brycewang-stanford
brycewang-stanford/Auto-Empirical-Research-Skills
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 onecite-reference-guide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 | onecite-reference-guide |
| description | AI toolkit to parse, complete, and format academic references |
| metadata | {"openclaw":{"emoji":"📌","category":"writing","subcategory":"citation","keywords":["OneCite","reference formatting","citation parser","BibTeX","metadata completion","MCP"],"source":"https://github.com/HzaCode/OneCite"}} |
OneCite is an AI-powered toolkit for parsing, completing, and formatting academic references. Given incomplete or messy citation strings, it extracts structured metadata, fills in missing fields via API lookups (CrossRef, OpenAlex), and outputs clean formatted references in any style (APA, MLA, BibTeX, Chicago). Available as a Python library and MCP server for agent integration.
# Python package
pip install onecite
# MCP server
npx @onecite/mcp-server
from onecite import parse_reference
# Parse messy reference string
ref = parse_reference(
"Vaswani et al. Attention Is All You Need. "
"NeurIPS 2017. arXiv:1706.03762"
)
print(ref.title) # "Attention Is All You Need"
print(ref.authors) # ["Vaswani, A.", "Shazeer, N.", ...]
print(ref.year) # 2017
print(ref.venue) # "NeurIPS"
print(ref.arxiv_id) # "1706.03762"
print(ref.doi) # "10.48550/arXiv.1706.03762"
from onecite import complete_reference
# Fill in missing metadata from APIs
ref = complete_reference(
title="Attention Is All You Need",
# Automatically looks up: DOI, authors, venue,
# abstract, citation count, pages, volume
)
print(f"DOI: {ref.doi}")
print(f"Authors: {', '.join(ref.authors)}")
print(f"Pages: {ref.pages}")
print(f"Volume: {ref.volume}")
print(f"Citations: {ref.citation_count}")
from onecite import format_reference, parse_reference
ref = parse_reference(
"B. Kerbl et al., '3D Gaussian Splatting for Real-Time "
"Radiance Field Rendering,' SIGGRAPH 2023"
)
# Output in different styles
print(format_reference(ref, style="apa"))
# Kerbl, B., Kopanas, G., Leimkühler, T., & Drettakis, G.
# (2023). 3D Gaussian Splatting for Real-Time Radiance Field
# Rendering. ACM SIGGRAPH 2023.
print(format_reference(ref, style="bibtex"))
# @inproceedings{kerbl2023,
# title = {3D Gaussian Splatting...},
# author = {Kerbl, Bernhard and ...},
# booktitle = {ACM SIGGRAPH 2023},
# year = {2023}
# }
print(format_reference(ref, style="mla"))
print(format_reference(ref, style="chicago"))
print(format_reference(ref, style="ieee"))
from onecite import process_references
# Process a list of raw reference strings
raw_refs = [
"Vaswani et al. Attention Is All You Need. NeurIPS 2017",
"Devlin et al. BERT. NAACL 2019",
"Brown et al. Language Models are Few-Shot Learners. 2020",
]
results = process_references(
raw_refs,
complete=True, # Fill missing metadata
format="bibtex", # Output format
deduplicate=True, # Remove duplicates
)
# Save as .bib file
with open("references.bib", "w") as f:
for ref in results:
f.write(ref.formatted + "\n\n")
{
"mcpServers": {
"onecite": {
"command": "npx",
"args": ["@onecite/mcp-server"],
"tools": [
"parse_reference",
"complete_reference",
"format_reference",
"search_paper",
"get_bibtex"
]
}
}
}
from onecite import validate_references
# Check a .bib file for issues
issues = validate_references("references.bib")
for issue in issues:
print(f"[{issue.severity}] {issue.entry}: {issue.message}")
# [WARNING] smith2023: Missing DOI
# [ERROR] jones2024: Author field empty
# [INFO] chen2022: Title case inconsistency