Agent skill
search3
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/search3
SKILL.md
search3 (Brave → Tavily → Firecrawl)
Use this skill to make web search more reliable by falling back across three providers.
What it does
- Try Brave using the built-in
web_searchtool.
- For Chinese, always use:
search_lang: "zh-hans"ui_lang: "zh-CN"
-
If Brave errors / returns empty, try Tavily via script:
{baseDir}/scripts/search3.py tavily ... -
If Tavily fails / returns empty, try Firecrawl via script:
{baseDir}/scripts/search3.py firecrawl ...
How to run (preferred)
Run the helper script and paste the JSON output back into the conversation:
python3 "{baseDir}/scripts/search3.py" all --query "<your query>" --max-results 8 --lang zh-hans
Provider-only mode
python3 "{baseDir}/scripts/search3.py" brave --query "..."
python3 "{baseDir}/scripts/search3.py" tavily --query "..."
python3 "{baseDir}/scripts/search3.py" firecrawl --query "..."
Output
The script prints JSON:
providerUsed: brave|tavily|firecrawlqueryresults: array of{ title, url, snippet }errors: any provider errors encountered before success
Requirements
- Uses env vars (already configured in
~/.openclaw/openclaw.json):TAVILY_API_KEYFIRECRAWL_API_KEY
If a key is missing, that provider is skipped.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?