From ship
Performs web search, page fetch with Markdown conversion, deep research, and GitHub repo exploration (tree, read, overview) via the scout CLI tool. Requires Gemini API key.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ship:use-cli-scoutWhen to use
web search, page fetch, deep research, GitHub repo exploration, latest docs, release notes, library docs, external info, WebFetch alternative, WebSearch alternative, 最新ドキュメント, リリースノート, 外部情報
This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run `scout <subcommand> --help` for options, `--json` envelope, exit codes, stdin input, and examples. The help output is the authoritative source for the installed version.
Run scout <subcommand> --help for options, --json envelope, exit codes, stdin input, and examples. The help output is the authoritative source for the installed version.
| Purpose | Command |
|---|---|
| Web search | scout search "query" |
| Fetch page | scout fetch <url> |
| Deep research | scout research "topic" |
| Repo tree | scout repo-tree <owner/repo> |
| Repo read | scout repo-read <owner/repo> <path> |
| Repo overview | scout repo-overview <owner/repo> |
| use-cli-scout | Built-in WebFetch / WebSearch |
|---|---|
| Latest docs, release notes | Never (scout preferred) |
| GitHub repository exploration | Never (scout repo-* preferred) |
| Deep research with compiled report | Unavailable (use scout research) |
| Markdown-clean page extraction | WebFetch lacks Markdown conversion |
| Env Var | Required | Purpose |
|---|---|---|
| GEMINI_API_KEY | Yes | scout search / scout research |
| GITHUB_TOKEN | No | Higher rate limit for scout repo-* |
npx claudepluginhub thkt/dotclaude --plugin shipToken-efficient web research protocol that prioritizes minimal fetching. Guides API-based GitHub repo analysis, layered URL scraping, and search queries.
Gathers content from URLs (auto-detects Google/Slack/Notion/GitHub), web searches (Tavily/Exa), and local codebase into markdown artifacts for stable reasoning context.
Generates invocations for ferris-search MCP tools like web_search, fetch_web_content, fetch_github_readme, and domain-specific article fetchers. Explains tool usage, parameters, and troubleshooting.