Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add YuanyuanMa03/academic-research-skills --skill sd-parse-resultsgit clone --depth 1 https://github.com/YuanyuanMa03/academic-research-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/sd-parse-results)<a href="https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/sd-parse-results"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/sd-parse-results/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/sd-parse-results"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/sd-parse-results.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.00691 |
| Opus 5.5 | $0.00010 | $0.00276 |
| Sonnet 5.5 | $0.00005 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
sd-parse-results scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parse Current ScienceDirect Results Page
Extract structured data from an already-open ScienceDirect search results page without navigating.
When to use
- After the user has manually navigated to a search results page
- When re-parsing results after sorting or filtering changes
- Called internally by other skills
Steps
Step 1: Extract results from current page
Use evaluate_script (no navigation needed):
() => {
// Verify we are on a search results page
if (!window.location.pathname.includes('/search')) {
return { error: 'Not on a ScienceDirect search results page.' };
}
const items = document.querySelectorAll('li.ResultItem');
if (items.length === 0) {
return { error: 'No results found on the current page. The page may still be loading.' };
}
const papers = [];
for (let i = 0; i < items.length; i++) {
const item = items[i];
const titleLink = item.querySelector('a.result-list-title-link');
const journal = item.querySelector('a.subtype-srctitle-link');
const dateSpans = item.querySelectorAll('.srctitle-date-fields > span');
const date = dateSpans.length > 1 ? dateSpans[dateSpans.length - 1].textContent.trim() : '';
const authors = [...item.querySelectorAll('.Authors .author')].map(a => a.textContent.trim());
const doi = item.getAttribute('data-doi');
const pii = titleLink?.href?.match(/pii\/(\w+)/)?.[1] || '';
const articleType = item.querySelector('.article-type')?.textContent?.trim() || '';
const isOpenAccess = !!item.querySelector('.access-label');
const checkboxId = item.querySelector('.checkbox-input')?.id || '';
papers.push({
rank: i + 1,
title: titleLink?.textContent?.trim() || '',
pii, doi: doi || '',
journal: journal?.textContent?.trim() || '',
date, authors, articleType, openAccess: isOpenAccess,
checkboxId,
});
}
const totalText = document.querySelector('.search-body-results-text')?.textContent?.trim() || '';
const pageInfo = document.querySelector('.Pagination li:first-child')?.textContent?.trim() || '';
const currentUrl = window.location.href;
return { papers, totalResults: totalText, pageInfo, currentUrl };
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 78 lines · 24 tokens per session scan A 1594062b9025
sd-parse-results is a skill published in the GitHub repository YuanyuanMa03/academic-research-skills (75 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 691 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-29.
Other skills, from other repositories
explore-cnki-view
A browser-based CNKI research skill that uses Chrome or computer control to search pages, inspect paper and journal details, extract abstracts and citation information, and download pages after user confirmation.
cnki-exp-search-automation
A browser-based automation tool for CNKI, the China National Knowledge Infrastructure research database, that runs advanced literature searches and collects result lists and abstracts.
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
bigquery-troubleshooting
Provides diagnostic workflows and step-by-step root-cause analysis procedures for actively broken, failing, or slow BigQuery jobs, execution graph and query plan stage bottlenecks, system performance issues, or unexpectedly expensive workloads. Use when interpreting symptoms, isolating bottlenecks, diagnosing cost…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…