Is the Briesearch skill free?

Yes. The skill itself is free from paulnsorensen/easy-cheese. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Briesearch SkillProof Score?

8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Briesearch?

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 Briesearch 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.

Briesearch

Cited, multi-source research with a mechanical grounding checker — but ships wired into a whole sibling-skill suite.

by paulnsorensen · paulnsorensen/easy-cheese

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.4/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 8a379fa

Ran the bundled ground_check.py grounding linter on a real synthesis report (httpx HTTP/2 support) and it correctly flagged an under-supported 'certain' absence claim — the mechanical check works. But the skill body hard-references sibling files outside its own folder (../cheese/references/ask-user-question.md, ../cheese/references/formatting.md, ../age/references/voice.md, ../age/references/sub-agent-gate.md) that a bare `cp -r skills/briesearch` install leaves behind, silently breaking its house-style formatting, voice kernel, and clarifying-question transport.

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 8/10
Docs & honesty 4/5

What Briesearch does

Routes a research question to library docs (Context7), the web (Tavily), local code, and GitHub, then produces a claim-level evidence table with per-claim confidence labels (certain/speculating/don't know). Triggers on "research X", "look up the API for Y", "compare libraries", "what does the doc say about Z", or bare library-name mentions; explicitly skips single obvious file lookups.

How to install Briesearch

git clone https://github.com/paulnsorensen/easy-cheese
cd easy-cheese
mkdir -p ~/.claude/skills
cp -r skills/briesearch ~/.claude/skills/briesearch

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

Commands — how to trigger Briesearch

/briesearch Cited, multi-source research with a mechanical grounding checker — but ships wired into a whole sibling-skill suite.

It also activates on plain-language prompts like these:

Does httpx actually support HTTP/2, and can you cite the docs?
Compare Postgres and MySQL for JSON columns with real citations
Look up how Stripe's webhook signature verification API works

Frequently asked questions

Is the Briesearch skill free?: Yes. The skill itself is free from paulnsorensen/easy-cheese. SkillProof publishes the install command and an independent test verdict at no cost.
Does Briesearch work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Works with setup. Ran the bundled ground_check.py grounding linter on a real synthesis report (httpx HTTP/2 support) and it correctly flagged an under-supported 'certain' absence claim — the mechanical check works. But the skill body hard-references sibling files outside its own folder (../cheese/references/ask-user-question.md, ../cheese/references/formatting.md, ../age/references/voice.md, ../age/references/sub-agent-gate.md) that a bare `cp -r skills/briesearch` install leaves behind, silently breaking its house-style formatting, voice kernel, and clarifying-question transport.
What is the Briesearch SkillProof Score?: 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Briesearch?: 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 Briesearch 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.