PluginBench
Skill
Fail
Audit score 45

rust-learner

actionbook/rust-skills

How to install rust-learner

npx skills add https://github.com/actionbook/rust-skills --skill rust-learner
Claude Code
Cursor
Windsurf
Cline
Full instructions (SKILL.md)

Source of truth, from actionbook/rust-skills.


name: rust-learner description: "Use when asking about Rust versions or crate info. Keywords: latest version, what's new, changelog, Rust 1.x, Rust release, stable, nightly, crate info, crates.io, lib.rs, docs.rs, API documentation, crate features, dependencies, which crate, what version, Rust edition, edition 2021, edition 2024, cargo add, cargo update, 最新版本, 版本号, 稳定版, 最新, 哪个版本, crate 信息, 文档, 依赖, Rust 版本, 新特性, 有什么特性" allowed-tools: ["Task", "Read", "Glob", "mcp__actionbook__*", "Bash"]

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:

Query TypeAgent File Path
Crate info/version../../agents/crate-researcher.md
Rust version features../../agents/rust-changelog.md
Std library docs../../agents/std-docs-researcher.md
Third-party crate docs../../agents/docs-researcher.md
Clippy lints../../agents/clippy-researcher.md

Agent Mode (Plugin Install)

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

Workflow

  1. Read the appropriate agent file (relative to this skill)
  2. Launch Task with run_in_background: true
  3. Continue with other work or wait for completion
  4. Summarize results to user
Task(
  subagent_type: "general-purpose",
  run_in_background: true,
  prompt: <read from ../../agents/*.md file>
)

Agent Routing Table

Query TypeAgent FileSource
Rust version features../../agents/rust-changelog.mdreleases.rs
Crate info/version../../agents/crate-researcher.mdlib.rs, crates.io
Std library docs (Send, Sync, Arc, etc.)../../agents/std-docs-researcher.mddoc.rust-lang.org
Third-party crate docs (tokio, serde, etc.)../../agents/docs-researcher.mddocs.rs
Clippy lints../../agents/clippy-researcher.mdrust-clippy docs

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:

ItemPath
Send, Sync, Copy, Clonestd/marker/trait.{Name}.html
Arc, Mutex, RwLockstd/sync/struct.{Name}.html
Rc, Weakstd/rc/struct.{Name}.html
RefCell, Cellstd/cell/struct.{Name}.html
Boxstd/boxed/struct.Box.html
Vecstd/vec/struct.Vec.html
Stringstd/string/struct.String.html

Output Format:

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

**Signature:**
```rust
{signature}

Description: {description}

Examples:

{example_code}

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

  1. Construct URL: "https://docs.rs/{crate}/latest/{crate}/{path}"
  2. agent-browser CLI (or WebFetch fallback):
    • open <url>
    • get text ".docblock"
    • close
  3. Parse and format output

**Output Format:**
```markdown
## {crate}::{path}

**Signature:**
```rust
{signature}

Description: {description}

Examples:

{example_code}

### Clippy Lints

  1. agent-browser CLI (or WebFetch fallback):
  2. Parse and format output

**Output Format:**
```markdown
## Clippy Lint: {lint_name}

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

**Description:**
{what_it_checks}

**Example (Bad):**
```rust
{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

2. **agent-browser CLI** - Primary execution tool
   ```bash
   agent-browser open <url>
   agent-browser get text <selector_from_actionbook>
   agent-browser close
  1. WebFetch - Last resort only if agent-browser unavailable

Fallback Principle (CRITICAL)

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

DO NOT:

  • Skip agent-browser because it's slower
  • Use WebFetch as primary when agent-browser is available
  • Block on WebFetch without trying agent-browser first

Deprecated Patterns

DeprecatedUse InsteadReason
WebSearch for crate infoTask + agent or inline modeStructured data
Direct WebFetchactionbook + agent-browserPre-computed selectors
Guessing version numbersAlways fetch from sourcePrevents misinformation

Error Handling

ErrorCauseSolution
Agent file not foundSkills-only installUse inline mode
actionbook unavailableMCP not configuredFall back to WebFetch
agent-browser not foundCLI not installedFall back to WebFetch
Agent timeoutSite slow/downRetry or inform user
Empty resultsSelector mismatchReport and use WebFetch fallback

Proactive Triggering

This skill triggers AUTOMATICALLY when:

  • Any Rust crate name mentioned (tokio, serde, axum, sqlx, etc.)
  • Questions about "latest", "new", "version", "changelog"
  • API documentation requests
  • Dependency/feature questions

DO NOT use WebSearch for Rust crate info. Use agents or inline mode instead.

Related skills

More from actionbook/rust-skills and the wider catalog.

CO

coding-guidelines

actionbook/rust-skills

Use when asking about Rust code style or best practices. Keywords: naming, formatting, comment, clippy, rustfmt, lint, code style, best practice, P.NAM, G.FMT, code review, naming convention, variable naming, function naming, type naming, 命名规范, 代码风格, 格式化, 最佳实践, 代码审查, 怎么命名

1.2k installsAudited
M0

m07-concurrency

actionbook/rust-skills

CRITICAL: Use for concurrency/async. Triggers: E0277 Send Sync, cannot be sent between threads, thread, spawn, channel, mpsc, Mutex, RwLock, Atomic, async, await, Future, tokio, deadlock, race condition, 并发, 线程, 异步, 死锁

1.2k installsAudited
M1

m10-performance

actionbook/rust-skills

CRITICAL: Use for performance optimization. Triggers: performance, optimization, benchmark, profiling, flamegraph, criterion, slow, fast, allocation, cache, SIMD, make it faster, 性能优化, 基准测试

1.2k installsAudited
M0

m06-error-handling

actionbook/rust-skills

CRITICAL: Use for error handling. Triggers: Result, Option, Error, ?, unwrap, expect, panic, anyhow, thiserror, when to panic vs return Result, custom error, error propagation, 错误处理, Result 用法, 什么时候用 panic

1.2k installsAudited
M0

m01-ownership

actionbook/rust-skills

CRITICAL: Use for ownership/borrow/lifetime issues. Triggers: E0382, E0597, E0506, E0507, E0515, E0716, E0106, value moved, borrowed value does not live long enough, cannot move out of, use of moved value, ownership, borrow, lifetime, 'a, 'static, move, clone, Copy, 所有权, 借用, 生命周期

1.2k installsAudited
M0

m02-resource

actionbook/rust-skills

CRITICAL: Use for smart pointers and resource management. Triggers: Box, Rc, Arc, Weak, RefCell, Cell, smart pointer, heap allocation, reference counting, RAII, Drop, should I use Box or Rc, when to use Arc vs Rc, 智能指针, 引用计数, 堆分配

1.2k installsAudited