ClawHub

Web Researcher

v1.0.0

Use this skill for deep research, fact-checking, or finding the latest technical news.

⭐ 0· 1.7k·6 current·6 all-time
by@aokikaito79

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for aokikaito79/web-researcher.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Web Researcher" (aokikaito79/web-researcher) from ClawHub.
Skill page: https://clawhub.ai/aokikaito79/web-researcher
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install aokikaito79/web-researcher

ClawHub CLI

Package manager switcher

npx clawhub@latest install web-researcher
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (deep research, fact-checking, latest news) match the instructions: run multiple searches, fetch full text of top results, synthesize and cite. It does not request unrelated credentials, binaries, or config access.
✓
Instruction Scope
SKILL.md stays within the stated purpose: perform 2–3 targeted searches, use web_fetch on top results, summarize and cite. The only notable action is retrieving full page content from external URLs (via web_fetch), which is expected for web research.
✓
Install Mechanism
Instruction-only skill with no install spec or code files — nothing is written to disk or downloaded by the skill itself.
✓
Credentials
No environment variables, secrets, or config paths are requested. The credential surface is minimal and appropriate for a web research task.
ℹ
Persistence & Privilege
always:false (normal). The skill can be invoked autonomously by the agent (platform default). Because it fetches external web content, autonomous runs could contact arbitrary sites — this is expected for a research skill but worth noting.
Assessment
This skill appears coherent and only asks the agent to run searches and fetch public web pages for synthesis. Before enabling it, confirm you are comfortable with the agent fetching arbitrary external URLs (check your platform's web_fetch behavior, privacy, and rate limits). No credentials are requested, and there is no install step. If you need stricter limits, consider restricting autonomous invocation or reviewing fetched results before they are presented.

Like a lobster shell, security has layers — review code before you run it.

latestvk973x8vz3srv96pp97v9nddabh82c192
1.7kdownloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0
@aokikaito79
latest
Download

Web Researcher Skill

When to use

  • Use when the user asks for "the latest," "news," or "research" on a topic.
  • Use when you need to verify a fact that isn't in your local training data.

Research Protocol

  1. Multi-Query Search: Don't just search once. Run 2-3 targeted searches (e.g., "OpenClaw 2026.3.2 features" AND "OpenClaw 2026.3.2 bugs").
  2. Deep Dive: Use web_fetch on at least the top 2 most relevant URLs to get the full text. Snippets are not enough for deep research.
  3. Synthesis: Summarize the findings by grouping them into "Key Facts," "Timeline," and "Contradictions" (if any).
  4. Cite Sources: Always list the URLs you actually read at the end of your report.

Output Format

  • Start with a 🪐 Jupiter Research Brief header.
  • Use bullet points for readability.
  • Highlight any "Breaking News" or "Critical Alerts" in bold.

Comments

Loading comments...