Narrative Fallacy Guard
Stops a true set of facts from being assembled into a false story. Runs the retrospective slot audit, the outcome-blind rewrite (flip test, separation test), the inevitability audit with its overshoot check, the survivorship graveyard pass, the counterfactual admissibility gate, and the expensive proportion and omission audits. Every check labels and discloses; none deletes. Use when drafting or reviewing history, post-mortems, biography, market or protocol narratives, research writeups, or any account written after the outcome was known, or when user mentions hindsight bias, narrative fallacy
Install
/plugin marketplace add lyndonkl/claudeThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add lyndonkl/claude --skill narrative-fallacy-guardgit clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/narrative-fallacy-guard ~/.claude/skills/narrative-fallacy-guardPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Narrative Fallacy Guard ## Table of Contents - [Core Principles](#core-principles) - [Workflow](#workflow) - [What Each Failed Check Produces](#what-each-failed-check-produces) - [Banned Constructions and Their Licences](#banned-constructions-and-their-licences) - [Guardrails](#guardrails) - [Quick Reference](#quick-reference) **Related skills:** Use `writing-structure-planner` for choosing the architecture before this guard tests it, `narrative-opposition-web` for warranting an antagonist. Use `narrative-evidence-ledger` for the causal ladder and the omission set this skill leans on, `causal-inference-root-cause` for building the causal case this skill audits. Use `narrative-fidelity-audit` for the proportion, representativeness, and anachronism questions asked at draft time, `cognitive-fallacies-guard` for chart-level and visual misleads. ## Core Principles 1. **Label, never delete**: every check terminates in a disclosure sentence, a rewrite, or a tag. None of them terminates in a cut claim. A guard used as a delete rule deletes every interesting explanation and ships a chronicle, and chronicles inform nobody. 2. **The ending is the contaminant**: any structural slot, evaluative adjective, or causal verb selected after the outcome was known is suspect by construction, not by evidence of error.
Details
- Skill name
narrative-fallacy-guard- Repository
- lyndonkl/claude
- Path
skills/narrative-fallacy-guard/SKILL.md- Repo updated
- 1 September 2026
FAQ
What does the Narrative Fallacy Guard skill do?
Stops a true set of facts from being assembled into a false story. Runs the retrospective slot audit, the outcome-blind rewrite (flip test, separation test), the inevitability audit with its overshoot check, the survivorship graveyard pass, the counterfactual admissibility gate, and the expensive proportion and omission audits. Every check labels and discloses; none deletes. Use when drafting or reviewing history, post-mortems, biography, market or protocol narratives, research writeups, or any account written after the outcome was known, or when user mentions hindsight bias, narrative fallacy
How do I install the Narrative Fallacy Guard skill?
Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Narrative Fallacy Guard popular?
It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.
Related skills
Abstraction Concrete Examples
200lyndonkl/claude
Builds 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 Architect
200lyndonkl/claude
Guides 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 Architecture
200lyndonkl/claude
Documents 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.
Narrative Opposition Web
200lyndonkl/claude
Builds a four-corner opposition web for narrative nonfiction and stops the writer from casting whoever lost as the villain. Runs Truby's four-corner worksheet (shared central moral problem, per-corner value clusters, distinct routes of attack, corner-to-corner conflict), the best-possible-opponent audit (same goal, necessity, relentlessness, value conflict, the double, power parity, justification in the opponent's own voice), the Opponent Warrant evidence test that demotes undocumented antagonists to rivals or constraints, and a drive-section collapse check that catches a web that was decorati
Mcphee Structure Derivation
200lyndonkl/claude
Derives a document's structure out of its own corpus instead of picking one off a menu, using John McPhee's coding-and-sorting procedure - cold read, short topic codes one per card, a strict chronology sort run against a strict theme sort, a logged list of every disagreement resolved toward chronology, candidate juxtapositions gated by a state-and-footnote test, a named shape, and an invisibility test. Use when you hold researched material and have no structure yet, when a draft has turned into concept-named sections full of time-scrambled evidence, when deciding whether a flashback is earned,
Option Valuation Toolkit
200lyndonkl/claude
Prices options for valuation work — Black-Scholes with a cost-of-delay yield, binomial trees that allow early exercise, dilution-adjusted employee options for the equity bridge, equity in a heavily levered firm valued as a call on firm value, and implied volatility. Use when employee options or warrants must be subtracted before computing value per share, when a distressed or negative-earnings company's equity still trades above zero, when testing whether a patent, licence, undeveloped reserve or expansion right is a real option that deserves a premium, or when early exercise makes a European
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.