Is the Deep Brainstorming skill free?

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

What is the Deep Brainstorming SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.

How do I install Deep Brainstorming?

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 Deep Brainstorming 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.

Deep Brainstorming

Multi-round, bias-audited research process for costly-to-reverse tech and architecture picks.

by belumume · belumume/claude-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 40b2c24

Ran a real search-tech decision for an offline-first notes app: an unguided pass reached straight for Elasticsearch/Algolia (server-dependent, wrong fit for the stated offline requirement); following the skill's sanitize-vision + bias-audit + independent-verification steps caught that exact marketing/popularity-bias failure and, backed by 3 live corroborating sources, redirected to embedded serverless options (SQLite FTS5 / Tantivy) that actually satisfy the constraint.

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 3/5

What Deep Brainstorming does

Runs a disciplined, multi-round research and review process for high-stakes tech-stack or architecture decisions, auditing every research round against 9 known bias types (marketing, popularity, hallucinated benchmarks, phantom requirements, and more) and requiring independent local verification of any claim before it enters a spec. Triggers when the user wants an 'objectively best' pick, is starting an architecture/tech-stack decision, or worries about vendor bias, hallucinated benchmarks, or premature convergence on a popular tool. Ships with reference templates for research-round prompts and a three-phase (verify-fix / adversarial / security-ops) spec review.

How to install Deep Brainstorming

git clone https://github.com/belumume/claude-skills
cd claude-skills
mkdir -p ~/.claude/skills
cp -r deep-brainstorming ~/.claude/skills/deep-brainstorming

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

Commands — how to trigger Deep Brainstorming

/deep-brainstorming Multi-round, bias-audited research process for costly-to-reverse tech and architecture picks.

It also activates on plain-language prompts like these:

What's the objectively best database choice here, free of vendor bias?
We're picking an architecture for a new service, audit it for bias first.
I'm worried these benchmarks are marketing fluff, verify before we commit.

Frequently asked questions

Is the Deep Brainstorming skill free?: Yes. The skill itself is free from belumume/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Deep Brainstorming work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran a real search-tech decision for an offline-first notes app: an unguided pass reached straight for Elasticsearch/Algolia (server-dependent, wrong fit for the stated offline requirement); following the skill's sanitize-vision + bias-audit + independent-verification steps caught that exact marketing/popularity-bias failure and, backed by 3 live corroborating sources, redirected to embedded serverless options (SQLite FTS5 / Tantivy) that actually satisfy the constraint.
What is the Deep Brainstorming SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.
How do I install Deep Brainstorming?: 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 Deep Brainstorming 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.