Agent skill

Anystyle API

by wentorai in wentorai/research-plugins

Citation reference parser using machine learning. An agent skill from wentorai/research-plugins.

MITAuto-check passedResearch & Science

Install Anystyle API

skills CLI
$ npx skills add wentorai/research-plugins --skill anystyle-api -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install wentorai/research-plugins anystyle-api --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/wentorai/research-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tools/document/anystyle-api .claude/skills/anystyle-api && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
anystyle-api
GitHub stars
298
Used in
1 other repo
Token cost
~2.1k tokens
SKILL.md length
499 words
Files
1
Skills in repo
405
Repo updated
First seen
Licence
MIT

At a glance

Citation reference parser using machine learning. An agent skill from wentorai/research-plugins.

  • Tasks that involve Citation management
  • SKILL.md covers Overview, Authentication, Core Endpoints and Rate Limits, plus 2 more sections
  • Calls curl and gem; reaches anystyle.io
  • Tasks that involve Machine learning

What it does

Anystyle API is an agent skill from wentorai/research-plugins. Citation reference parser using machine learning

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Citation management and Machine learning. The repository describes itself as: 350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents. The licence is MIT.

When your agent uses it

  • Tasks that involve Citation management
  • Tasks that involve Machine learning

Example prompts

  • “/anystyle-api”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit bf44b3c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • gem

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • anystyle.io

    Also links to:

    • github.com
    • rubygems.org
    • citationstyles.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Anystyle API loads about 2.1k tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 499 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wentorai/research-plugins at commit bf44b3c, republished under its MIT licence (© wentorai). 499 words, ~2,098 tokens.

Download SKILL.mdSave it as .claude/skills/anystyle-api/SKILL.md (or your agent's skills folder).
name
anystyle-api
description
Citation reference parser using machine learning

AnyStyle API Guide

Overview

AnyStyle is a fast and smart citation reference parser that uses machine learning (specifically conditional random fields, CRFs) to extract structured bibliographic data from unformatted citation strings. It can parse raw reference text into structured fields such as author, title, journal, volume, pages, year, and DOI, handling the enormous variety of citation formats found in academic literature.

The AnyStyle service provides both a web interface and an API endpoint for programmatic citation parsing. Unlike rule-based parsers that rely on specific citation style templates, AnyStyle uses a trained machine learning model that generalizes across citation formats, making it effective for parsing references from diverse disciplines and publication traditions where citation styles vary widely.

Researchers, librarians, digital humanists, and research software developers use AnyStyle to extract structured references from PDF documents, legacy bibliographies, dissertation reference lists, and scanned documents. It is particularly valuable for building citation networks, enriching bibliographic databases, migrating references between management tools, and processing large volumes of unstructured citation data that would be impractical to parse manually.

Authentication

No authentication required. The AnyStyle web service is freely accessible without any API key, token, or registration. The service can be used via the web interface at https://anystyle.io/ or through its API endpoint. For heavy usage or private deployments, AnyStyle is also available as an open-source Ruby gem that can be installed locally.

Core Endpoints

parse: Parse Citation References

Submit raw citation text and receive structured bibliographic data extracted by the machine learning parser. The endpoint accepts one or more citation strings and returns parsed fields for each reference.

  • URL: POST https://anystyle.io/parse
  • Parameters:
ParameterTypeRequiredDescription
bodystringYesRaw citation text (one reference per line in the POST body)
formatstringNoOutput format: json (default), xml, bib (BibTeX)
  • Example:
bash
# Parse a single citation
curl -X POST "https://anystyle.io/parse" \
  -H "Content-Type: text/plain" \
  -d "Vaswani, A., Shazeer, N., Parmar, N., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998-6008."

# Parse multiple citations (one per line)
curl -X POST "https://anystyle.io/parse" \
  -H "Content-Type: text/plain" \
  -d "Vaswani, A. et al. (2017). Attention is all you need. NeurIPS 30, 5998-6008.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. NeurIPS 25."
  • Response: Returns an array of parsed citation objects, each containing extracted fields:
json
[
  {
    "author": [{"family": "Vaswani", "given": "A."}, {"family": "Shazeer", "given": "N."}],
    "title": ["Attention is all you need"],
    "date": ["2017"],
    "container-title": ["Advances in Neural Information Processing Systems"],
    "volume": ["30"],
    "pages": ["5998-6008"],
    "type": "article-journal"
  }
]

Key response fields include author (array of name objects), title, date, container-title (journal/conference name), volume, issue, pages, doi, url, publisher, location, and type (inferred reference type).

