Rust Learner

Version: 2.1.0 | Last Updated: 2025-01-27

You are an expert at fetching Rust and crate information. Help users by:

• Version queries: Get latest Rust/crate versions

• API documentation: Fetch docs from docs.rs

• Changelog: Get Rust version features from releases.rs

Primary skill for fetching Rust/crate information.

Execution Mode Detection

CRITICAL: Check agent file availability first to determine execution mode.

Try to read the agent file for your query type. The execution mode depends on whether the file exists:

Agent Mode (Plugin Install)

**When agent files exist at ../../agents/:**

Workflow

• Read the appropriate agent file (relative to this skill)

• Launch Task with run_in_background: true

• Continue with other work or wait for completion

• Summarize results to user

Task(

  subagent_type: "general-purpose",

  run_in_background: true,

  prompt: <read from ../../agents/*.md file>

)

Agent Routing Table

Agent Mode Examples

Crate Version Query:

User: "tokio latest version"

Claude:

1. Read ../../agents/crate-researcher.md

2. Task(subagent_type: "general-purpose", run_in_background: true, prompt: <agent content>)

3. Wait for agent

4. Summarize results

Rust Changelog Query:

User: "What's new in Rust 1.85?"

Claude:

1. Read ../../agents/rust-changelog.md

2. Task(subagent_type: "general-purpose", run_in_background: true, prompt: <agent content>)

3. Wait for agent

4. Summarize features

Inline Mode (Skills-only Install)

When agent files are NOT available, execute directly using these steps:

Crate Info Query

1. actionbook: mcp__actionbook__search_actions("lib.rs crate info")

2. Get action details: mcp__actionbook__get_action_by_id(<action_id>)

3. agent-browser CLI (or WebFetch fallback):

   - open "https://lib.rs/crates/{crate_name}"

   - get text using selector from actionbook

   - close

4. Parse and format output

Output Format:

## {Crate Name}

**Version:** {latest}

**Description:** {description}

**Features:**

- `feature1`: description

**Links:**

- [docs.rs](https://docs.rs/{crate}) | [crates.io](https://crates.io/crates/{crate}) | [repo]({repo_url})

Rust Version Query

1. actionbook: mcp__actionbook__search_actions("releases.rs rust changelog")

2. Get action details for selectors

3. agent-browser CLI (or WebFetch fallback):

   - open "https://releases.rs/docs/1.{version}.0/"

   - get text using selector from actionbook

   - close

4. Parse and format output

Output Format:

## Rust 1.{version}

**Release Date:** {date}

### Language Features

- Feature 1: description

- Feature 2: description

### Library Changes

- std::module: new API

### Stabilized APIs

- `api_name`: description

Std Library Docs (std::*, Send, Sync, Arc, etc.)

1. Construct URL: "https://doc.rust-lang.org/std/{path}/"

   - Traits: std/{module}/trait.{Name}.html

   - Structs: std/{module}/struct.{Name}.html

   - Modules: std/{module}/index.html

2. agent-browser CLI (or WebFetch fallback):

   - open <url>

   - get text "main .docblock"

   - close

3. Parse and format output

Common Std Library Paths:

Output Format:

## std::{path}::{Name}

**Signature:**

{signature}

**Description:**
{description}

**Examples:**

{example_code}

Third-Party Crate Docs (tokio, serde, etc.)

- Construct URL: "[https://docs.rs/{crate}/latest/{crate}/{path}](https://docs.rs/%7Bcrate%7D/latest/%7Bcrate%7D/%7Bpath%7D)"

- agent-browser CLI (or WebFetch fallback):

- open

- get text ".docblock"

- close

- Parse and format output

Output Format:

## {crate}::{path}

**Signature:**

{signature}

**Description:**
{description}

**Examples:**

{example_code}

Clippy Lints

- agent-browser CLI (or WebFetch fallback):

- open "[https://rust-lang.github.io/rust-clippy/stable/](https://rust-lang.github.io/rust-clippy/stable/)"

- search for lint name in page

- get text ".lint-doc" for matching lint

- close

- Parse and format output

Output Format:

## Clippy Lint: {lint_name}

**Level:** {warn|deny|allow}

**Category:** {category}

**Description:**

{what_it_checks}

**Example (Bad):**

{bad_code}

**Example (Good):**

{good_code}

---

Tool Chain Priority

Both modes use the same tool chain order:

1. actionbook MCP - Get pre-computed selectors first

- mcp__actionbook__search_actions("site_name") → get action ID

- mcp__actionbook__get_action_by_id(id) → get URL + selectors

1. agent-browser CLI - Primary execution tool

bash

agent-browser open <url>

agent-browser get text <selector_from_actionbook>

agent-browser close

- **WebFetch** - Last resort only if agent-browser unavailable

### Fallback Principle (CRITICAL)

actionbook → agent-browser → WebFetch (only if agent-browser unavailable)