product-on-purpose

Think Audit Reasoning — Security skill for Claude Code

Security community

Check whether a conclusion is sound before trusting it, by sorting evidence from inference, reconstructing the inferential climb, and reviewing through separated lenses.

How to install Think Audit Reasoning

Installs to ~/.claude/skills/product-on-purpose-thinking-framework-skills-think-audit-reasoning/SKILL.md

Terminal
mkdir -p ~/.claude/skills/product-on-purpose-thinking-framework-skills-think-audit-reasoning && curl -fsSL https://raw.githubusercontent.com/product-on-purpose/thinking-framework-skills/HEAD/commands/think-audit-reasoning.md -o ~/.claude/skills/product-on-purpose-thinking-framework-skills-think-audit-reasoning/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Think Audit Reasoning does

description: Check whether a conclusion is sound before trusting it, by sorting evidence from inference, reconstructing the inferential climb, and reviewing through separated lenses. argument-hint: "[the decision, problem, or material to work through]" maps-to: think-audit-reasoning

Run the **think-audit-reasoning** recipe: 3 skills chaine

Alternatives in Security

  • Reflexion — Audit and optimize the .claude/ ecosystem — skills, hooks, guides, patterns, agents, and settings — for qualit 224 ★
  • CodexQB — CodexQB is a Codex plugin for evidence-backed repo comprehension, planning, QA audit, and gated implementation 186 ★
  • Beamer Skill — A Claude Code skill for creating, compiling, reviewing, and polishing academic Beamer LaTeX presentations 163 ★

Full documentation available on GitHub

View Source Repository

Related Skills

UX Check — Security skill for Claude Code

UX Check

Audit a frontend surface through the Laws of UX and Motion lenses. Fitts's law, Hick's law, Doherty threshold,

Security community
Twin Sparrow Oppus Reasoning Contract — Security skill for Claude Code

Twin Sparrow Oppus Reasoning Contract

Enforce disciplined reasoning structure for research, architecture, audit, spec review, implementation plannin

Security community
Ke Autonomous — Security skill for Claude Code

Ke Autonomous

Orchestrate an approved project through product analysis, architecture, implementation, automated testing, QA,

Security community
Audit Diff — Security skill for Claude Code

Audit Diff

Diff two Rugproof audit reports (before vs after) to track regressions — what's new, what's fixed, and whether

Security community
J Diff Review — Security skill for Claude Code

J Diff Review

Deep multi-perspective diff review — code quality, security, testing gaps, documentation drift, observability

Security community
Customer Changelog Check — Security skill for Claude Code

Customer Changelog Check

Audit whether user-visible changes in the current session have matching CHANGELOG.md entries; report MISSING w

Security community

Related Agents

Meta Challenger — Development agent for Claude Code

Meta Challenger

Challenges reasoning quality of plans, decisions, and approaches through 6 meta-cognitive lenses. Use when rev

Development community
Challenge Assumptions — Development agent for Claude Code

Challenge Assumptions

Probe lens 2 of 6. Surfaces the hidden premises an argument rests on and tests whether the conclusion survives

Development community
Gitnexus Synthesis Critic — Development agent for Claude Code

Gitnexus Synthesis Critic

GitNexus final review synthesis critic. Use to check whether the final PR review is evidence-grounded, risk-pr

Development community