Is the Paper Reading Zh skill free?

Yes. The skill itself is free from MrGeDiao/paper-reading-zh. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Paper Reading Zh SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Paper Reading Zh?

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 Paper Reading Zh 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.

Paper Reading Zh

Disciplined Chinese deep-reading workflow for papers, with anti-hallucination guardrails.

by MrGeDiao · MrGeDiao/paper-reading-zh

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 17a7403

Forces a hard 150-character single-paragraph summary and labels every unverified venue/CCF/code claim as '未核验' instead of guessing — a real anti-hallucination discipline most freeform paper summaries skip.

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 8/10
Docs & honesty 5/5

What Paper Reading Zh does

Structures a Chinese-language deep read of a paper (PDF, arXiv/OpenReview/ACM/IEEE link, title, or figure screenshot) into a fixed skeleton: keywords, one-paragraph summary, core contributions, method, experiments, critique. Triggers on deep-read/reproduction/comparison/evidence-audit intent tied to a paper anchor; explicitly refuses plain translation, term lookups, or BibTeX-only requests. Enforces a four-tier claim/evidence/inference/uncertain split and requires unverifiable external facts (venue, CCF rank, code links) be labeled '未核验' rather than guessed.

How to install Paper Reading Zh

git clone https://github.com/MrGeDiao/paper-reading-zh
cd paper-reading-zh
mkdir -p ~/.claude/skills
cp -r paper-reading-zh ~/.claude/skills/paper-reading-zh

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

Commands — how to trigger Paper Reading Zh

/paper-reading-zh Disciplined Chinese deep-reading workflow for papers, with anti-hallucination guardrails.

It also activates on plain-language prompts like these:

请帮我深度精读这篇论文的PDF全文,梳理关键词、核心贡献、研究方法和实验设计,并标注哪些细节尚未核验
我上传了一篇arXiv论文的截图和链接,请帮我做逐段深度精读,给出批判性评述和四级证据分级,不要直接翻译
帮我复现并比较这篇会议论文的方法部分和实验结果,区分哪些是事实、哪些是推断、哪些还不确定

Frequently asked questions

Is the Paper Reading Zh skill free?: Yes. The skill itself is free from MrGeDiao/paper-reading-zh. SkillProof publishes the install command and an independent test verdict at no cost.
Does Paper Reading Zh work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Forces a hard 150-character single-paragraph summary and labels every unverified venue/CCF/code claim as '未核验' instead of guessing — a real anti-hallucination discipline most freeform paper summaries skip.
What is the Paper Reading Zh SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Paper Reading Zh?: 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 Paper Reading Zh 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.