← Back to Skills Marketplace
408
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install paper-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 p...
README (SKILL.md)
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.mdto produce a structured fact sheet. - Load and execute prompt in
references/round2.mdusing 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 paperorInsufficient 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\r
Usage Guidance
This skill is internally consistent and only needs the PDF you upload plus the included prompt files. Before using it, consider: (1) do not upload confidential or unpublished manuscripts you don't want processed by the agent or potentially retained in logs; (2) the skill intentionally forbids external sources, but model behavior may still leak background knowledge—verify outputs against the PDF evidence tags; (3) the second pass requests a long (2000–3000 Chinese-word) critique—ensure you actually want that length. If you need the skill to never run autonomously, disable autonomous invocation in your agent settings.
Capability Analysis
Type: OpenClaw Skill
Name: paper-pdf-two-pass-review
Version: 1.0.0
The OpenClaw skill bundle is designed for a two-pass PDF analysis workflow, focusing on fact extraction and critical review. All instructions for the AI agent across `SKILL.md`, `references/round1.md`, and `references/round2.md` consistently include strong guardrails, such as 'use only the uploaded PDF', 'do not use external knowledge', and 'record facts only, no judgments'. There are no indications of malicious intent, data exfiltration, unauthorized command execution, or prompt injection attempts to subvert the agent. The garbled text in `agents/openai.yaml` appears to be an encoding issue or placeholder, not a security risk.
Capability Assessment
Purpose & Capability
Name/description match the actual behavior: it analyzes uploaded CVPR PDFs via two local prompt files. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
Runtime instructions are narrowly scoped to (1) confirm an uploaded PDF in the chat, (2) run the two local prompts to extract facts and produce a critique, and (3) restrict outputs to PDF evidence. The skill does not instruct reading unrelated files, accessing env vars, or contacting external endpoints.
Install Mechanism
This is an instruction-only skill with no install spec and no code files to execute; nothing is written to disk or downloaded during install.
Credentials
No environment variables, credentials, or config paths are requested. The declared inputs align with the paper-analysis purpose.
Persistence & Privilege
always is false and there is no request to modify other skills or system-wide settings. disable-model-invocation is default (false), which is normal for skills and not, by itself, a concern.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install paper-pdf-two-pass-review - After installation, invoke the skill by name or use
/paper-pdf-two-pass-review - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the cvpr-pdf-two-pass-review skill.
- Implements a strict two-pass analysis workflow for CVPR paper PDFs: first extracting verifiable facts with evidence references, then generating a detailed Chinese research critique based solely on those facts.
- Enforces clear evidence tagging ([Evidence: p.X, Sec.Y, Fig/Table Z]) for all major claims.
- Clearly identifies missing or insufficient information from the paper.
- Designed to minimize unsupported claims and hallucination by separating fact extraction from critique writing.
- Supports reproducibility assessment, deep interpretation, and PhD-level reading notes based on PDF content only.
Metadata
Frequently Asked Questions
What is PaperRead-Skills?
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... It is an AI Agent Skill for Claude Code / OpenClaw, with 408 downloads so far.
How do I install PaperRead-Skills?
Run "/install paper-pdf-two-pass-review" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is PaperRead-Skills free?
Yes, PaperRead-Skills is completely free (open-source). You can download, install and use it at no cost.
Which platforms does PaperRead-Skills support?
PaperRead-Skills is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created PaperRead-Skills?
It is built and maintained by GPIOX (@gpiox); the current version is v1.0.0.
More Skills