exa-search

Name: exa-search
Author: MoizIbnYousaf

27stars5forks

How to install exa-search?

moizibnyousaf/marketing-cli/exa-search

$npx -y skills add MoizIbnYousaf/marketing-cli --skill exa-search

Installs into the current project.

Summary

Call Exa Search (POST /search) for semantic web retrieval with ranked results, filters, freshness, highlights/text, structured output, or streaming. Use when the agent needs open-ended web search, competitor discovery, news, people, or research papers and does not already have UR

Files · 1

View on GitHub

SKILL.md

1	## On Activation
2
3	1. Read `brand/positioning.md`, `brand/competitors.md`, and `brand/landscape.md` if present. Use them to sharpen queries and exclusions. All optional - works at zero brand context.
4	2. Confirm Exa auth: Exa MCP connected, or `EXA_API_KEY` set (`mktg doctor --json --fields integrations`). If neither, stop and surface: get a key at https://dashboard.exa.ai/api-keys then `export EXA_API_KEY=...`.
5	3. Prefer MCP tools when present; otherwise use the cURL examples below.
6	4. After discovery, chain `firecrawl` or `exa-contents` only when a known URL needs deeper extraction.
7
8	# Exa Search
9
10	> Requires API key: Get one at https://dashboard.exa.ai/api-keys
11	>
12	> Header: `x-api-key: $EXA_API_KEY`
13
14	Use `POST https://api.exa.ai/search` for semantic web retrieval, ranked results, and optional result-level extraction in one raw HTTP call. Start with `type: "auto"` for general retrieval. Add `contents` only when the caller needs page text, highlights, summaries, freshness-controlled crawling, subpages, or extracted links.
15
16	## Quick Start (cURL)
17
18	### Basic search
19
20	```bash
21	curl -sS -X POST "https://api.exa.ai/search" \
22	-H "Content-Type: application/json" \
23	-H "x-api-key: $EXA_API_KEY" \
24	-d '{
25	"query": "latest developments in LLMs",
26	"type": "auto",
27	"numResults": 10
28	}'
29	```
30
31	### Search with highlights
32
33	```bash
34	curl -sS -X POST "https://api.exa.ai/search" \
35	-H "Content-Type: application/json" \
36	-H "x-api-key: $EXA_API_KEY" \
37	-d '{
38	"query": "latest developments in LLMs",
39	"type": "auto",
40	"numResults": 5,
41	"contents": {
42	"highlights": true
43	}
44	}'
45	```
46
47	### With filters and freshness
48
49	```bash
50	curl -sS -X POST "https://api.exa.ai/search" \
51	-H "Content-Type: application/json" \
52	-H "x-api-key: $EXA_API_KEY" \
53	-d '{
54	"query": "AI regulation policy updates",
55	"type": "auto",
56	"category": "news",
57	"numResults": 10,
58	"includeDomains": ["reuters.com", "bbc.com"],
59	"startPublishedDate": "2025-01-01",
60	"contents": {
61	"text": {
62	"maxCharacters": 2000
63	},
64	"maxAgeHours": 24,
65	"livecrawlTimeout": 12000
66	}
67	}'
68	```
69
70	### Deep search
71
72	```bash
73	curl -sS -X POST "https://api.exa.ai/search" \
74	-H "Content-Type: application/json" \
75	-H "x-api-key: $EXA_API_KEY" \
76	-d '{
77	"query": "map the major technical and commercial tradeoffs in sodium-ion batteries for grid storage",
78	"type": "deep",
79	"numResults": 8
80	}'
81	```
82
83	## Endpoint
84
85	```text
86	POST https://api.exa.ai/search
87	```
88
89	Authentication: `x-api-key: <API_KEY>` header. Exa also accepts `Authorization: Bearer <API_KEY>`, but prefer `x-api-key` in cURL examples for consistency.
90
91	Use this endpoint when the agent needs search results. If the agent already has URLs and only needs extraction, use `POST /contents` instead.
92
93	## Parameters
94
95	### Core request parameters
96
97	\| Parameter \| Type \| Required \| Default \| Description \|
98	\| --- \| --- \| --- \| --- \| --- \|
99	\| `query` \| string \| Yes \| - \| Natural-language search query. Long, semantically rich descriptions work well. \|
100	\| `type` \| string \| No \| `auto` \| Search method: `auto`, `fast`, `instant`, `deep-lite`, `deep`, or `deep-reasoning`. \|
101	\| `numResults` \| integer \| No \| `10` \| Number of results to return. Use small values for agent loops; maximum is 100. \|
102	\| `category` \| string \| No \| - \| Specialized result type: `company`, `people`, `research paper`, `news`, `personal site`, or `financial report`. \|
103	\| `includeDomains` \| string[] \| No \| - \| Only return results from these domains, paths, or wildcard patterns. Max 1200. \|
104	\| `excludeDomains` \| string[] \| No \| - \| Exclude these domains, paths, or wildcard patterns. Max 1200. \|
105	\| `startPublishedDate` \| string \| No \| - \| ISO 8601 lower bound for result publication date. \|
106	\| `endPublishedDate` \| string \| No \| - \| ISO 8601 upper bound for result publication date. \|
107	\| `userLocation` \| string \| No \| - \| Two-letter ISO country code such as `US` or `GB`. \|
108	\| `moderation` \| boolean \| No \| `false` \| Filter unsafe content from results. \|
109	\| `additionalQueries` \| string[] \| No \| - \| Extra query variants for deep-search variants. Use alongside the main `query`. \|
110	\| `systemPrompt` \| string \| No \| - \| Instructions for synthesized output and deep-search planning, s

