Is the Honest Thinking Partner skill free?

Yes. The skill itself is free from aiskilloftheweek/claude-ai-skill-of-the-week. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Honest Thinking Partner SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Honest Thinking Partner?

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 Honest Thinking Partner 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.

Honest Thinking Partner

Brutally honest feedback engine that dismantles flawed plans instead of validating them.

by aiskilloftheweek · aiskilloftheweek/claude-ai-skill-of-the-week

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · cddcd6c

Ran a real 'should I quit my job for dropshipping' plan through it: baseline gave hedged encouragement, the skill named the planning fallacy driving the plan, costed the avoidance in concrete salary-runway terms, and closed with a forced 2-4-choice question instead of a pep talk.

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 9/10
Docs & honesty 5/5

What Honest Thinking Partner does

Reframes Claude into a structured 6-step critique partner that audits assumptions, names the specific cognitive bias at play, and ends with a prioritized action plan plus a kill-switch signal instead of generic encouragement. Triggers on requests for brutal honesty, devil's-advocate feedback, or a pasted plan/decision seeking validation; explicitly skips pure information questions with no decision component.

How to install Honest Thinking Partner

git clone https://github.com/aiskilloftheweek/claude-ai-skill-of-the-week
cd claude-ai-skill-of-the-week
mkdir -p ~/.claude/skills
cp -r skills/010-honest-thinking-partner ~/.claude/skills/honest-thinking-partner

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Honest Thinking Partner

/honest-thinking-partner Brutally honest feedback engine that dismantles flawed plans instead of validating them.

It also activates on plain-language prompts like these:

Tear apart this business plan and tell me what's actually wrong with it
Be brutally honest about whether this decision makes sense, don't validate me
Play devil's advocate on my startup idea and find the flawed assumptions

Frequently asked questions

Is the Honest Thinking Partner skill free?: Yes. The skill itself is free from aiskilloftheweek/claude-ai-skill-of-the-week. SkillProof publishes the install command and an independent test verdict at no cost.
Does Honest Thinking Partner work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Ran a real 'should I quit my job for dropshipping' plan through it: baseline gave hedged encouragement, the skill named the planning fallacy driving the plan, costed the avoidance in concrete salary-runway terms, and closed with a forced 2-4-choice question instead of a pep talk.
What is the Honest Thinking Partner SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Honest Thinking Partner?: 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 Honest Thinking Partner 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.