Menu
Use for generic Exa Search API research. Provides auth, request-shape, date-filter, batching, highlights, error-handling, and compact JSON evidence guidance for arbitrary caller-supplied queries. Query-agnostic; does not decide what to search for.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use for Drip Meta Ads CLI work: Meta account/Page preflight, env mapping, paused Facebook campaign creation, Graph fallback commands, redaction, safety rules, and Performance Marketer evidence.
Use for Drip Builder work. Builder turns the user's selected Fashion Designer product images into a reviewed, deployed, one-page limited-drop site and writes builder-output.json.
Use for Drip Fashion Designer work. Fashion Designer turns approved Scout ideas into polished product mockups through three thin product-lane agents, lightweight curation, and fashion-designer-output.json.
Use when a sandbox task needs to operate Meta Ads through the `meta` CLI: account/page preflight, campaign/ad set/ad/creative creation or updates, optional read-only status checks, insights reads, catalog/dataset/pixel checks, env mapping, command safety, redaction, and paused-by-default ad operations.
Use for Drip Performance Marketer work. Performance Marketer turns a generated Builder drop-site URL plus selected product images into one paused Facebook-only drop-of-week ad artifact, writes performance-marketer-output.json, and stops before activation, spend, insights readback, or optimization loops.
Use for Drip Scout cultural-moment discovery. Scout is an end-to-end AI employee that coordinates X and Exa research subagents, judges evidence-informed cultural moments, and writes scout-output.json with five diverse fashion-plausible candidates by default.
| name | exa-search |
| description | Use for generic Exa Search API research. Provides auth, request-shape, date-filter, batching, highlights, error-handling, and compact JSON evidence guidance for arbitrary caller-supplied queries. Query-agnostic; does not decide what to search for. |
Use Exa as a source-backed web search adapter. The caller decides the research question and query text. This skill explains how to execute Exa Search API calls and return compact evidence.
Do not use Exa MCP. Do not require an Exa CLI.
Use EXA_API_KEY and never print its value.
curl -fsS "https://api.exa.ai/search" \
-H "Content-Type: application/json" \
-H "x-api-key: $EXA_API_KEY" \
-d '{"query":"<caller supplied query>","type":"fast","numResults":8,"contents":{"highlights":{"maxCharacters":500}}}'
type: "fast" for first-pass research.numResults between 5 and 10 unless the caller asks otherwise.contents.highlights for token-efficient evidence.category: "news" only when the caller explicitly wants news-like recency.category: "company" unless the caller asks for company research.moderation: true when the caller needs safer public web results.Example request body:
{
"query": "<caller supplied query>",
"type": "fast",
"numResults": 8,
"moderation": true,
"startPublishedDate": "2026-06-03T00:00:00.000Z",
"endPublishedDate": "2026-06-04T23:59:59.999Z",
"contents": {
"highlights": {
"maxCharacters": 500
},
"livecrawlTimeout": 5000
}
}
When the caller supplies multiple query angles or topics, run independent Exa calls in parallel when practical. Keep the merged return compact; do not dump raw result sets into the parent context.
Parallelism is API-level. Do not spawn additional Codex subagents from this skill.
Return compact JSON-like evidence:
{
"source": "exa",
"queriesRun": 2,
"evidence": [
{
"query": "<query that found this>",
"title": "Source title",
"url": "https://example.com/story",
"publishedDate": "2026-06-04T00:00:00.000Z",
"highlight": "Short relevant excerpt or summary",
"sourceDomain": "example.com"
}
],
"errors": []
}