curse", "common value auction", "valuation haircut", "adverse valuation", "Bayesian bid adjustment", or "over-paying in auction".