H Index Guide

What it does

When your agent uses it

• Tasks that involve Academic paper search

Example prompts

• “/h-index-guide”

Requirements

• Python 3

Workflow steps

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

1. 1Field dependence: Average citation rates vary dramatically across disciplines. An h-index of 20 is excellent in mathematics but modest in…
2. 2Career stage bias: The h-index monotonically increases over time. Always compare within career stage (m-quotient helps).
3. 3Self-citation: Some databases include self-citations in h-index calculation.
4. 4Database coverage: Google Scholar, Scopus, and Web of Science yield different h-index values for the same author.
5. 5Gaming: Metrics can be inflated through citation cartels, salami slicing, and excessive self-citation.

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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  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:

  • api.openalex.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

H Index Guide loads about 1.6k tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 463 words of instructions outside code blocks.

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

~17

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

~1.6k

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). 463 words, ~1,573 tokens.

name

h-index-guide

description

Understanding and calculating research impact metrics

def calculate_h_index(citation_counts):
    """Calculate h-index from a list of citation counts."""
    sorted_counts = sorted(citation_counts, reverse=True)
    h = 0
    for i, count in enumerate(sorted_counts):
        if count >= i + 1:
            h = i + 1
        else:
            break
    return h

# Example
citations = [120, 80, 55, 40, 22, 18, 15, 12, 10, 8, 5, 3, 2, 2, 1, 1, 0, 0, 0, 0]
print(f"h-index: {calculate_h_index(citations)}")  # Output: 10

def calculate_g_index(citation_counts):
    """Calculate g-index from citation counts."""
    sorted_counts = sorted(citation_counts, reverse=True)
    cumulative = 0
    g = 0
    for i, count in enumerate(sorted_counts):
        cumulative += count
        if cumulative >= (i + 1) ** 2:
            g = i + 1
    return g

def calculate_i10_index(citation_counts):
    """Calculate i10-index."""
    return sum(1 for c in citation_counts if c >= 10)

print(f"g-index: {calculate_g_index(citations)}")    # Output: 19
print(f"i10-index: {calculate_i10_index(citations)}") # Output: 10

JIF(Y) = (Citations in Y to articles published in Y-1 and Y-2)
         / (Number of citable items published in Y-1 and Y-2)

import requests

# Using the OpenAlex API to get journal/source information
journal_name = "Nature"
response = requests.get(
    "https://api.openalex.org/sources",
    params={"filter": f"display_name.search:{journal_name}", "per_page": 5}
)
results = response.json()["results"]
for source in results:
    print(f"Name: {source['display_name']}")
    print(f"  ISSN: {source.get('issn_l', 'N/A')}")
    print(f"  Works count: {source.get('works_count', 'N/A')}")
    print(f"  Cited by count: {source.get('cited_by_count', 'N/A')}")
    print(f"  h-index: {source.get('summary_stats', {}).get('h_index', 'N/A')}")
    print(f"  2-year mean citedness: {source.get('summary_stats', {}).get('2yr_mean_citedness', 'N/A')}")

# OpenAlex provides h-index directly in author profiles
author_name = "Geoffrey Hinton"
response = requests.get(
    "https://api.openalex.org/authors",
    params={"filter": f"display_name.search:{author_name}", "per_page": 1}
)
author = response.json()["results"][0]
print(f"h-index: {author['summary_stats']['h_index']}")
print(f"i10-index: {author['summary_stats']['i10_index']}")
print(f"2-year mean citedness: {author['summary_stats']['2yr_mean_citedness']}")

© 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/h-index-guide 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/h-index-guide