lyndonkl/cognitive-fallacies-guard
skills/cognitive-fallacies-guard/SKILL.md
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`.
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude cognitive-fallacies-guardInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 6:26 AM9.8s4 files scanned
SKILL.md
- 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
- Fallacy Audit Workflow
- Path Selection Menu
- Path 1: Visual Misleads Scan
- Path 2: Cognitive Bias Check
- Path 3: Data Integrity Verification
- Quick Reference
- 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 — 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
- 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.
Related Skills
lyndonkl/skills/zettel-note
development
VerifiedTrustedCommunity
--- name: zettel-note description: The note-writing discipline for this vault's evergreen knowledge graph, modeled on a Zettelkasten reading companion and governed by the vault conventions. Enforces declarative-claim titles, one claim per note (atomicity), own-words prose with no block quotes, the piped [[slug|Title]] link form, the labeled link-relationship vocabulary (Confirms/Contradicts/Extends/Context/Prerequisite/Builds-on/Applies/Example-of/Contrasts-with), 3-6 links per note, and search-
119SKILL.mdUpdated Jun 12, 2026
lyndonkl/wc-transfer-planner
development
VerifiedTrustedCommunity
Plans between-round FIFA World Cup Fantasy transfers — budgets the round's free transfer(s), forces out players whose nation has been eliminated, chases fixture-swing drops, upgrades on value, and decides when a rebuild is large enough to fire the Wildcard instead of spending free transfers one at a time. Ranks candidate in/out pairs by EV gain over each player's remaining survival horizon (delta xEV weighted by progression_carry) MINUS transfer cost (a free transfer is cheap, a points hit is real, churning the squad for marginal swings is a critic flag), and tags forced/fixture/upgrade priority. Emits a `transfer-plan` signal. Use when called by wc-squad-architect (whose transfer work this skill is the engine for) and by the strategists in the populate stage when their candidate is transfer-adjacent rather than a full rebuild.
119SKILL.mdUpdated Jun 12, 2026
lyndonkl/wc-tournament-state
testing
VerifiedTrustedCommunity
Reads and updates the FIFA World Cup Fantasy tournament state machine (footballfantasy/context/tournament-state.md) — the temporal backbone tracking phase (pre-tournament → group MD1-3 → R32 → R16 → QF → SF → final), budget ($100m group / $105m knockouts), nation cap (3 group, loosening in knockouts), chips remaining, surviving nations, each owned player's elimination-risk horizon, and deadlines. Validates state on load (count/feasibility checks), applies phase transitions, and appends to the append-only state log (never silent overwrite). Use to load state at the start of a run and to commit state changes after the manager makes a move.
119SKILL.mdUpdated Jun 12, 2026
lyndonkl/wc-signal-emitter
development
VerifiedTrustedCommunity
Validates and persists FIFA World Cup Fantasy signal files to signals/YYYY-MM-DD-<type>.md. Checks the required frontmatter (type, round, date, emitted_by, confidence, source_urls), range-checks declared numeric signals, confirms every factual claim carries a source URL or "manager-provided", rejects unknown signal types, and refuses to persist a signal that fails validation (logging the failure instead). Keeps the inter-agent signal layer auditable so downstream agents can trust what they read and never re-derive it. Use whenever an agent or skill writes a signal.
119SKILL.mdUpdated Jun 12, 2026