用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills --skill figshare-api命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
中英双语学术降 AIGC / bilingual academic de-AIGC skill. Removes AI-generated writing signatures from empirical papers in economics, management, and the social sciences — in both English and Chinese. Covers Turnitin AI, GPTZero, Originality.ai on the English side and 知网 AMLC, 万方, 维普 on the Chinese side. Uses a six-step loop (intake → audit → claim-evidence check → differentiated rewrite → five-dimension self-score → cold-reader recheck) with two pattern libraries (22 English + 17 Chinese patterns), section-by-section strategies for empirical papers, and hard protections that keep every number, coefficient, and citation intact.
Use when a research task needs reproducible Kaggle discovery, metadata inspection, bounded public-data downloads, competition or kernel discovery, model discovery, or an explicitly approved Kaggle write/delete operation through the official CLI.
基于 SOC 职业分类
正在显示 SKILL.md
| name | figshare-api |
| description | Research data sharing and repository |
| metadata | {"openclaw":{"emoji":"🔍","category":"research","subcategory":"funding","keywords":["open data","data sharing","data archiving","FAIR data principles","open source code"],"source":"https://docs.figshare.com/","requires":{"env":["FIGSHARE_API_TOKEN"]}}} |
Figshare is a cloud-based research data management platform that allows researchers to store, share, and discover research outputs including datasets, figures, media, papers, posters, and fileset collections. Every item uploaded to Figshare receives a citable DOI and is stored in a FAIR-compliant manner, making research outputs findable, accessible, interoperable, and reusable.
The Figshare API provides comprehensive programmatic access to the repository, enabling researchers and institutions to automate data publishing, integrate with research workflows, and build custom discovery interfaces. The platform supports versioning, embargo periods, and flexible access controls for both public and private research data.
Researchers, data managers, institutional repository administrators, and research infrastructure developers use the Figshare API to automate deposit workflows, harvest metadata for institutional dashboards, build data discovery tools, and integrate research data management into existing laboratory information management systems. Figshare serves over 150 institutions worldwide and hosts millions of research outputs.
Authentication via personal access token is required for write operations and accessing private content. Read access to public content is available without authentication but has lower rate limits.
Authorization headercurl -H "Authorization: token YOUR_FIGSHARE_TOKEN" "https://api.figshare.com/v2/account/articles"
Public endpoints can be accessed without a token for browsing published content.
Search the public Figshare repository for published articles (datasets, figures, papers, media, and other item types).
GET https://api.figshare.com/v2/articles| Parameter | Type | Required | Description |
|---|---|---|---|
| search_for | string | No | Free-text search query |
| item_type | int | No | Item type filter (1=figure, 2=media, 3=dataset, etc.) |
| published_since | string | No | Filter by date (YYYY-MM-DD format) |
| order | string | No | Sort: published_date, modified_date, views |
| order_direction | string | No | asc or desc |
| page | int | No | Page number (default 1) |
| page_size | int | No | Results per page (default 10, max 1000) |
curl -X POST "https://api.figshare.com/v2/articles/search" \
-H "Content-Type: application/json" \
-d '{"search_for": "genomics CRISPR", "item_type": 3, "page_size": 5}'
id, title, doi, url, published_date, description, defined_type_name, categories, tags, authors, files (with download URLs), and citation.Retrieve and manage dataset-specific content in Figshare. Datasets are a specialized article type with additional support for large file collections.
GET https://api.figshare.com/v2/articles/{article_id}| Parameter | Type | Required | Description |
|---|---|---|---|
| article_id | int | Yes | The Figshare article/dataset ID |
# Get a specific dataset by ID
curl "https://api.figshare.com/v2/articles/12345678"
# List files in a dataset
curl "https://api.figshare.com/v2/articles/12345678/files"
id, title, doi, description, authors, categories, tags, files (array with name, size, download_url, computed_md5), license, version, is_embargoed, and custom_fields.Rate limits vary based on authentication status and endpoint. Authenticated requests generally allow up to 100 requests per minute. Unauthenticated requests are limited to approximately 10 requests per minute. The API returns HTTP 429 with a Retry-After header when limits are exceeded. For bulk data harvesting, Figshare provides OAI-PMH endpoints at https://api.figshare.com/v2/oai which are more suitable for large-scale metadata collection.
Find publicly available datasets matching specific research topics:
import requests
payload = {
"search_for": "single cell RNA-seq",
"item_type": 3, # datasets only
"page_size": 20,
"order": "published_date",
"order_direction": "desc"
}
resp = requests.post("https://api.figshare.com/v2/articles/search", json=payload)
results = resp.json()
for item in results:
print(f"{item['title']}")
print(f" DOI: {item['doi']}")
print(f" Published: {item['published_date']}")
print()
Automate data deposit for reproducible research workflows:
import requests
TOKEN = os.environ["FIGSHARE_API_TOKEN"]
headers = {"Authorization": f"token {TOKEN}", "Content-Type": "application/json"}
# Step 1: Create a new article
article_data = {
"title": "Supplementary Data for Analysis of Gene Expression",
"defined_type": "dataset",
"description": "RNA-seq counts and metadata for the analysis.",
"tags": ["RNA-seq", "gene expression"],
"categories": [69] # Genetics category
}
resp = requests.post("https://api.figshare.com/v2/account/articles",
headers=headers, json=article_data)
article_url = resp.json()["location"]
# Step 2: Upload file
article = requests.get(article_url, headers=headers).json()
print(f"Created article ID: {article['id']}, DOI will be assigned on publish")
Collect metadata from all Figshare items in an institution's repository:
curl "https://api.figshare.com/v2/oai?verb=ListRecords&metadataPrefix=oai_dc&set=institution_123"