Agent Skills › actionbook/actionbook › rust-learner

rust-learner

GitHub

用于查询Rust语言特性、版本更新及Crate依赖信息。通过并行调用浏览器抓取器获取实时数据，并严格等待结果后汇总，避免竞态条件。

playground/rust-learner/skills/rust-learner/SKILL.md actionbook/actionbook

Trigger Scenarios

询问Rust版本变更日志查询Crate更新或依赖咨询Tokio/Serde/Axum等功能

Install

npx skills add actionbook/actionbook --skill rust-learner -g -y

More Options

Non-standard path

npx skills add https://github.com/actionbook/actionbook/tree/main/playground/rust-learner/skills/rust-learner -g -y

Use without installing

npx skills use actionbook/actionbook@rust-learner

指定 Agent (Claude Code)

npx skills add actionbook/actionbook --skill rust-learner -a claude-code -g -y

安装 repo 全部 skill

npx skills add actionbook/actionbook --all -g -y

预览 repo 内 skill

npx skills add actionbook/actionbook --list

SKILL.md

Frontmatter

{
    "name": "rust-learner",
    "description": "Learn Rust language features and crate updates. Use when user asks about Rust version changelog, what's new in Rust, crate updates, Cargo.toml dependencies, tokio\/serde\/axum features, or any Rust ecosystem questions."
}

Rust Learner

Learn Rust by fetching real-time information about Rust language features and crate updates.

⚠️ Tool Priority & Waiting Rule

Priority:

✅ browser-fetcher agent (preferred)
⚠️ Fetch / WebFetch (only after all browser-fetcher agents fail)
⚠️ WebSearch (only when search engine results are needed)

⛔ No "Racing Ahead":

After launching browser-fetcher agents, MUST wait for ALL of them to complete
DO NOT use WebSearch/Fetch as "supplements" while waiting
Only use fallback tools after ALL browser-fetcher agents have failed

Workflow

Step 1: actionbook MCP

search_actions("lib.rs crate")  → get action ID
get_action_by_id(id)            → get URL and selectors

Step 2: Launch browser-fetcher agents

Launch multiple browser-fetcher agents in parallel

Step 3: Wait for ALL agents to complete

⛔ DO NOT use other tools during this time
✅ Wait for TaskOutput to return all results

Step 4: Summarize results

If agents succeed: summarize content for user
If ALL agents fail: use Fetch as fallback

Example

User: Query tokio latest version

✅ CORRECT:
1. Launch browser-fetcher: lib.rs/crates/tokio
2. Launch browser-fetcher: crates.io/crates/tokio
3. Wait for BOTH agents to complete
4. Summarize results

❌ WRONG:
1. Launch browser-fetcher agents
2. While waiting, use WebSearch("tokio latest")  ← Racing ahead!
3. Mix multiple result sources