Show full SKILL.md (166 more words)Show less

Rate Limits

No formal rate limits are documented for the AnyStyle web service. However, the service is provided as a free community resource, so users should exercise responsible usage patterns. For high-volume parsing tasks (thousands of citations or more), it is strongly recommended to install the AnyStyle Ruby gem locally:

bash
gem install anystyle

The local installation provides the same parsing capabilities without any network dependencies or rate concerns, and supports batch processing of large reference lists and PDF files directly.

Common Patterns

Parse a Reference List from a Paper

Extract structured data from a raw reference list copied from a PDF:

python
import requests

references = """Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL-HLT, 4171-4186.
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., et al. (2020). Language models are few-shot learners. NeurIPS 33, 1877-1901."""

resp = requests.post(
    "https://anystyle.io/parse",
    headers={"Content-Type": "text/plain"},
    data=references
)

for ref in resp.json():
    authors = ", ".join(
        f"{a.get('family', '')} {a.get('given', '')}" for a in ref.get("author", [])
    )
    title = ref.get("title", [""])[0]
    year = ref.get("date", [""])[0]
    journal = ref.get("container-title", [""])[0]
    print(f"{authors} ({year}). {title}. {journal}")
Batch Process Citations from Multiple Documents

Process reference lists from multiple papers for citation network analysis:

python
import requests

def parse_references(raw_text):
    """Parse raw citation text into structured records."""
    resp = requests.post(
        "https://anystyle.io/parse",
        headers={"Content-Type": "text/plain"},
        data=raw_text
    )
    if resp.status_code == 200:
        return resp.json()
    return []

# Process references from multiple source documents
documents = {
    "paper_A": "Smith, J. (2020). Title A. Journal X, 1, 1-10.\nDoe, J. (2019). Title B. Journal Y, 2, 20-30.",
    "paper_B": "Jones, K. (2021). Title C. Conference Z, 100-110.\nSmith, J. (2020). Title A. Journal X, 1, 1-10."
}

citation_graph = {}
for doc_id, refs in documents.items():
    parsed = parse_references(refs)
    citation_graph[doc_id] = parsed
    print(f"{doc_id}: parsed {len(parsed)} references")
Convert Citations to BibTeX Format

Transform unstructured references into BibTeX entries for use with LaTeX:

python
import requests

citation = "Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press."

resp = requests.post(
    "https://anystyle.io/parse",
    headers={"Content-Type": "text/plain"},
    data=citation
)

parsed = resp.json()[0]
# Build a BibTeX entry from parsed fields
authors = " and ".join(
    f"{a.get('family', '')}, {a.get('given', '')}" for a in parsed.get("author", [])
)
bib_key = parsed.get("author", [{}])[0].get("family", "unknown").lower() + parsed.get("date", ["0000"])[0]

print(f"@book{{{bib_key},")
print(f"  author = {{{authors}}},")
print(f"  title = {{{parsed.get('title', [''])[0]}}},")
print(f"  year = {{{parsed.get('date', [''])[0]}}},")
print(f"  publisher = {{{parsed.get('publisher', [''])[0] if parsed.get('publisher') else 'Unknown'}}}")
print("}")
Local Installation for High-Volume Processing

For large-scale processing, install AnyStyle locally as a Ruby gem:

bash
# Install the gem
gem install anystyle

# Parse references from command line
anystyle parse "Smith, J. (2020). My Paper. Journal, 1, 1-10."

# Parse references from a text file
anystyle parse references.txt --format json > parsed.json

# Parse references directly from a PDF
anystyle find document.pdf --format json > extracted_refs.json

References

© wentorai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/tools/document/anystyle-api of wentorai/research-plugins.

Open the folder on GitHubat commit bf44b3c

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in wentorai/research-plugins, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Anystyle API next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Anystyle API compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Anystyle API this skillwentorai/research-plugins2981 repos~2.1kAutomated safety check: PassMIT
Aistats Related Workbrycewang-stanford/Awesome-Journal-Skills1.2k—~855Automated safety check: PassMIT
Ectj Literature Positioningbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.2kAutomated safety check: PassMIT
Qiskit 2.x Quantum ML Referenceaiming-lab/AutoResearchClaw15k—~4.7kAutomated safety check: PassMIT
Gtars Genomic Interval Toolkitdavila7/claude-code-templates32k12 repos~1.9kAutomated safety check: PassMIT
PyHealth Clinical ML Toolkitdavila7/claude-code-templates32k12 repos~4.4kAutomated safety check: PassMIT

Similar skills

  • Aistats Related Work

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when positioning an AISTATS submission against AI, machine-learning, statistics, and uncertainty literature, including arXiv preprints, workshop versions, concurrent…

    1.2k GitHub stars~855 tokensUpdated 11 days ago
    Research & ScienceAuto-check passed
  • Ectj Literature Positioning

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when positioning a The Econometrics Journal (EctJ) paper against econometric theory, applied econometrics, statistics, and machine-learning literatures while keeping the…

    1.2k GitHub stars~1.2k tokensUpdated 11 days ago
    Research & ScienceAuto-check passed
  • Qiskit 2.x Quantum ML Reference

    aiming-lab/AutoResearchClaw

    Reference patterns for writing qiskit 2.x code for variational quantum machine learning: feature maps, VQC training, VQE for chemistry, MPS circuits and noise models.

