thkt/scout-search
skills/scout-search/SKILL.md
Web search, page fetch, and GitHub repo exploration via scout CLI. Use when: 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.
$ install --global
skillsauthnpx skillsauth add thkt/claude-config scout-searchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 7:21 AM170.2s1 file scanned
SKILL.md
- name:
- scout-search
- description:
- Web search, page fetch, and GitHub repo exploration via scout CLI. Use when: 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.
- allowed-tools:
- [Bash, Read]
- user-invocable:
- false
scout-search
Commands
| Purpose | Command |
| ----------------- | ------------------------------------------------------------------- |
| Web search | scout search "query" |
| Language filter | scout search "query" --lang ja or --lang en |
| Fetch page | scout fetch <url> |
| Fetch (SPA) | scout fetch <url> --js |
| Fetch (raw) | scout fetch <url> --raw |
| Deep research | scout research "topic" |
| Research depth | scout research "topic" --depth N (1-10, default 3) |
| Repo tree | scout repo-tree <owner/repo> |
| Repo tree filter | scout repo-tree <owner/repo> --path <prefix> / --pattern <glob> |
| Repo tree at ref | scout repo-tree <owner/repo> --ref <branch-or-tag-or-sha> |
| Repo read | scout repo-read <owner/repo> <path> |
| Repo read lines | scout repo-read <owner/repo> <path> --lines 1-80 |
| Repo overview | scout repo-overview <owner/repo> |
When to Use
| scout-search | 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 |
Prerequisite
| Env Var | Required | Purpose |
| ---------------- | -------- | ------------------------------------ |
| GEMINI_API_KEY | Yes | scout search / scout research |
| GITHUB_TOKEN | No | Higher rate limit for scout repo-* |
Related Skills
thkt/outcome
documentation
VerifiedTrustedCommunity
Generates and updates .claude/OUTCOME.md interactively. When the file is absent or empty (no Behavior / all sections TBD), collects content via AskUserQuestion and writes the stub; when present, shows the current state and applies updates.
9SKILL.mdUpdated Jun 12, 2026
thkt/audit-skill-craft
development
VerifiedTrustedCommunity
Judge a SKILL.md against craft axes (single responsibility, description distinctiveness, imperative voice, verifiable completion, calibration, progressive disclosure) and apply the fixes the audit surfaces. Do not use for format-presence-only checks (use reviewer-prompt) or reproducibility loops (use /tuning).
9SKILL.mdUpdated Jun 11, 2026
thkt/use-workflow-plan-preview
tools
VerifiedTrustedCommunity
Internal helper for /think Step 11. Renders SOW.md + Spec.md as an integrated Astro view and returns a dev server URL.
9SKILL.mdUpdated Jun 1, 2026
thkt/probe
development
VerifiedTrustedCommunity
Extract repository spec while detecting bugs, spec gaps, and consistency drift via dual-purpose documentation. OUTCOME.md-axis question-driven exploration with ephemeral output. Do NOT use for code review (use /audit or /polish), feature implementation (use /code), planning only (use /think), or single-bug fix (use /fix).
9SKILL.mdUpdated Jun 1, 2026