zhihaoairobotic/clawphd/ai-review

Claude Code and agent skill by zhihaoairobotic/clawphd

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

AI paper reviewer. Use when the user says 'review my paper', 'help me review this paper', '审稿', 'give me feedback on my paper', 'check my manuscript', 'evaluate this paper for NeurIPS/ICLR/EuroSys'. Accepts PDF files and produces structured narrative reviews with venue-specific dimensional scores and Accept/Reject recommendation.

Install

npx vskill@latest install zhihaoairobotic/clawphd/ai-review

SKILL.md

When to use

  • "Review my paper at /path/to/paper.pdf"
  • "Help me prepare my NeurIPS submission — review this draft"
  • "给我审一下这篇论文"
  • "Check if this paper is ready for ICLR submission"
  • "Give me peer-review style feedback on this manuscript"
  • "Evaluate this paper for EuroSys, tell me the scores"

Tool

paper_review(pdf_path, venue="NeurIPS", mode="sot", num_reflections=1)

Parameters

ParameterTypeRequiredDescription
pdf_pathstringyesAbsolute path to the paper PDF
venuestringnoTarget conference: NeurIPS / ICLR / ICML / EuroSys / OSDI / SOSP / CVPR / ICCV / General (default: General)
modestringnosot = Strength-of-Thought multi-pass (default, highest quality); pure = single-pass (faster); vlm = send page images to vision model (evaluates figures/typesetting)
num_reflectionsintegernoSelf-reflection iterations (default: 1)

Return value

json
{
  "status": "ok",
  "output_path": "/home/user/.clawphd/workspace/outputs/paper_review/my_paper/review.md",
  "venue": "NeurIPS",
  "decision": "Accept",
  "overall_score": 7,
  "scores": {
    "Originality": 3,
    "Quality": 3,
    "Clarity": 4,
    "Significance": 3,
    "Soundness": 3,
    "Presentation": 4,
    "Contribution": 3,
    "overall": 7,
    "confidence": 4,
    "decision": "Accept",
    "score_rationale": "Solid contribution with strong experiments and clear presentation, minor novelty concerns."
  },
  "warnings": []
}

Scoring rubric

Scores follow real conference review forms:

VenueDimensionsOverall scale
NeurIPS / ICLR / ICMLOriginality, Quality, Clarity, Significance, Soundness, Presentation, Contribution (each 1–4)1–10
EuroSys / OSDI / SOSPNovelty, Systems_Contribution, Evaluation_Rigor, Clarity (each 1–4)1–10
CVPR / ICCVTechnical_Novelty, Soundness, Experiments, Presentation, Impact (each 1–4)1–6

Rubric source: SakanaAI/AI-Scientist (12.5k stars) — NeurIPS official review form.

Example conversation

User: 帮我把这篇论文按照 NeurIPS 标准审一下：/home/user/papers/my_draft.pdf

Agent: [calls paper_review with pdf_path="/home/user/papers/my_draft.pdf", venue="NeurIPS", mode="sot"] → Review saved to ~/.clawphd/workspace/outputs/paper_review/my_draft/review.md → Decision: Accept | Overall: 7/10 → Originality: 3/4 | Soundness: 3/4 | Contribution: 3/4

Output layout

outputs/paper_review/<paper_stem>/
├── review.md    # narrative review (6 sections) + score table
└── meta.json    # venue, mode, scores, elapsed time

review.md structure

# Paper Review: <title>
> Venue: NeurIPS | Mode: sot | Generated: 2026-03-22
 
## Synopsis
## Summary of Review
## Strengths
## Weaknesses
## Suggestions for Improvement
## References
 
---
 
## Scores (NeurIPS)
| Dimension | Score |
...
**Decision: Accept**

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/zhihaoairobotic/clawphd/ai-review/badge)](https://verified-skill.com/skills/zhihaoairobotic/clawphd/ai-review)

Something wrong with this skill or its page? Tell us.