Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rongarede/claude-skills-research --skill semantic-scholargit clone --depth 1 https://github.com/rongarede/claude-skills-researchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rongarede/claude-skills-research/semantic-scholar)<a href="https://agentmods.dev/skills/rongarede/claude-skills-research/semantic-scholar"><img src="https://agentmods.dev/badge/skills/rongarede/claude-skills-research/semantic-scholar/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rongarede/claude-skills-research/semantic-scholar"><img src="https://agentmods.dev/badge/skills/rongarede/claude-skills-research/semantic-scholar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.02671 |
| Opus 5.5 | $0.00037 | $0.01068 |
| Sonnet 5.5 | $0.00019 | $0.00534 |
| Haiku 4.5 | $0.00009 | $0.00267 |
Grade A, and why
semantic-scholar scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Scholar 论文检索与验证
概述
基于 Semantic Scholar Academic Graph API 的论文检索工具,支持:
- 并发搜索:同时查询多个关键词
- 批量验证:通过 DOI / ArXiv ID / S2 ID 批量查询论文详情
- 引用分析:获取引用数、被引论文
- 开放获取:识别 OA 论文和 PDF 链接
覆盖 214M+ 学术论文,免费无需注册。
执行步骤
- 确认搜索意图:用户提供关键词、DOI 或论文 ID
- 选择搜索模式:单关键词搜索、多关键词并发搜索、批量 ID 查询
- 执行搜索脚本
search_papers.py,获取结果 JSON - 如需摘要补全,执行
batch_abstract.py批量获取缺失摘要 - 如需格式化输出,执行
export_md.py生成 Markdown 报告 - 返回结果给用户,附带论文数量和关键统计
约束
- 禁止在无用户确认的情况下自动清除缓存(
--clear-cache) - 禁止将 API Key 硬编码到脚本或 commit 中
- 不可绕过速率限制器直接发请求
- 批量查询每批不可超过 500 篇(API 限制)
- 缓存 TTL 固定 3600s,不可在运行时修改
使用场景
- 按关键词检索论文标题、作者、年份
- 验证论文是否存在及其元数据是否正确
- 批量查询一组 DOI 对应的论文信息
- 与 OpenAlex 交叉验证检索结果
- 查找某领域高引论文
快速开始
依赖安装
pip install aiohttp
API Key 配置(可选)
无 Key 可用(1 req/s),配置 Key 后提升至 10 req/s。三种配置方式:
# 方式 1:交互式配置(推荐,保存到配置文件)
python $SCRIPTS/search_papers.py --setup
# 方式 2:环境变量
export S2_API_KEY="your-key-here"
# 方式 3:手动写入配置文件
# ~/.config/semantic-scholar/config.json
# {"api_key": "your-key-here"}
Key 解析优先级:--api-key 参数 → S2_API_KEY 环境变量 → 配置文件
支持两种 Key:
- 官方 Key:申请地址 https://www.semanticscholar.org/product/api#api-key-form
- ai4scholar.net 代理 Key:以
sk-user-开头,自动路由到 ai4scholar.net
CLI 用法
SCRIPTS=~/.claude/skills/semantic-scholar/scripts
# 单关键词搜索
python $SCRIPTS/search_papers.py "blockchain consensus"
# 并发多关键词搜索
python $SCRIPTS/search_papers.py "HotStuff BFT" "DAG consensus" "PBFT protocol"
# 按 DOI 批量查询
python $SCRIPTS/search_papers.py --ids "DOI:10.1145/3293611.3331591" "ARXIV:1803.05069"
# 年份 + 引用数过滤
python $SCRIPTS/search_papers.py "consensus algorithm" --year "2020-" --min-cite 50
# 输出到 JSON
python $SCRIPTS/search_papers.py "BFT consensus" -n 20 -o results.json
# 跳过缓存(强制重新请求)
python $SCRIPTS/search_papers.py "HotStuff" --no-cache
# 清除所有缓存
python $SCRIPTS/search_papers.py --clear-cache
Python API 用法
import asyncio
from scripts.s2_client import S2Client
async def main():
client = S2Client() # 或 S2Client(api_key="your-key")
# 单次搜索
result = await client.search("blockchain consensus", limit=5)
for p in result["data"]:
print(f"{p['title']} ({p['year']}) - 引用: {p['citationCount']}")
# 并发搜索多个关键词
queries = ["HotStuff BFT", "DAG consensus", "PBFT protocol"]
results = await client.search_concurrent(queries, limit=5)
for q, r in results.items():
print(f"\n== {q} ({r['total']} 条) ==")
for p in r["data"]:
print(f" {p['title']}")
# 批量 ID 查询
papers = await client.batch_papers([
"DOI:10.1145/3293611.3331591",
"ARXIV:1803.05069",
])
for p in papers:
if p:
print(f"{p['title']} ({p['year']})")
await client.close()
asyncio.run(main())
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 284 lines · 93 tokens per session scan A 9691427102f0
semantic-scholar is a skill published in the GitHub repository rongarede/claude-skills-research (4 stars, last pushed 7mo ago), licensed MIT. It adds 93 tokens to every session and 2,671 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
semantic-scholar compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| semantic-scholarrongarede/claude-skills-research | Skill | 4 | 7mo ago | MIT | A | 93 | Claude Code |
| paper-skillcLin-c/paper-skill | Skill | 141 | 12d ago | MIT | A | 122 | Codex |
| latex-fmtCalix-L/awesome-latex-skills | Skill | 185 | 1mo ago | MIT | A | 43 | Codex |
| latex-rescueCalix-L/awesome-latex-skills | Skill | 185 | 1mo ago | MIT | A | 41 | Codex |
| pdf2texCalix-L/awesome-latex-skills | Skill | 185 | 1mo ago | MIT | A | 46 | Codex |
| research-expertpersonamanagmentlayer/pcl | Skill | 44 | 13d ago | Apache-2.0 | A | 50 | Claude Code |
| latex-polishCalix-L/awesome-latex-skills | Skill | 185 | 1mo ago | MIT | A | 45 | Codex |