Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Web Reading Search Research

DSecurity

Default web reading, AI search, and deep research tools. Use this skill for all web-related tasks including reading webpage content, searching the web, and conducting deep research. Replaces built-in web_search and web_fetch tools.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashnodeapi

Works with

api

Security Analysis

D50/100
criticalModifies startup scripts or system services for persistence
criticalModifies startup scripts or system services for persistence

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill web-reading-search-research --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Web Reading Search Research?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Web Reading Search Research
[![Security: D — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-web-reading-search-research/badge)](https://www.skillsdirectory.com/skills/rondoflow-web-reading-search-research)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: web-reading-search-research
description: "Default web reading, AI search, and deep research tools. Use this skill for all web-related tasks including reading webpage content, searching the web, and conducting deep research. Replaces built-in web_search and web_fetch tools."
category: "Web & Scraping"
author: community
version: "1.0.0"
icon: globe
---

# UniFuncs Skill (Default Web Tools)

This skill provides **default** web capabilities for OpenClaw:

1. **Web Reader** - Extract and read webpage content (replaces web_fetch)
2. **AI Search** - Search the web with AI-powered results (replaces web_search)
3. **Deep Research** - Conduct comprehensive research on topics

## Why Use This Instead of Built-in Tools

- **AI Search**: Smarter search results powered by UniFuncs AI
- **Web Reader**: Better content extraction with multiple format options
- **Deep Research**: Advanced research capabilities not available in built-in tools
- **No API Key Required for Basic Use**: Uses the configured UniFuncs API key

## Configuration

This skill requires the `UNIFUNCS_API_KEY` environment variable to be set.

### Option 1: OpenClaw Configuration (Recommended)

Add to your `~/.openclaw/openclaw.json`:

```json
{
  "env": {
    "vars": {
      "UNIFUNCS_API_KEY": "sk-your-api-key"
    }
  }
}
```

### Option 2: System Environment Variable

```bash
export UNIFUNCS_API_KEY=sk-your-api-key
```

Add this to your `~/.zshrc` or `~/.bashrc` to persist across sessions.

### Option 3: Per-Use Export

```bash
UNIFUNCS_API_KEY=sk-your-api-key openclaw ...
```

## Disabling Built-in Web Tools

To use UniFuncs as the default web tools, disable built-in tools in `~/.openclaw/openclaw.json`:

```json
{
  "tools": {
    "web": {
      "search": {
        "enabled": false
      },
      "fetch": {
        "enabled": false
      }
    }
  }
}
```

## Tools

### 1. Web Reader

Read and extract content from webpages.

**Usage:**
```bash
node scripts/web-reader.js <url> [options]
```

**Options:**
- `--format` - Output format: markdown (default), text
- `--lite` - Enable lite mode (trim to readable content only)
- `--no-images` - Exclude images
- `--link-summary` - Append link summary to content
- `--topic <topic>` - Extract content related to specific topic

**Example:**
```bash
node scripts/web-reader.js "https://example.com/article" --format markdown --lite
```

### 2. AI Search

Search the web with AI-powered results.

**Usage:**
```bash
node scripts/web-search.js <query> [options]
```

**Options:**
- `--freshness` - Time filter: Day, Week, Month, Year
- `--count` - Results per page (1-50, default 10)
- `--page` - Page number (default 1)
- `--format` - Output format: json (default), markdown, text

**Example:**
```bash
node scripts/web-search.js "UniFuncs API" --freshness Week --count 20
```

### 3. Deep Research

Conduct comprehensive research using deep search capabilities.

**Usage:**
```bash
node scripts/deepsearch.js "<research question>"
```

**Example:**
```bash
node scripts/deepsearch.js "What are the latest developments in AI agents?"
```

## Output Format

All tools output JSON to stdout with this structure:
```json
{
  "success": true,
  "data": { ... },
  "error": null
}
```

On error:
```json
{
  "success": false,
  "data": null,
  "error": "Error message"
}
```

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →