Think Idea Quality Audit — Security skill for Claude Code
Decide which of a batch of candidate ideas are worth committing to, by scoring them on explicit quality dimensions and then adversarially stress-testing the strongest few.
How to install Think Idea Quality Audit
Installs to ~/.claude/skills/product-on-purpose-thinking-framework-skills-think-idea-quality-audit/SKILL.md
mkdir -p ~/.claude/skills/product-on-purpose-thinking-framework-skills-think-idea-quality-audit && curl -fsSL https://raw.githubusercontent.com/product-on-purpose/thinking-framework-skills/HEAD/commands/think-idea-quality-audit.md -o ~/.claude/skills/product-on-purpose-thinking-framework-skills-think-idea-quality-audit/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Think Idea Quality Audit does
description: Decide which of a batch of candidate ideas are worth committing to, by scoring them on explicit quality dimensions and then adversarially stress-testing the strongest few. argument-hint: "[the decision, problem, or material to work through]" maps-to: think-idea-quality-audit
Run the **think-idea-quality-audit** recipe: 2 sk
Alternatives in Security
- Cve MCP Server — Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS sco 1.2k ★
- Engage.Cvediff — Find the canonical fix commit(s) for a CVE across sources, then diff for root cause 348 ★
- Audit Agent Sessions — Analyze all agent sessions from the last 3 days across Claude, Codex, and Gemini 238 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Motion Audit
Audit animation timing, easing, springs, and transitions — decide first whether motion should exist, then appl
Gaia Debt
Fix the tech-debt backlog, a single issue or a recommended related batch, highest severity then oldest first,
Cw Audit
Red-team and premortem an existing plan or strategy. Takes any document and stress-tests it.
OpenVault
OpenVault: a bootstrap CLI that generates a retrieval-first Obsidian vault for SOC work (IR, DFIR, Threat Hunt
Integration Audit
Run the Playbook §6a/§12 integration audit — sweep the platform for the five darkness classes (broken wiring,
Evolution Audit
Audit how Evo turns real sessions into evolution plans and candidate artifacts
Related Agents
Critical Friend
Use this agent to stress-test a draft argument, plan, or position. Returns the sharpest pushbacks, the stronge
Critical Thinking
Critical thinking mode that challenges assumptions and probes reasoning. Use when you want a second opinion on
Advocate
Argues one assigned approach in a boss-run debate. Read-only; builds the strongest case for its position and a