    15k GitHub stars~4.7k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed
  • Gtars Genomic Interval Toolkit

    davila7/claude-code-templates

    Works with genomic intervals using gtars, a Rust toolkit with Python bindings: overlap detection, coverage tracks, tokenization for ML models and reference sequences.

    32k GitHub starsUsed in 12 repos~1.9k tokens
    Research & ScienceAuto-check passed
  • PyHealth Clinical ML Toolkit

    davila7/claude-code-templates

    Builds machine learning pipelines on clinical data with PyHealth: EHR datasets, prediction tasks, medical code mapping, healthcare models and evaluation.

    32k GitHub starsUsed in 12 repos~4.4k tokens
    Research & ScienceAuto-check passed
  • Deepchem

    davila7/claude-code-templates

    Molecular machine learning toolkit. An agent skill from davila7/claude-code-templates.

    32k GitHub starsUsed in 11 repos~4.4k tokens
    Research & ScienceAuto-check passed

More from wentorai/research-plugins

All 405 skills in this repo
  • Abstract Writing Guide

    wentorai/research-plugins

    Craft structured research abstracts that maximize clarity and journal acceptance

    298 GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • Academic Citation Manager

    wentorai/research-plugins

    Manage academic citations across BibTeX, APA, MLA, and Chicago formats

    298 GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed
  • Academic Paper Summarizer

    wentorai/research-plugins

    Summarize academic papers with structured extraction of key elements

    298 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Academic Study Methods

    wentorai/research-plugins

    Evidence-based study techniques for academic learning and retention

    298 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Academic Tone Guide

    wentorai/research-plugins

    Adjust writing tone and register for academic audiences and venues

    298 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed
  • Academic Translation Guide

    wentorai/research-plugins

    Academic translation, post-editing, and Chinglish correction guide

    298 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Questions about Anystyle API

What does Anystyle API do?

Citation reference parser using machine learning. An agent skill from wentorai/research-plugins. Anystyle API is an agent skill from wentorai/research-plugins.

When should I use Anystyle API?

Anystyle API fits situations like: tasks that involve Citation management; tasks that involve Machine learning.

How do I install Anystyle API in Claude Code?

Run `npx skills add wentorai/research-plugins --skill anystyle-api -a claude-code`. Or copy the skill folder (skills/tools/document/anystyle-api in wentorai/research-plugins) into .claude/skills/anystyle-api in your project. Claude Code loads it when a task matches its description.

How do I install Anystyle API in Codex?

Run `npx skills add wentorai/research-plugins --skill anystyle-api -a codex`. Or copy the skill folder (skills/tools/document/anystyle-api in wentorai/research-plugins) into .agents/skills/anystyle-api in your project. Codex loads it when a task matches its description.

Can I use Anystyle API in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wentorai/research-plugins --skill anystyle-api -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/anystyle-api, .gemini/skills/anystyle-api, .github/skills/anystyle-api and .opencode/skills/anystyle-api in your project.

What does Anystyle API need to run?

Going by SKILL.md and its folder, Anystyle API needs the command-line tools its instructions call (curl and gem). Our summary lists: Python 3.

Does Anystyle API access the network?

SKILL.md names 4 domains. In commands or code: anystyle.io; the agent is likely to contact it when it follows the instructions. As links in the text: github.com, rubygems.org and citationstyles.org. This is read from the text; nothing was executed.

Is Anystyle API safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Anystyle API use?

Anystyle API is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Anystyle API use?

About 2.1k tokens (SKILL.md is roughly 8.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Anystyle API?

Skills that share tags, products or a category with Anystyle API: Aistats Related Work (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars), Ectj Literature Positioning (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars), Qiskit 2.x Quantum ML Reference (aiming-lab/AutoResearchClaw, 15k stars) and Gtars Genomic Interval Toolkit (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Anystyle API?

wentorai (a GitHub user) maintains it in wentorai/research-plugins, which has 298 GitHub stars. The repository holds 405 skills in this directory. The repository was last updated on June 19, 2026.

Source: wentorai/research-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.