R

rust-learner

by @zhanghandongv
4.2(25)

Rust学習者向けに設計されており、Rustのバージョン、パッケージ(クレート)情報、関連学習リソースに関するクエリとガイダンスを提供し、Rustプログラミングの迅速な習得を支援します。

rust-programminglearning-resourcesprogramming-educationbeginner-friendlycode-examplesGitHub
インストール方法
npx skills add zhanghandong/rust-skills --skill rust-learner
compare_arrows

Before / After 効果比較

1
使用前

Rust言語を学習する際、最新のバージョン情報や特定のクレートの詳細資料を探すのは時間と労力がかかり、学習曲線が急であるため、挫折しがちです。

使用後

Rust学習アシスタントを利用することで、バージョン情報やクレート情報を素早く取得できます。これにより学習プロセスが大幅に簡素化され、Rust言語をより効率的に習得できるようになります。

SKILL.md

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
    • 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.

ユーザーレビュー (0)

レビューを書く

効果
使いやすさ
ドキュメント
互換性

レビューなし

統計データ

インストール数624
評価4.2 / 5.0
バージョン
更新日2026年5月23日
比較事例1 件

ユーザー評価

4.2(25)
5
60%
4
40%
3
0%
2
0%
1
0%

この Skill を評価

0.0

対応プラットフォーム

🔧Claude Code
🔧OpenClaw
🔧OpenCode
🔧Codex
🔧Gemini CLI
🔧GitHub Copilot
🔧Amp
🔧Kimi CLI

タイムライン

作成2026年3月16日
最終更新2026年5月23日