PaperRead-Skills
VerifiedAnalyze uploaded CVPR paper PDFs with a strict two-pass workflow. First pass extracts verifiable facts with page/section/figure/table evidence only. Second p...
Install
Claude Code
Add to .claude/skills/ About This Skill
--- name: cvpr-pdf-two-pass-review description: Analyze uploaded CVPR paper PDFs with a strict two-pass workflow. First pass extracts verifiable facts with page/section/figure/table evidence only. Second pass produces a 2000-3000 Chinese research critique grounded in those facts. Use when the user uploads a paper PDF and asks for deep interpretation, critical review, reproducibility assessment, or PhD-level reading notes. ---
# CVPR PDF Two-Pass Review
Overview
Run a deterministic two-pass paper analysis workflow on an uploaded PDF. Prioritize evidence-grounded outputs and reduce hallucinations by separating fact extraction from interpretation.
Workflow
- Confirm the user has uploaded the PDF in the current chat. If not, ask them to upload it first.
- Load and execute prompt in `references/round1.md` to produce a structured fact sheet.
- Load and execute prompt in `references/round2.md` using only round-1 facts plus PDF evidence.
- Enforce evidence tags for core claims: `[Evidence: p.X, Sec.Y, Fig/Table Z]`.
- If any required information is missing, explicitly state `Not provided in paper` or `Insufficient evidence`.
Output Rules
- Keep analysis strictly based on uploaded PDF content.
- Do not introduce external papers, benchmarks, or assumptions unless user explicitly asks.
- Keep language concise and technical.
- Preserve required length in pass 2: 2000-3000 words or characters as requested by the prompt.
References
- Round 1 prompt: `references/round1.md`
- Round 2 prompt: `references/round2.md`
Use Cases
- Analyze CVPR paper PDFs with a structured two-pass review separating fact extraction from interpretation
- Extract verifiable claims with page, section, figure, and table evidence citations
- Generate 2000-3000 word Chinese research critiques grounded in extracted facts
- Assess reproducibility and methodological rigor of uploaded conference papers
- Produce PhD-level reading notes with evidence-tagged core claims
Pros & Cons
Pros
- + Two-pass design reduces hallucination by grounding interpretation in previously extracted facts
- + Strict evidence tagging requirement ensures every claim is traceable to the source PDF
- + Explicitly marks missing information rather than fabricating plausible-sounding content
Cons
- - Primarily designed for CVPR papers — may need adaptation for other venues or fields
- - Second-pass output is in Chinese only, limiting usefulness for non-Chinese speakers
Frequently Asked Questions
What does PaperRead-Skills do?
Analyze uploaded CVPR paper PDFs with a strict two-pass workflow. First pass extracts verifiable facts with page/section/figure/table evidence only. Second p...
What platforms support PaperRead-Skills?
PaperRead-Skills is available on Claude Code, OpenClaw.
What are the use cases for PaperRead-Skills?
Analyze CVPR paper PDFs with a structured two-pass review separating fact extraction from interpretation. Extract verifiable claims with page, section, figure, and table evidence citations. Generate 2000-3000 word Chinese research critiques grounded in extracted facts.
Stay Updated on Agent Skills
Get weekly curated skills + safety alerts