Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →sundial-org/grok-search
Search the web or X/Twitter using xAI Grok server-side tools (web_search, x_search) via the xAI Responses API.
Passed 6 of 12 test cases with the skill, and 2 of 12 without it.
and 7 more in the full report
9 fixed3 passed either way10 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
What fields are present in each item inside the results array of the search script JSON output?
| Checked | Without skill | With skill |
|---|---|---|
| Includes title, url, snippet, author, and posted_at | Missed | Passed |
The instructions your model reads when the skill loads.
Run xAI Grok locally via bundled scripts (search + chat + model listing). Default output for search is pretty JSON (agent-friendly) with citations.
The script looks for an xAI API key in this order:
XAI_API_KEY env var~/.clawdbot/clawdbot.json → env.XAI_API_KEY~/.clawdbot/clawdbot.json → skills.entries["grok-search"].apiKeyskills.entries["search-x"].apiKey or skills.entries.xai.apiKeyUse {baseDir} so the command works regardless of workspace layout.
Web search (JSON):
node {baseDir}/scripts/grok_search.mjs "<query>" --webX/Twitter search (JSON):
node {baseDir}/scripts/grok_search.mjs "<query>" --xChat (text):
node {baseDir}/scripts/chat.mjs "<prompt>"Chat (vision):
node {baseDir}/scripts/chat.mjs --image /path/to/image.jpg "<prompt>"node {baseDir}/scripts/models.mjsOutput:
--links-only print just citation URLs--text hide the citations section in pretty outputtest cases passed, vs 2 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.