Is the Research Architect Audit skill free?

Yes. The skill itself is free from mmTheBest/Research-Architect. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Research Architect Audit SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Research Architect Audit?

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 Research Architect Audit 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.

Research Architect Audit

Gate-by-gate audit of research paper drafts; won't pass on missing evidence

by mmTheBest · mmTheBest/Research-Architect

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 18, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · c311372

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 18, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Fed it a flawed draft (causal overclaim from a survey, an unsourced '73%' stat, a near-copied exemplar quote, no methods) in an otherwise empty paper_output; the bundled first_paper_artifact_check.py flagged all 33 missing upstream artifacts and the 13-gate rubric mapped each planted flaw to a named gate. Unlike a plain read that risks a 'looks solid' pass, the mandatory clearance gate refuses completion while evidence is missing, and all three gate scripts run under Python 3.13. Value is real but coupled to the full Research Architect pipeline: a standalone draft gets an audit skeleton plus owner-routing rather than a finished paper.

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 7/10
Docs & honesty 5/5

What Research Architect Audit does

Audits a Research Architect paper draft across 13 named quality gates, routing each failure to the artifact that owns it and recording missing upstream work as blocking debts. Triggers when reviewing, revising, or deciding whether to complete an RA draft. Ships Python scripts that verify the artifact trail and refuse to declare completion while evidence or provenance is missing.

How to install Research Architect Audit

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Research Architect Audit

/research-architect-audit Gate-by-gate audit of research paper drafts; won't pass on missing evidence

It also activates on plain-language prompts like these:

Audit my research paper draft before I submit it for missing evidence.
Check if the citations and claim boundaries in my draft are solid.
Is this paper's artifact trail complete, or does it need more revision?

Frequently asked questions

Is the Research Architect Audit skill free?: Yes. The skill itself is free from mmTheBest/Research-Architect. SkillProof publishes the install command and an independent test verdict at no cost.
Does Research Architect Audit work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 18, 2026. Verdict: Tested · Works. Fed it a flawed draft (causal overclaim from a survey, an unsourced '73%' stat, a near-copied exemplar quote, no methods) in an otherwise empty paper_output; the bundled first_paper_artifact_check.py flagged all 33 missing upstream artifacts and the 13-gate rubric mapped each planted flaw to a named gate. Unlike a plain read that risks a 'looks solid' pass, the mandatory clearance gate refuses completion while evidence is missing, and all three gate scripts run under Python 3.13. Value is real but coupled to the full Research Architect pipeline: a standalone draft gets an audit skeleton plus owner-routing rather than a finished paper.
What is the Research Architect Audit SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Research Architect Audit?: 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 Research Architect Audit 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.