walker

Deep crawl functionality that extracts and visits internal links from a webpage.

7 stars

Best use case

walker is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Deep crawl functionality that extracts and visits internal links from a webpage.

Teams using walker should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/walker/SKILL.md --create-dirs "https://raw.githubusercontent.com/codata/croissant-toolkit/main/skills/walker/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/walker/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How walker Compares

Feature / AgentwalkerStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Deep crawl functionality that extracts and visits internal links from a webpage.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 🚶 Walker Skill

The Walker skill provides "deep dive" capabilities for the toolkit. It allows the agent to explore a website by extracting all internal links from a given page and optionally visiting them in a browser.

This is particularly useful when a high-level search (via `Navigator`) doesn't provide enough information and the agent needs to "drill down" into a specific domain.

## Features
- **Link Extraction**: Parses HTML to find all links sharing the same domain as the parent page.
- **Normalization**: Automatically handles relative paths and cleans fragments.
- **Automated Navigation**: Can trigger the host browser to visit discovered pages.
- **Data Persistence**: Stores lists of discovered links in `./data/walker/` for future reference.

## Usage

### 1. Extract Links from a URL
```bash
python3 skills/walker/scripts/walk.py "https://example.com"
```

### 2. Extract and Automatically Open in Browser
```bash
python3 skills/walker/scripts/walk.py "https://example.com" --navigate --limit 3
```

## How it integrates
When the **Navigator** or **Wizard** encounters a page that seems relevant but lacks detail, the **Walker** can be invoked to expand the search perimeter within that specific site.

Related Skills

orchestrator_expert

7
from codata/croissant-toolkit

Orchestrator agent that has comprehensive knowledge and command over all available skills in this toolkit to create complex workflows.

neo4j_expert

7
from codata/croissant-toolkit

Store and query Croissant datasets in a Neo4j Graph Database for relational discovery and semantic search.

youtuber

7
from codata/croissant-toolkit

Search for videos on YouTube based on specific keywords. Get list of videos with title, description, and URL.

wizard

7
from codata/croissant-toolkit

The ultimate data integrator. Orchestrates transcription, translation, NLP analysis, and Croissant serialization into a single automated pipeline.

unf

7
from codata/croissant-toolkit

Universal Numeric Fingerprint (UNF) generator. For strings, it splits into words and sorts them alphabetically to provide order-invariant fingerprints. Supports dataframes and files too.

translator

7
from codata/croissant-toolkit

Recognize the language of input content or video scripts and translate them precisely into English using Gemini 3.

transcriber

7
from codata/croissant-toolkit

Fetch and store transcripts from YouTube videos for deep content analysis.

telegram_expert

7
from codata/croissant-toolkit

Send results and notifications to Telegram channels or users.

rohub

7
from codata/croissant-toolkit

Deposit research objects and add semantic annotations to the RO-Hub portal using the rohub library.

ro-crate-expert

7
from codata/croissant-toolkit

Specialized in creating RO-Crate packages from Dataverse metadata, with integrated ODRL-based DID (Decentralized Identifier) attribution and provenance via the ro-crate-py library.

📊 Presentation Expert Skill

7
from codata/croissant-toolkit

The **Presentation Expert** is responsible for transforming complex research data, metadata, and insights into high-impact presentation decks.

photograph

7
from codata/croissant-toolkit

Captures visual snapshots (screenshots) of web pages and records screen sessions (video).