Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

paper-analyze — measured AI agent skill | DecimalAI

xiangyue-zhang/paper-analyze

NewSkillScoreMaintained

Deep analysis of a single paper with figure extraction from arXiv source

researchby xiangyue-zhang

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

decimalai skills pull xiangyue-zhang-paper-analyze

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/xiangyue-zhang-paper-analyze/SKILL.md

Raw file: /s/xiangyue-zhang-paper-analyze/SKILL.md ↗ · machine-readable summary at /s/xiangyue-zhang-paper-analyze.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4h ago

—-33% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-73%	0%
case-10	✗→✓	▲ Improved	-50%	0%
case-11	✗→✓	▲ Improved	-31%	0%
case-13	✗→✓	▲ Improved	-31%	0%
case-14	✗→✓	▲ Improved	-57%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

xiangyue-zhang / auto-deep-researcher-24x7

skills/paper-analyze/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

paper-analyze

Perform deep analysis of a single academic paper.

Usage

Claude Code: /paper-analyze <arxiv_id or url>
Codex: $paper-analyze

Behavior

Fetch paper metadata from arXiv API
Attempt to download arXiv source package (.tar.gz)
Extract actual figures from source (not screenshots)
Read the full paper (PDF if source unavailable)
Generate structured analysis

Figure Extraction

Priority order:

arXiv source package → extract .png/.jpg/.pdf figures
PDF extraction as fallback
Name files with arxiv_id prefix to avoid collisions

Output Format

markdown
# [Paper Title]

**arXiv**: [id] | **Authors**: ... | **Year**: ...

## Problem
What specific problem does this paper address?

## Motivation  
Why is this problem important? What gap exists?

## Method
Detailed technical approach with key equations/algorithms.

![Figure 1](figures/arxiv_id_fig1.png)

## Experiments
- Datasets, baselines, metrics
- Key results table
- Ablation findings

## Insights
- What can we learn and apply?
- Strengths and limitations
- Connections to our research

Want to see if xiangyue-zhang/paper-analyze would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.