academic-deep-research
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bloodandeath/keats-deep-researchWhat This Skill Does
Academic Deep Research is a professional-grade research agent designed for complex information synthesis. Unlike standard AI queries, this skill forces a rigid, multi-phase methodology that prevents superficial answers. By leveraging a mandatory 2-cycle research process per theme, it ensures that your inquiries are backed by an evidence hierarchy, addressing contradictions rather than ignoring them. The skill utilizes OpenClaw's native tools, including web_search for breadth, web_fetch for source verification, and sessions_spawn for parallel processing of distinct research threads.
Installation
To integrate this agent into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/bloodandeath/keats-deep-research
Ensure your agent has the required permissions to access web browsing and temporary session storage, as this skill is designed for deep-web data ingestion and iterative analysis.
Use Cases
This skill is built for users requiring high-fidelity information, such as:
- Academic Literature Reviews: Identifying existing consensus and gaps in scholarly discourse.
- Competitive Intelligence: Deeply auditing market participants and long-term industry trends.
- Evidence-Based Reporting: Verifying news, claims, or technical documentation from multiple, verified, and high-authority sources.
- Complex Decision Support: Providing comprehensive briefing documents for non-trivial, multi-factor business or personal decisions.
Example Prompts
- "Perform a deep research cycle on the long-term macroeconomic impacts of universal basic income, specifically looking at studies from the last 5 years."
- "I need an exhaustive comparison of decentralized vs. centralized database architectures for high-frequency financial applications. Use Academic Deep Research."
- "Conduct a literature review on the efficacy of carbon capture technologies; please focus on technical feasibility reports and peer-reviewed journals."
Tips & Limitations
- Patience is Key: This skill enforces three mandatory stop-points to ensure alignment. Do not expect an immediate, single-shot response; it is designed for accuracy over speed.
- Clarity Matters: Because the skill requires you to approve a research plan, the more specific you are in your initial intent, the higher the quality of the resulting report.
- Resource Usage: Given the requirement for two research cycles per theme and high-count web searches, this skill will consume more computational resources and token credits than standard conversational agents.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bloodandeath-keats-deep-research": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, data-collection
Related Skills
design-engineering
Orchestrate iterative design and frontend engineering work through research, planning, sub-agent execution, and validation loops. Use when a visual/UI task requires multiple iterations, when the first implementation needs refinement based on feedback, when choosing between competing technical approaches (Canvas vs SVG vs CSS), or when coordinating sub-agents on design-heavy work. Covers animation architecture decisions, progressive enhancement patterns, performance-aware rendering choices, and the research→plan→execute→validate workflow. Complements frontend-design (which handles aesthetics) by adding engineering discipline, iteration management, and technical decision-making.
agent-cost-monitor
Real-time token usage and cost tracking across all your OpenClaw agents — alerts, budgets, and optimization tips
web-monitor
Monitor web pages for content changes and get alerts. Track URLs, detect updates, view diffs. Use when asked to watch a website, track changes on a page, monitor for new posts/content, set up page change alerts, or check if a site has been updated. Supports CSS selectors for targeted monitoring.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
code-reviewer
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Default behavior is a single-model adversarial review that identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Supports an optional `--dual` mode for heavier cross-model iterative review when deeper scrutiny is worth the added cost and latency. Use when users ask to "critically review my code", "critically review" code or a PR, "critique my code", "find issues in my code", "find issues" in code, ask "what's wrong with this code", ask to "review this code", "critique my PR", say "double review this", or request a "cross-model review". Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required Changes, Suggestions, Noted) and specific, actionable recommendations.