Is the BMAD Analyst skill free?

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

What is the BMAD Analyst SkillProof Score?

8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.

How do I install BMAD Analyst?

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 BMAD Analyst 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.

BMAD Analyst

Structured product-brief/research/brainstorm skill with a real completeness-checking script — but built for OpenAI Codex, not Claude

by xmm · xmm/codex-bmad-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.4/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 0c6c136

Ran the bundled scripts/validate-brief.sh against two real product briefs for the same feature: a freeform baseline scored 36% complete (7 of 11 required sections missing), the skill's own template-guided version scored 100% — objective, script-checked, not a judgment call. The catch: this repo is built and documented exclusively for OpenAI Codex (Codex-only installers, ~/.agents/skills target, requires yq+python3), has no Claude Code install path of its own, and its attribution note reveals a Claude-Code-native BMAD fork already exists upstream (aj-geddes/claude-code-bmad-skills) that this was ported FROM — that's arguably the better catalog pick.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 3/5

What BMAD Analyst does

Runs a templated product-discovery workflow (product brief, research report, or brainstorm) with a mandatory batched interview gate and a bundled bash script that objectively scores brief completeness against 11 required sections. Triggers on requests to write a product brief, do market/competitor research, or brainstorm solution options — though the whole repo is documented, installed, and tested only as an OpenAI Codex skill pack.

How to install BMAD Analyst

git clone https://github.com/xmm/codex-bmad-skills
cd codex-bmad-skills
mkdir -p ~/.claude/skills
cp -r skills/bmad-analyst ~/.claude/skills/bmad-analyst

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

Commands — how to trigger BMAD Analyst

/bmad-analyst Structured product-brief/research/brainstorm skill with a real completeness-checking script — but built for OpenAI Codex, not Claude

It also activates on plain-language prompts like these:

Write a product brief for a Slack bot that reminds engineers about on-call
Run a completeness check on this product brief before I share it
Brainstorm solution options for our new onboarding flow problem

Frequently asked questions

Is the BMAD Analyst skill free?: Yes. The skill itself is free from xmm/codex-bmad-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does BMAD Analyst work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. Ran the bundled scripts/validate-brief.sh against two real product briefs for the same feature: a freeform baseline scored 36% complete (7 of 11 required sections missing), the skill's own template-guided version scored 100% — objective, script-checked, not a judgment call. The catch: this repo is built and documented exclusively for OpenAI Codex (Codex-only installers, ~/.agents/skills target, requires yq+python3), has no Claude Code install path of its own, and its attribution note reveals a Claude-Code-native BMAD fork already exists upstream (aj-geddes/claude-code-bmad-skills) that this was ported FROM — that's arguably the better catalog pick.
What is the BMAD Analyst SkillProof Score?: 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 3/5.
How do I install BMAD Analyst?: 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 BMAD Analyst 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.