pubmed-search by yorkeccak/scientific-skills
npx skills add https://github.com/yorkeccak/scientific-skills --skill pubmed-search使用由 Valyu 语义搜索 API 驱动的自然语言查询,搜索完整的 PubMed 生物医学文献数据库。
本文档中的 scripts/search 命令是相对于此技能的安装目录而言的。
在运行任何命令之前,请使用以下命令定位脚本:
PUBMED_SCRIPT=$(find ~/.claude/plugins/cache -name "search" -path "*/pubmed-search/*/scripts/*" -type f 2>/dev/null | head -1)
然后对所有命令使用完整路径:
$PUBMED_SCRIPT "CRISPR gene editing" 15
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
当您运行搜索并收到 "setup_required": true 时,请遵循此流程:
向用户询问其 API 密钥: "要搜索 PubMed,我需要您的 Valyu API 密钥。请在 https://platform.valyu.ai 免费获取(10 美元额度)"
一旦用户提供了密钥,运行:
scripts/search setup <api-key>
重试原始搜索。
User: Search PubMed for CAR-T cell therapy advances
→ Response: {"success": false, "setup_required": true, ...}
→ Claude asks: "Please provide your Valyu API key from https://platform.valyu.ai"
→ User: "val_abc123..."
→ Claude runs: scripts/search setup val_abc123...
→ Response: {"success": true, "type": "setup", ...}
→ Claude retries: scripts/search "CAR-T cell therapy advances" 10
→ Success!
scripts/search "your natural language query" [maxResults]
# Search for recent COVID-19 research
scripts/search "COVID-19 vaccine efficacy studies" 15
# Find papers on a specific gene
scripts/search "BRCA1 mutations and breast cancer risk" 20
# Search for treatment approaches
scripts/search "immunotherapy for melanoma clinical trials" 10
# Drug mechanism research
scripts/search "mechanism of action of metformin in type 2 diabetes" 12
scripts/search setup <api-key>
{
"success": true,
"type": "pubmed_search",
"query": "CRISPR gene editing",
"result_count": 10,
"results": [
{
"title": "Article Title",
"url": "https://pubmed.ncbi.nlm.nih.gov/...",
"content": "Full article text with figures...",
"source": "pubmed",
"relevance_score": 0.95,
"images": ["https://example.com/figure1.jpg"]
}
],
"cost": 0.025
}
# Get article titles
scripts/search "query" 10 | jq -r '.results[].title'
# Get URLs
scripts/search "query" 10 | jq -r '.results[].url'
# Extract full content
scripts/search "query" 10 | jq -r '.results[].content'
# Find all papers on a topic
scripts/search "mechanisms of aging in humans" 50
# Search for drug targets
scripts/search "novel targets for Alzheimer's disease treatment" 20
# Find clinical trial results
scripts/search "phase 3 trials for rheumatoid arthritis biologics" 15
# Research gene function
scripts/search "role of TP53 in cancer development" 25
所有命令都返回带有 success 字段的 JSON:
{
"success": false,
"error": "Error message"
}
退出代码:
0 - 成功1 - 错误(检查 JSON 获取详情)https://api.valyu.ai/v1/searchscripts/
├── search # Bash wrapper
└── search.mjs # Node.js CLI
使用 Node.js 内置的 fetch() 直接进行 API 调用,零外部依赖。
如果您正在构建一个 AI 项目,并希望将 PubMed 搜索直接集成到您的应用程序中,请使用 Valyu SDK:
from valyu import Valyu
client = Valyu(api_key="your-api-key")
response = client.search(
query="immunotherapy for melanoma",
included_sources=["valyu/valyu-pubmed"],
max_results=20
)
for result in response["results"]:
print(f"Title: {result['title']}")
print(f"URL: {result['url']}")
print(f"Content: {result['content'][:500]}...")
import { Valyu } from "valyu-js";
const client = new Valyu("your-api-key");
const response = await client.search({
query: "immunotherapy for melanoma",
includedSources: ["valyu/valyu-pubmed"],
maxResults: 20
});
response.results.forEach((result) => {
console.log(`Title: ${result.title}`);
console.log(`URL: ${result.url}`);
console.log(`Content: ${result.content.substring(0, 500)}...`);
});
有关完整的集成示例和 SDK 参考,请参阅 Valyu 文档。
每周安装量
219
仓库
GitHub 星标数
25
首次出现
2026年1月21日
安全审计
安装于
opencode196
cursor191
codex190
gemini-cli187
github-copilot180
amp167
Search the complete PubMed database of biomedical literature using natural language queries powered by Valyu's semantic search API.
