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 nber-working-papers-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。
正在显示 SKILL.md
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
| name | nber-working-papers-api |
| description | Access NBER working papers and economic research datasets |
| metadata | {"openclaw":{"emoji":"📈","category":"domains","subcategory":"economics","keywords":["NBER","working papers","economics research","macroeconomics","economic policy","recession dating"],"source":"https://www.nber.org/"}} |
The National Bureau of Economic Research (NBER) is the leading U.S. economics research organization, publishing 1,200+ working papers annually by top economists. NBER papers are among the most cited in economics. The website provides structured JSON API access to working papers and macroeconomic datasets. Free metadata access; some full text requires subscription.
API last verified: 2026-04-23. RSS feeds (
/papers.rss) and the old query-param API (?q=...without/searchpath) are defunct. Use the endpoints below.
Base URL: https://www.nber.org/api/v1/working_page_listing/contentType/working_paper
# Search working papers (returns JSON)
curl "https://www.nber.org/api/v1/working_page_listing/contentType/working_paper/_/_/search?page=1&perPage=20&q=inflation+expectations"
# Get new-this-week papers (omit q for all recent)
curl "https://www.nber.org/api/v1/working_page_listing/contentType/working_paper/_/_/search?page=1&perPage=20&newThisWeek=true"
# Find a specific paper by number
curl "https://www.nber.org/api/v1/working_page_listing/contentType/working_paper/_/_/search?page=1&perPage=1&q=w33000"
Program names go in the URL path (use + for spaces), replacing the two _/_ placeholders:
# Labor Studies papers
curl "https://www.nber.org/api/v1/working_page_listing/contentType/working_paper/programs/Labor+Studies/search?page=1&perPage=20"
# Labor Studies + keyword search
curl "https://www.nber.org/api/v1/working_page_listing/contentType/working_paper/programs/Labor+Studies/search?page=1&perPage=20&q=minimum+wage"
# Economic Fluctuations and Growth
curl "https://www.nber.org/api/v1/working_page_listing/contentType/working_paper/programs/Economic+Fluctuations+and+Growth/search?page=1&perPage=20"
{
"totalResults": 11711,
"results": [
{
"title": "Paper Title",
"authors": ["<a href=\"/people/john_doe\">John Doe</a>"],
"displaydate": "March 2025",
"abstract": "First ~300 chars of abstract...",
"url": "/papers/w33000",
"nid": "767372",
"type": "working_paper",
"displaytypename": "Working Paper",
"newthisweek": false,
"certifiedrandom": false
}
],
"facets":
...
...
...
...
Note on authors field: Values contain HTML anchor tags. Strip tags to get plain names:
import re
plain = re.sub(r'<[^>]+>', '', author_html)
For richer metadata on a single paper, parse <meta> tags from the paper page:
curl -sL "https://www.nber.org/papers/w33000" | grep 'citation_'
# citation_title, citation_author, citation_doi, citation_publication_date,
# citation_technical_report_number, citation_pdf_url
# Business cycle dates (JSON, works directly)
curl "https://data.nber.org/data/cycles/business_cycle_dates.json"
# Returns: [{"peak": "2020-02-01", "trough": "2020-04-01"}, ...]
# CPS labor data extracts: https://data.nber.org/cps/
# Macrohistory database: https://data.nber.org/
| Program Name (use in API path) | Focus |
|---|---|
Economic Fluctuations and Growth | Macro, business cycles |
Labor Studies | Employment, wages |
Industrial Organization | Markets, competition |
Public Economics | Taxation, spending |
Economics of Health | Healthcare markets |
Development Economics | Developing countries |
International Finance and Macroeconomics | Exchange rates, capital flows |
International Trade and Investment | Trade policy |
Monetary Economics | Central banking |
Corporate Finance | Firm finance |
Asset Pricing | Financial markets |
Economics of Education | Education economics |
Economics of Aging | Demographics |
Children and Families | Child welfare |
Law and Economics | Legal institutions |
Environment and Energy Economics | Environmental policy |
Political Economy | Political institutions |
import re
import requests
SEARCH_BASE = (
"https://www.nber.org/api/v1/working_page_listing"
"/contentType/working_paper"
)
def _strip_html(text: str) -> str:
"""Remove HTML tags from a string."""
return re.sub(r'<[^>]+>', '', text)
def _extract_paper_number(url: str) -> str:
"""Extract paper number from URL like /papers/w33000."""
return url.rsplit("/", 1)[-1] if url else ""
def search_papers(query: str = "", program: str = "",
page: int = 1, per_page: int = 20,
new_this_week: bool = False) -> dict:
"""Search NBER working papers.
Args:
query: Search keywords (optional).
program: Full program name, e.g. "Labor Studies" (optional).
page: Page number (1-indexed).
per_page: Results per page (max ~100).
new_this_week: If True, return only new-this-week papers.
Returns:
Dict with 'total' count and 'papers' list.
"""
if program:
url = f"{SEARCH_BASE}/programs/{program}/search"
:
url =
params = {: page, : per_page}
query:
params[] = query
new_this_week:
params[] =
resp = requests.get(url, params=params, timeout=)
resp.raise_for_status()
data = resp.json()
papers = []
item data.get(, []):
number = _extract_paper_number(item.get(, ))
papers.append({
: item.get(, ),
: [_strip_html(a) a item.get(, [])],
: number,
: item.get(, ),
: item.get() ,
: number ,
: item.get(, ),
: item.get(, ),
})
{: data.get(, ), : papers}
() -> :
resp = requests.get(
, timeout=
)
resp.raise_for_status()
meta = {}
re.finditer(
, resp.text
):
key, val = .group(), .group()
key == :
meta.setdefault(, []).append(val)
:
meta[key] = val
meta
() -> :
resp = requests.get(
,
timeout=,
)
resp.raise_for_status()
resp.json()
results = search_papers()
()
p results[][:]:
()
()
new = search_papers(new_this_week=, per_page=)
p new[]:
()
labor = search_papers(query=, program=, per_page=)
p labor[]:
()
meta = get_paper_metadata()
()
()
()
cycles = get_business_cycle_dates()
c cycles[-:]:
()
| Dataset | Description |
|---|---|
| Business Cycle Dates | Official US recession start/end dates |
| CPS Extracts | Current Population Survey labor data |
| Macrohistory Database | 150 years of macro indicators |
| Patent Data | Patent citation and classification |
| Trade Data | Bilateral trade statistics |