Orkg API

What it does

When your agent uses it

• Tasks that involve Knowledge graphs

Example prompts

• “/orkg-api”

Requirements

• Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Literature surveys: Find existing comparisons to quickly understand a field
2. 2Method selection: Compare methods across papers on structured criteria
3. 3Gap analysis: Identify research problems without solutions
4. 4Reproducibility: Access structured descriptions of experimental setups

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

  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:

  • orkg.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

Orkg API loads about 1.3k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 260 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~19

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

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

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). 260 words, ~1,294 tokens.

name

orkg-api

description

Query the Open Research Knowledge Graph for structured research data

https://orkg.org/api/

# Search papers in ORKG
curl "https://orkg.org/api/papers?q=climate+change+adaptation&size=20"

# Get paper details by ID
curl "https://orkg.org/api/papers/R12345"

# Search any resource (papers, predicates, comparisons)
curl "https://orkg.org/api/resources?q=machine+learning&size=20"

# Filter by class
curl "https://orkg.org/api/resources?q=BERT&exact=false&classes=Paper"

# List comparisons
curl "https://orkg.org/api/comparisons?size=10"

# Get a specific comparison
curl "https://orkg.org/api/comparisons/R54321"

# Search comparisons
curl "https://orkg.org/api/comparisons?q=sentiment+analysis"

# Get contributions of a paper
curl "https://orkg.org/api/papers/R12345/contributions"

# A contribution describes what a paper contributes:
# - Research problem addressed
# - Method used
# - Results achieved
# - Materials/datasets used

import requests

BASE_URL = "https://orkg.org/api"

def search_orkg_papers(query: str, size: int = 20) -> list:
    """Search papers in the Open Research Knowledge Graph."""
    resp = requests.get(f"{BASE_URL}/papers", params={"q": query, "size": size})
    resp.raise_for_status()
    data = resp.json()

    papers = []
    for item in data.get("content", []):
        papers.append({
            "id": item.get("id"),
            "title": item.get("title"),
            "created": item.get("created_at"),
            "contributions": item.get("contributions", [])
        })
    return papers

def get_paper_contributions(paper_id: str) -> dict:
    """Get structured research contributions for a paper."""
    resp = requests.get(f"{BASE_URL}/papers/{paper_id}/contributions")
    resp.raise_for_status()
    return resp.json()

def search_comparisons(topic: str) -> list:
    """Find structured paper comparisons on a topic."""
    resp = requests.get(f"{BASE_URL}/comparisons", params={"q": topic, "size": 10})
    resp.raise_for_status()
    return resp.json().get("content", [])

# Example usage
papers = search_orkg_papers("transfer learning NLP")
for p in papers:
    print(f"[{p['id']}] {p['title']}")

comparisons = search_comparisons("named entity recognition")
for c in comparisons:
    print(f"Comparison: {c.get('title')} ({len(c.get('contributions', []))} papers)")

© 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/literature/metadata/orkg-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.

• brycewang-stanford/Auto-Empirical-Research-Skillsskills/43-wentorai-research-plugins/skills/literature/metadata/orkg-api