The scripts/search commands in this documentation are relative to this skill's installation directory.
Before running any command, locate the script using:
PUBMED_SCRIPT=$(find ~/.claude/plugins/cache -name "search" -path "*/pubmed-search/*/scripts/*" -type f 2>/dev/null | head -1)
Then use the full path for all commands:
$PUBMED_SCRIPT "CRISPR gene editing" 15
When you run a search and receive "setup_required": true, follow this flow:
Ask the user for their API key: "To search PubMed, I need your Valyu API key. Get one free ($10 credits) at https://platform.valyu.ai"
Once the user provides the key, run:
scripts/search setup <api-key>
Retry the original search.
User: Search PubMed for CAR-T cell therapy advances
→ Response: {"success": false, "setup_required": true, ...}
→ Claude asks: "Please provide your Valyu API key from https://platform.valyu.ai"
→ User: "val_abc123..."
→ Claude runs: scripts/search setup val_abc123...
→ Response: {"success": true, "type": "setup", ...}
→ Claude retries: scripts/search "CAR-T cell therapy advances" 10
→ Success!
scripts/search "your natural language query" [maxResults]
# Search for recent COVID-19 research
scripts/search "COVID-19 vaccine efficacy studies" 15
# Find papers on a specific gene
scripts/search "BRCA1 mutations and breast cancer risk" 20
# Search for treatment approaches
scripts/search "immunotherapy for melanoma clinical trials" 10
# Drug mechanism research
scripts/search "mechanism of action of metformin in type 2 diabetes" 12
scripts/search setup <api-key>
{
"success": true,
"type": "pubmed_search",
"query": "CRISPR gene editing",
"result_count": 10,
"results": [
{
"title": "Article Title",
"url": "https://pubmed.ncbi.nlm.nih.gov/...",
"content": "Full article text with figures...",
"source": "pubmed",
"relevance_score": 0.95,
"images": ["https://example.com/figure1.jpg"]
}
],
"cost": 0.025
}
# Get article titles
scripts/search "query" 10 | jq -r '.results[].title'
# Get URLs
scripts/search "query" 10 | jq -r '.results[].url'
# Extract full content
scripts/search "query" 10 | jq -r '.results[].content'
# Find all papers on a topic
scripts/search "mechanisms of aging in humans" 50
# Search for drug targets
scripts/search "novel targets for Alzheimer's disease treatment" 20
# Find clinical trial results
scripts/search "phase 3 trials for rheumatoid arthritis biologics" 15
# Research gene function
scripts/search "role of TP53 in cancer development" 25
All commands return JSON with success field:
{
"success": false,
"error": "Error message"
}
Exit codes:
0 - Success1 - Error (check JSON for details)https://api.valyu.ai/v1/searchscripts/
├── search # Bash wrapper
└── search.mjs # Node.js CLI
Direct API calls using Node.js built-in fetch(), zero external dependencies.
If you're building an AI project and want to integrate PubMed search directly into your application, use the Valyu SDK:
from valyu import Valyu
client = Valyu(api_key="your-api-key")
response = client.search(
query="immunotherapy for melanoma",
included_sources=["valyu/valyu-pubmed"],
max_results=20
)
for result in response["results"]:
print(f"Title: {result['title']}")
print(f"URL: {result['url']}")
print(f"Content: {result['content'][:500]}...")
import { Valyu } from "valyu-js";
const client = new Valyu("your-api-key");
const response = await client.search({
query: "immunotherapy for melanoma",
includedSources: ["valyu/valyu-pubmed"],
maxResults: 20
});
response.results.forEach((result) => {
console.log(`Title: ${result.title}`);
console.log(`URL: ${result.url}`);
console.log(`Content: ${result.content.substring(0, 500)}...`);
});
See the Valyu docs for full integration examples and SDK reference.
Weekly Installs
219
Repository
GitHub Stars
25
First Seen
Jan 21, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykFail
Installed on
opencode196
cursor191
codex190
gemini-cli187
github-copilot180
amp167
飞书OpenAPI Explorer:探索和调用未封装的飞书原生API接口
23,400 周安装