Comprehensive Thinking
Five-pass judgment framework for high-stakes, high-uncertainty decisions and root-cause calls.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 71ae410
Run against a real pricing-strategy question (switch a $600K-ARR SaaS from per-seat to usage-based?), it reframes the question from 'which pricing model' to 'is per-seat mismatched with the value-scaling variable', names a real strongest-counterargument, and labels its own premises as fact/guess/borrowed before concluding - a baseline single-pass answer gave generic consulting advice with no counter-argument or premise check.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 4/5
What Comprehensive Thinking does
Forces a mandatory five-layer review (problem framing, master-theory lens, synthesized fact base, strongest-counterargument and premise audit, then a falsifiable synthesis) instead of a single-pass answer, for complex judgment calls where being wrong is costly - architecture decisions, financial/ledger truth, strategic pivots, root-cause analysis. Entirely Chinese-language instructions; triggers on explicit phrases like "全面思考", "从根上看", "根因分析" as well as English high-risk project signals (multi-region, ledger, live trading).
How to install Comprehensive Thinking
git clone https://github.com/syzkillall/comprehensive-thinking-skill
cd comprehensive-thinking-skill
mkdir -p ~/.claude/skills
cp -r . ~/.claude/skills/comprehensive-thinking
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Comprehensive Thinking
-
/comprehensive-thinkingFive-pass judgment framework for high-stakes, high-uncertainty decisions and root-cause calls.
It also activates on plain-language prompts like these:
-
From the root cause up, should pricing shift from per-seat to usage-based? -
This decision is high-stakes, walk me through every angle before deciding -
We're planning a live-trading migration; think through this exhaustively
Frequently asked questions
- Is the Comprehensive Thinking skill free?
- Yes. The skill itself is free from syzkillall/comprehensive-thinking-skill. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Comprehensive Thinking work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Run against a real pricing-strategy question (switch a $600K-ARR SaaS from per-seat to usage-based?), it reframes the question from 'which pricing model' to 'is per-seat mismatched with the value-scaling variable', names a real strongest-counterargument, and labels its own premises as fact/guess/borrowed before concluding - a baseline single-pass answer gave generic consulting advice with no counter-argument or premise check.
- What is the Comprehensive Thinking SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
- How do I install Comprehensive Thinking?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Comprehensive Thinking with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.