active-research

Active Research provides automated web research and analysis capabilities. It generates HTML reports by navigating websites, handling dynamic SPA content, and extracting information using the Actionbook browser CLI.

1.7K
Installs
5
Use cases
5/10
Quality

Is active-research safe to install?

Review the source first

Review the source first: our audit of active-research's source files found 10 shell commands, 3 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands via the Actionbook CLI and performs network requests to arbitrary URLs. It also reads and writes local files for report generation.

How we audit skills: our security review methodology.

Who is this skill for?

Users requiring automated research, deep-dive analysis, or report generation on specific topics, academic papers, or technical domains.

What can you do with it?

  • Researching academic papers via arXiv
  • Generating comprehensive HTML reports on technical topics
  • Extracting content from dynamic, SPA-based websites
  • Performing multi-step web navigation and form interaction
  • Tracking changes on web pages

How good is this skill?

Quality score: 5/10. The documentation is highly technical and provides clear, actionable instructions for browser automation. It includes specific flags and workflows to ensure reliable data extraction.

What does the skill file contain?

SKILL.md
# Active Research

Analyze any topic, domain, or paper and generate a beautiful HTML report using **Actionbook Browser** — featuring SPA-aware navigation, network idle detection, batch operations, and intelligent page analysis.

## Enhanced Browser Capabilities

| Capability | Description |
|------------|-------------|
| Page load wait | `wait-idle` — monitors fetch/XHR until network settles |
| SPA content | `wait-fn` — wait for JS conditions before extracting |
| Page understanding | `snapshot --filter interactive --max-tokens N` — focused, budget-friendly |
| Popups blocking | `--auto-dismi...

Frequently asked questions

How does the skill handle dynamic content?

It uses the 'wait-idle' command to monitor network activity until requests settle and 'wait-fn' to wait for specific JavaScript conditions before extracting content.

Can I use standard tools like curl or wget?

No. The skill strictly forbids the use of curl, wget, python requests, or other HTTP libraries. It requires the use of 'actionbook browser' commands.

How should I handle dead links during research?

The skill instructs users to verify page status using 'wait-fn' to check for 404 titles. If a page is dead, the skill advises skipping it immediately without retrying.

What is the preferred method for academic research?

The skill recommends using URL-based searches for arXiv rather than form submission, as URL-based methods are more reliable.

Data sourced from actionbook/actionbook on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills

lark-workflow-meeting-summary

219.7K

Users who need to summarize meeting minutes, generate weekly reports, or review meeting history within the Lark ecosystem

The lark-workflow-meeting-summary skill provides a structured workflow for agents to aggregate meeting minutes from Lark VC, generate summaries, and create or update reports in Lark Docs.

highlarkmeeting-summarylarksuite

programmatic-seo

83.5K

Content strategists, SEO specialists, and marketers building large-scale, data-driven website content

The programmatic-seo skill provides a framework for generating SEO-optimized pages at scale using templates and data. It guides users through keyword research, data sourcing, template design, internal linking, and indexation strategies while emphasizing content uniqueness to avoid search engine penalties.

lowseomarketingcoreyhaines31

ad-creative

64.0K

Performance marketers, growth teams, and advertisers who need to produce ad copy at scale or optimize existing ad creative

The ad-creative skill generates, iterates, and scales ad copy for paid advertising platforms including Google, Meta, LinkedIn, TikTok, and Twitter. It provides frameworks for creating ad headlines, descriptions, and primary text based on product context and performance data.

highmarketingadvertisingcoreyhaines31

customer-research

46.7K

Product marketers, founders, and researchers who need to ground their strategy in customer data

The customer-research skill provides a framework for analyzing existing research assets and gathering new insights from online communities to inform product marketing, messaging, and persona development.

lowresearchmarketingcoreyhaines31