A browser workflow for searching ScienceDirect, a website that hosts academic papers, by keywords. It uses the current ScienceDirect website or institutional access address.

Use it to find academic papers on ScienceDirect by keyword.

It removes the need to construct search URLs and manually run the same paper search in a browser.

sd-search — Skill for Claude Code by YuanyuanMa03

Install

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.

Any agent

npx skills add YuanyuanMa03/academic-research-skills --skill sd-search

Clone the repo

git clone --depth 1 https://github.com/YuanyuanMa03/academic-research-skills

Made for: Claude Code.

Or install sd-search, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/sd-search/github.svg)](https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/sd-search)

Your own site

<a href="https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/sd-search"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/sd-search/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yuanyuanma03/academic-research-skills/sd-search"><img src="https://agentmods.dev/badge/skills/yuanyuanma03/academic-research-skills/sd-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,459 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00028	$0.01459
Opus 5.5	$0.00011	$0.00584
Sonnet 5.5	$0.00006	$0.00292
Haiku 4.5	$0.00003	$0.00146

Measured today against content hash 975cfaa87dea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sd-search 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.

plugins/sd-search/skills/sd-search/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ScienceDirect Basic Search

Search for academic papers on ScienceDirect using Chrome DevTools MCP.

Important: Determine the ScienceDirect base URL

Before the first operation, check the current browser page URL to determine which ScienceDirect domain the user is accessing. Store it as BASE_URL. Common patterns:

Direct access: https://www.sciencedirect.com
Institutional proxy: URL containing sciencedirect in the hostname (e.g. WebVPN or EZProxy)

Use whatever origin the user's browser is currently on. If no ScienceDirect page is open, ask the user which URL to use.

Steps

Step 1: Navigate to search results

Use navigate_page to go to:

{BASE_URL}/search?qs={QUERY}&show=25

Where {QUERY} is the URL-encoded search keywords from $ARGUMENTS.

Important: Always include initScript to prevent bot detection:

initScript: "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})"

Step 2: Check access

After navigation, verify the page loaded correctly:

If the page shows "Are you a robot" or captcha: auto-click the Cloudflare Turnstile checkbox using the procedure below. If auto-click fails after 2 attempts, tell the user "请在浏览器中完成验证后告知我。"
If the URL no longer contains sciencedirect or search, the user may have been redirected to a login/authentication page. Tell the user: "页面被重定向，请在浏览器中完成登录或认证后告知我。" Then wait.
Otherwise, proceed.

Cloudflare Turnstile auto-click procedure

When a captcha page is detected (title "请稍候…" or body contains "Are you a robot"):

Wait for the Turnstile iframe to load — use evaluate_script to poll for #captcha-box (up to 8s).
Take a snapshot — use take_snapshot to get the a11y tree. The checkbox is inside a cross-origin iframe but Chrome DevTools MCP can see it:
```
Iframe "包含 Cloudflare 安全质询的小组件"
  checkbox "确认您是真人"   ← target uid
```
Click the checkbox — use click(uid) on the checkbox element.
Wait and verify — wait 3-5s, then check if document.contentType changed or the page URL changed (indicating success). If still on captcha, retry once or fall back to asking the user.

Read the full file on GitHub · 150 lines

Changes

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 · 150 lines · 28 tokens per session scan A 975cfaa87dea

Subscribe to this mod's changes

sd-search is a skill published in the GitHub repository YuanyuanMa03/academic-research-skills (75 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,459 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.

Browser automation Research cnki codex google google-scholar paper

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.

SepineTam/cnki-mcp · 79 tokens

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.

Drchronx/ai-agent-research-starter-kit · 54 tokens

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…

google/skills · 83 tokens

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…

google/skills · 140 tokens

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.

google/skills · 60 tokens

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…

google/skills · 85 tokens