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 | $0.00046 | $0.01336 |
| Sonnet 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 12d 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.
- 12d 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 (2 stars, last pushed 5mo ago), licensed MIT. It adds 93 tokens to every session and 2,671 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
package-author
A packaging guide for turning scripts, skills, or an MCP service into a standard plugin package. MCP is a way for an AI assistant to connect to external tools.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.