← 返回 Skills 市场

Clawie Research Agent

Name: Clawie Research Agent
Author: mrcalifornian

作者 mrcalifornian · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

305

总下载

当前安装

版本数

在 OpenClaw 中安装

/install clawie-research

功能描述

Deep research on any topic with structured report generation. Use when: (1) user asks for research, analysis, or investigation, (2) need competitive analysis...

使用说明 (SKILL.md)

Research Agent

Conduct deep research and generate structured reports.

Workflow

1. Scope Definition

Clarify the research question
Identify key aspects to investigate
Set boundaries (time, depth, focus areas)

2. Multi-Source Research

Gather data from diverse sources:

# Web search (DuckDuckGo)
curl -s "https://api.duckduckgo.com/?q=QUERY&format=json" | jq '.RelatedTopics[:5]'

# GitHub (repos, stars, activity)
gh search repos "TOPIC" --limit 20 --json name,description,stargazersCount,url

# News/Tech (Hacker News, TechCrunch)
curl -s "https://hacker-news.firebaseio.com/v0/topstories.json" | jq '.[:10]'

# NPM packages
npm search PACKAGE --json 2>/dev/null | jq '.[0:5]'

3. Analysis & Synthesis

Cross-reference findings across sources
Identify patterns, trends, gaps
Extract key statistics and quotes
Note contradictions or debates

4. Report Generation

Use the standard report structure from references/report-template.md.

Report Structure

Every research report follows this format:

# [Topic] Research Report

**Date:** YYYY-MM-DD
**Researcher:** Clawie (AI Research Agent)
**Sources:** X sources analyzed

---

## Executive Summary
[2-3 paragraph overview with key findings]

## Key Findings

### Finding 1: [Title]
[Evidence, data, sources]

### Finding 2: [Title]
[Evidence, data, sources]

## Market/Technology Landscape
[Competitors, alternatives, ecosystem]

## Trends & Predictions
[Where things are heading]

## Gaps & Opportunities
[What's missing, underserved areas]

## Recommendations
[Actionable next steps]

## Sources
[Numbered list of all sources with URLs]

## Methodology
[Brief note on research approach]

Quality Standards

Minimum sources: 20+ for comprehensive reports
Citations: Every claim backed by source
Objectivity: Present multiple perspectives
Actionability: End with clear recommendations

Quick Commands

# Check trending GitHub repos for a topic
gh search repos "ai agent" --sort stars --limit 30 --json name,description,stargazersCount,url,updatedAt

# Get recent articles from a domain
curl -sL "https://DOMAIN.com/feed" | grep -oP '\x3Ctitle>.*\x3C/title>' | head -20

# Check npm package popularity
npm view PACKAGE version time.created time.modified

Tips

Start broad, then narrow down
Verify claims across multiple sources
Prioritize primary sources (official docs, papers) over secondary (blogs, news)
Note publication dates for recency
Flag uncertain or unverified information

安全使用建议

This skill looks like a legitimate research/reporting tool, but before installing: (1) confirm whether you have the CLIs it expects (gh, npm, curl, jq) and whether you want the skill to run them; (2) understand that gh/npm may read local credentials (e.g., GH_TOKEN, GitHub CLI config) — the skill's manifest does not declare this; (3) ask the publisher for a homepage/source and an explicit list of runtime dependencies and network endpoints; (4) if you proceed, run it in a sandbox or environment without sensitive credentials, or create least-privilege/read-only tokens; (5) if you need higher assurance, audit scripts/research.py locally to ensure it only performs the expected searches and doesn't transmit collected data to unknown endpoints.

功能分析

Type: OpenClaw Skill Name: clawie-research Version: 1.0.0 The skill bundle provides legitimate research capabilities using standard tools like the GitHub CLI, NPM, and public APIs (DuckDuckGo, Hacker News). The Python helper script (scripts/research.py) and instructions in SKILL.md are well-structured and align with the stated purpose of generating research reports without any evidence of malicious intent, data exfiltration, or unauthorized access.

能力评估

ℹ Purpose & Capability

The skill's stated purpose (deep research, structured reports) matches the included instructions and helper script. However the registry metadata lists no required binaries or credentials while the SKILL.md and scripts clearly rely on external CLIs (gh, npm, curl, jq) and network access — these runtime dependencies are not declared in the manifest.

⚠ Instruction Scope

The SKILL.md instructs the agent to run network queries (DuckDuckGo API, Hacker News, RSS feeds) and local CLI commands (gh, npm, curl, jq). While expected for research, these commands can read or use locally-stored credentials (e.g., GitHub CLI config or GH_TOKEN) and will make outbound requests to arbitrary domains. The instructions do not acknowledge or constrain use of local credentials or sensitive files.

✓ Install Mechanism

This is an instruction-only skill with no install spec, so nothing is automatically downloaded or written by the registry installer. The included Python helper is present but not installed automatically.

⚠ Credentials

The skill declares no required environment variables or primary credential, yet it invokes tools (gh, npm) that commonly use user credentials/config stored on the machine. The manifest should declare these runtime requirements and warn about possible use of locally-configured tokens.

✓ Persistence & Privilege

The skill does not request always:true and there is no indication it modifies other skills or system-wide settings. It appears not to persist or demand special platform privileges.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install clawie-research
安装完成后，直接呼叫该 Skill 的名称或使用 /clawie-research 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release

元数据

Slug clawie-research

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题