# Web Doc Resolver

> Resolve queries or URLs into compact, LLM-ready markdown using a low-cost cascade. Prioritizes llms.txt for structured docs, uses web fetch/search tools for extraction. Use when you need to fetch documentation, resolve web URLs to markdown, search for technical content, or build context from web sources.

- **Type:** Skill
- **Install:** `agentstack add skill-d-o-hub-rust-self-learning-memory-web-doc-resolver`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [d-o-hub](https://agentstack.voostack.com/s/d-o-hub)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [d-o-hub](https://github.com/d-o-hub)
- **Source:** https://github.com/d-o-hub/rust-self-learning-memory/tree/main/.agents/skills/web-doc-resolver
- **Website:** https://d-o-hub.github.io/rust-self-learning-memory/

## Install

```sh
agentstack add skill-d-o-hub-rust-self-learning-memory-web-doc-resolver
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Web Documentation Resolver

Resolve query or URL inputs into compact, high-signal markdown using an intelligent cascade.

## Platform Tool Mapping

| Platform | Fetch Tool | Search Tool |
|----------|------------|-------------|
| opencode | `webfetch` | `websearch` |
| claude code | `WebFetch` (MCP) | `WebSearch` (MCP) |
| blackbox | `web_fetch` | `web_search` |
| Python | `scripts/resolve.py` (auto-detects) | `scripts/resolve.py` (auto-detects) |

## Cascade Resolution Strategy

### URL Inputs
1. **llms.txt**: Probe `https://origin/llms.txt` first (free, structured)
2. **Fetch**: Use platform fetch tool for markdown content
3. **Search fallback**: Find cached/mirrored versions if fetch fails

### Query Inputs
1. **Search first**: Use platform search tool (fast, free)
2. **Fetch top results**: Get markdown from promising results

## Python Script

```bash
python scripts/resolve.py "https://docs.rust-lang.org/book/"  # URL
python scripts/resolve.py "Rust async programming"           # Query
python scripts/resolve.py "query" --json --max-chars 4000    # Options
```

## Direct Tool Usage

```bash
# opencode
webfetch https://example.com/llms.txt
webfetch --format markdown https://docs.rust-lang.org/book/
websearch "Rust book documentation"

# claude code (MCP)
WebFetch(url="https://example.com/llms.txt")
WebFetch(url="https://docs.rust-lang.org/book/")
WebSearch(query="Rust book documentation")

# blackbox
web_fetch(url="https://example.com/llms.txt", prompt="Extract all content")
web_search(query="Rust book documentation")
```

## Best Practices

- Check `/llms.txt` first for structured documentation
- Use specific queries: "tokio spawn vs spawn_blocking difference" > "tokio"
- Add year to queries for current info: "Rust async 2026"
- Prefer official docs; try mirrors if primary fails

## Quality Indicators

Good: Code examples, API signatures, config samples, version info, clear structure
Poor: Boilerplate, paywalls, login requirements, heavy ads

## Error Handling

- Cascade fallback on provider failures
- Log errors for debugging
- Search fallback when direct fetch fails

## Testing

```bash
cd .agents/skills/web-doc-resolver
python -m pytest tests/ -v
```

## Files

`scripts/resolve.py` - Main implementation | `tests/test_resolve.py` - Unit tests | `reference.md` - Detailed reference

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [d-o-hub](https://github.com/d-o-hub)
- **Source:** [d-o-hub/rust-self-learning-memory](https://github.com/d-o-hub/rust-self-learning-memory)
- **License:** MIT
- **Homepage:** https://d-o-hub.github.io/rust-self-learning-memory/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-d-o-hub-rust-self-learning-memory-web-doc-resolver
- Seller: https://agentstack.voostack.com/s/d-o-hub
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.