Agent skill

active-research

Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Enhanced with advanced browser automation — SPA handling, network idle wait, batch operations, stealth browsing, and intelligent page analysis. Use when user asks to research, analyze, investigate, deep-dive, or generate a report on any subject.

Actionbook1,582★ · +2/wk · 1 repos on radarProfile →
claude-codeApache-2.0
Install
npx skills add actionbook/actionbook --skill active-research --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 32 KB
Bundled scripts: none
Path: skills/active-research/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,584 · +2 this week
Language: Rust
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the 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-dismiss-dialogs` — auto-handle alert/confirm/prompt | | Load speed | `--block-images` — skip images for faster text extraction | | Page stability | `--no-animations` — freeze CSS transitions | | Error detection | `console --level error` — check for page issues | | Multi-step forms | `batch` — execute multiple actions in one call | | Element debugging | `info <selector>` — inspect visibility, position, properties | | Change tracking | `snapshot --diff` — only see what changed | | Anti-detection | `--stealth` + `fingerprint rotate` for protected sites | | Auth management | `storage set` — inject JWT/tok

What's inside
Steps it walks through
  1. Enhanced Browser Capabilities
  2. Usage
  3. Parameters
  4. Topic Detection
  5. Architecture
  6. MUST USE Actionbook CLI
  7. Browser Flags — Research Defaults
  8. Navigation Pattern — ALWAYS Follow
  9. Complete Workflow
  10. Step 1: Plan Search Strategy
  11. Step 2: Query Actionbook API for Selectors (ALWAYS DO THIS FIRST)
  12. Step 3: arXiv Search (URL-First, Form as Backup)
  13. Step 4: Supplement with Google / Bing Search
  14. Step 5: Deep Read Sources
Commands it runs
actionbook --block-images --rewrite-urls browser fetch "<url>" --format text --json
For interactive multi-step workflows, use explicit open:
actionbook --block-images --auto-dismiss-dialogs --no-animations --rewrite-urls browser open "<url>"
actionbook --block-images --auto-dismiss-dialogs --no-animations --stealth --rewrite-urls browser open "<url>"
Single command: navigate → wait (domain-aware) → extract → close
For static pages (Wikipedia, docs, blogs), add --lite to skip browser entirely:
actionbook --rewrite-urls browser fetch "<url>" --format text --lite --json
For accessibility tree:
actionbook --block-images --rewrite-urls browser fetch "<url>" --format snapshot --max-tokens 2000 --json
Step 1: Navigate
More from actionbook
All skills →
actionbook-web-testRun browser-based web tests against websites using Actionbook CLI. Activate when the user wants to…Testing & QAextractExtract structured data from websites and produce an executable Playwright script plus extracted…Testing & QAjson-uijson-ui, json render, component catalog, report render, HTML report, I18nString, i18n, bilingual…Frontenddeep-researchDeep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper…OtheractionbookBrowser action engine. Provides up-to-date action manuals for the modern web — operate any website…Testing & QAagent-browserAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use…Testing & QA
About this skill
What does the active-research skill do?

Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Enhanced with advanced browser automation — SPA handling, network idle wait, batch operations, stealth browsing, and intelligent page analysis. Use when user asks to research, analyze, investigate, deep-dive, or generate a report on any subject.

How do I install it?

Run `npx skills add actionbook/actionbook --skill active-research --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From actionbook/actionbook, a repository with 1,584 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.