Is the Evidence Review skill free?

Yes. The skill itself is free from yha9806/academic-writing-toolkit. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Evidence Review 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 Evidence Review?

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 Evidence Review 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.

Evidence Review

Keeps literature-review claims traceable to evidence status so adjacent-domain data can't masquerade as validation.

by yha9806 · yha9806/academic-writing-toolkit

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 992ba91

Ran a 3-source mental-health-chatbot review task both ways: the baseline blurred an RCT, a bare abstract, and an unpublished thesis into one 'validated tool' claim, while the skill-driven run tagged each source's evidence status, refused to let the abstract/thesis support the clinical claim, and logged the missing engagement-to-outcome link as an open gap instead of inferring it.

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 Evidence Review does

Guides drafting of evidence-controlled literature reviews and gap maps: classifies every source by evidence status (full-text, abstract-only, unpublished, candidate-only), builds claim registers and citation-role plans, and runs overclaim audits before assembly. Triggers on review-paper, thesis literature review, scoping review, gap-map, and overclaim-audit requests.

How to install Evidence Review

git clone https://github.com/yha9806/academic-writing-toolkit
mkdir -p ~/.claude/skills
cp -r academic-writing-toolkit/.claude/skills/evidence-review ~/.claude/skills/evidence-review

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

Commands — how to trigger Evidence Review

/evidence-review Keeps literature-review claims traceable to evidence status so adjacent-domain data can't masquerade as validation.

It also activates on plain-language prompts like these:

Draft the literature review chapter, avoid overclaiming from sources.
Build a gap map and claim register for my scoping review.
Separate the full-text sources from abstract-only ones in my draft.

Frequently asked questions

Is the Evidence Review skill free?: Yes. The skill itself is free from yha9806/academic-writing-toolkit. SkillProof publishes the install command and an independent test verdict at no cost.
Does Evidence Review work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Ran a 3-source mental-health-chatbot review task both ways: the baseline blurred an RCT, a bare abstract, and an unpublished thesis into one 'validated tool' claim, while the skill-driven run tagged each source's evidence status, refused to let the abstract/thesis support the clinical claim, and logged the missing engagement-to-outcome link as an open gap instead of inferring it.
What is the Evidence Review 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 Evidence Review?: 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 Evidence Review 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.