Install
$ agentstack add skill-vivy-yi-awesome-skills-paper-collector ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Paper Collector
Collects academic papers about AI Agent Skills and saves them to papers/.
Workflow
1. Search for Relevant Papers
# Search arXiv for skill-related papers
curl -s "https://export.arxiv.org/api/query?search_query=ti:agent+skill+OR+ti:tool+agent+OR+ti:agent+framework&start=0&max_results=20&sortBy=submittedDate&sortOrder=descending" | \
python3 (.*?)', xml, re.DOTALL)
papers = []
for entry in entries:
title = re.search(r'(.*?)', entry, re.DOTALL)
summary = re.search(r'(.*?)', entry, re.DOTALL)
link = re.search(r'(.*?)', entry)
published = re.search(r'(.*?)', entry)
if title and link:
title_clean = ' '.join(title.group(1).split())
summary_clean = ' '.join(summary.group(1).split())[:300] if summary else ""
link_url = link.group(1)
date = published.group(1)[:10] if published else ""
papers.append({
'title': title_clean,
'summary': summary_clean,
'url': link_url,
'date': date
})
print(f"Found {len(papers)} recent papers:\n")
for p in papers[:10]:
print(f"[{p['date']}] {p['title']}")
print(f" {p['summary'][:150]}...")
print()
PYEOF
2. Also Search Google Scholar / Semantic Scholar
# Search Semantic Scholar API (free, no auth needed)
curl -s "https://api.semanticscholar.org/graph/v1/paper/search?query=agent+skill+framework&limit=20&fields=title,abstract,year,citationCount,openAccessPdf,authors" | \
python3 "papers/paper-slug.md" **arXiv**: [arXiv:XXXX.XXXXX](https://arxiv.org/abs/XXXX.XXXXX)
> **年份**:2024
> **引用数**:XX
> **作者**:Author 1, Author 2
---
## 摘要
Paper abstract here...
## 核心贡献
1. Contribution 1
2. Contribution 2
## 方法
[Key methods described]
## 与 Skills 相关性
[How this relates to AI Agent Skills]
## 参考资料
- [arXiv](https://arxiv.org/abs/XXXX.XXXXX)
- [PDF](https://arxiv.org/pdf/XXXX.XXXXX.pdf)
EOF
4. Add to papers/README.md if exists
# Update papers README if it exists
cd /Volumes/waku/github-维护/awesome/awesome-skills-repos/papers
if [ -f README.md ]; then
echo "- [Paper Title](paper-slug.md) - YYYY-MM-DD" >> README.md
fi
5. Push to GitHub
cd /Volumes/waku/github-维护/awesome/awesome-skills-repos
git add papers/
git commit -m "Add: Paper Title (YYYY-MM)"
git push
Relevant Paper Topics
- Skill discovery and selection
- Skill composition and orchestration
- Skill security and trust
- LLM tool use / function calling
- Agent frameworks and architectures
- Prompt engineering for agents
- Skill distillation and transfer
- Multi-agent collaboration
Target: 2-4 papers per month
Focus on papers that:
- Introduce new Skill concepts or frameworks
- Analyze Skill effectiveness
- Address Skill security/safety
- Present skill-related datasets
Notes
- Always cite the original arXiv/paper URL
- Include why the paper is relevant to Skills
- Use Semantic Scholar for citation counts
- Check if open access PDF is available
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: vivy-yi
- Source: vivy-yi/awesome-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.