← Back to Skills Marketplace
di5cip1e

Research Assistant

by di5cip1e · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
94
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install director-research-assistant
Description
Conduct web research on any topic, summarize findings, and create structured reports. Use when user wants to (1) research a topic online, (2) get summaries o...
README (SKILL.md)

Research Assistant

Conduct thorough web research and create actionable reports.

Workflow

1. Gather Information

Use web_search (Perplexity) for comprehensive results:

Search query: \x3Ctopic> + "2024" or "latest" for recent info

2. Extract Key Sources

  • Fetch top 3-5 URLs using web_fetch
  • Extract main points from each source
  • Note publication dates and credibility

3. Synthesize Findings

  • Identify common themes
  • Note conflicting information
  • Find statistics and data points

4. Structure Report

Create organized output with:

  1. Executive Summary - 2-3 sentence overview
  2. Key Findings - Numbered list of main discoveries
  3. Details - Expanded explanation of each finding
  4. Sources - Links to references
  5. Next Steps - Recommended actions (if applicable)

Research Types

Competitive Analysis

Focus: Competitor features, pricing, market position
Output: Comparison table + recommendations

Technology Research

Focus: Capabilities, limitations, adoption, alternatives
Output: Technical overview + decision matrix

Market Research

Focus: Size, growth, trends, key players
Output: Statistics + trend analysis

News/Trends

Focus: Recent developments, emerging patterns
Output: Timeline + impact assessment

Best Practices

  • Cite sources - Always include links
  • Date everything - "As of [date]..."
  • Distinguish fact from opinion - Use "reportedly" for unconfirmed
  • Quantify when possible - Numbers > adjectives
  • Flag gaps - Note when information is limited

Output Example

# Research: AI Coding Assistants (April 2026)

## Summary
The AI coding assistant market has matured with 3 dominant players...

## Key Findings
1. GitHub Copilot leads with 2M+ paid subscribers
2. Cursor. AI gained 500K users in 6 months
3. New entrants focus on enterprise compliance

## Sources
- [TechCrunch](link) - March 2026
- [Andreessen Horowitz](link) - February 2026

## Recommendations
- For individuals: Start with free Cursor tier
- For enterprises: Evaluate GitHub Copilot Business
Usage Guidance
This skill appears coherent and low-risk, but check that your agent has the browsing tools (web_search/web_fetch) it assumes. Verify cited sources and dates (agents can hallucinate or misattribute claims), and avoid asking the skill to access paywalled or confidential data—it requests no credentials and should not be used to retrieve protected resources. For sensitive competitive-intelligence tasks, confirm legality and privacy implications before proceeding.
Capability Analysis
Type: OpenClaw Skill Name: director-research-assistant Version: 1.0.0 The skill bundle is a standard research assistant tool designed to perform web searches, fetch content, and generate structured reports. The instructions in SKILL.md are well-structured and align perfectly with the stated purpose, containing no evidence of malicious intent, data exfiltration, or prompt injection attacks.
Capability Assessment
Purpose & Capability
Name/description align with the runtime instructions (gather web sources, synthesize, produce reports). The SKILL.md assumes availability of web_search (Perplexity) and web_fetch tools for live web access; the skill metadata does not declare tool prerequisites, so the skill will fail or behave differently if those agent tools are absent.
Instruction Scope
Instructions stay on-topic: they direct web searches, fetching top URLs, extracting points, citing sources, and producing structured reports. They do not ask the agent to read local files, access unrelated environment variables, modify system configs, or exfiltrate data to external endpoints beyond citing source URLs.
Install Mechanism
No install spec and no code files; lowest-risk model. Nothing is written to disk or fetched during installation.
Credentials
Requires no environment variables, credentials, or config paths. The lack of requested secrets matches the skill's stated function.
Persistence & Privilege
always is false and the skill does not request elevated or permanent privileges. Autonomous invocation is allowed (platform default) but not combined with other risky behaviors.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install director-research-assistant
  3. After installation, invoke the skill by name or use /director-research-assistant
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - web research, summaries, structured reports
Metadata
Slug director-research-assistant
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Research Assistant?

Conduct web research on any topic, summarize findings, and create structured reports. Use when user wants to (1) research a topic online, (2) get summaries o... It is an AI Agent Skill for Claude Code / OpenClaw, with 94 downloads so far.

How do I install Research Assistant?

Run "/install director-research-assistant" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Research Assistant free?

Yes, Research Assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Research Assistant support?

Research Assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Research Assistant?

It is built and maintained by di5cip1e (@di5cip1e); the current version is v1.0.0.

💬 Comments