People who liked this also viewed

6 picks

Type

exa-search

27stars5forks

View on GitHub

How to install exa-search?

moizibnyousaf/marketing-cli/exa-search

$npx -y skills add MoizIbnYousaf/marketing-cli --skill exa-search

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## On Activation
2
3	1. Read `brand/positioning.md`, `brand/competitors.md`, and `brand/landscape.md` if present. Use them to sharpen queries and exclusions. All optional - works at zero brand context.
4	2. Confirm Exa auth: Exa MCP connected, or `EXA_API_KEY` set (`mktg doctor --json --fields integrations`). If neither, stop and surface: get a key at https://dashboard.exa.ai/api-keys then `export EXA_API_KEY=...`.
5	3. Prefer MCP tools when present; otherwise use the cURL examples below.
6	4. After discovery, chain `firecrawl` or `exa-contents` only when a known URL needs deeper extraction.
7
8	# Exa Search
9
10	> Requires API key: Get one at https://dashboard.exa.ai/api-keys
11	>
12	> Header: `x-api-key: $EXA_API_KEY`
13
14	Use `POST https://api.exa.ai/search` for semantic web retrieval, ranked results, and optional result-level extraction in one raw HTTP call. Start with `type: "auto"` for general retrieval. Add `contents` only when the caller needs page text, highlights, summaries, freshness-controlled crawling, subpages, or extracted links.
15
16	## Quick Start (cURL)
17
18	### Basic search
19
20	```bash
21	curl -sS -X POST "https://api.exa.ai/search" \
22	-H "Content-Type: application/json" \
23	-H "x-api-key: $EXA_API_KEY" \
24	-d '{
25	"query": "latest developments in LLMs",
26	"type": "auto",
27	"numResults": 10
28	}'
29	```
30
31	### Search with highlights
32
33	```bash
34	curl -sS -X POST "https://api.exa.ai/search" \
35	-H "Content-Type: application/json" \
36	-H "x-api-key: $EXA_API_KEY" \
37	-d '{
38	"query": "latest developments in LLMs",
39	"type": "auto",
40	"numResults": 5,
41	"contents": {
42	"highlights": true
43	}
44	}'
45	```
46
47	### With filters and freshness
48
49	```bash
50	curl -sS -X POST "https://api.exa.ai/search" \
51	-H "Content-Type: application/json" \
52	-H "x-api-key: $EXA_API_KEY" \
53	-d '{
54	"query": "AI regulation policy updates",
55	"type": "auto",
56	"category": "news",
57	"numResults": 10,
58	"includeDomains": ["reuters.com", "bbc.com"],
59	"startPublishedDate": "2025-01-01",
60	"contents": {
61	"text": {
62	"maxCharacters": 2000
63	},
64	"maxAgeHours": 24,
65	"livecrawlTimeout": 12000
66	}
67	}'
68	```
69
70	### Deep search
71
72	```bash
73	curl -sS -X POST "https://api.exa.ai/search" \
74	-H "Content-Type: application/json" \
75	-H "x-api-key: $EXA_API_KEY" \
76	-d '{
77	"query": "map the major technical and commercial tradeoffs in sodium-ion batteries for grid storage",
78	"type": "deep",
79	"numResults": 8
80	}'
81	```
82
83	## Endpoint
84
85	```text
86	POST https://api.exa.ai/search
87	```
88
89	Authentication: `x-api-key: <API_KEY>` header. Exa also accepts `Authorization: Bearer <API_KEY>`, but prefer `x-api-key` in cURL examples for consistency.
90
91	Use this endpoint when the agent needs search results. If the agent already has URLs and only needs extraction, use `POST /contents` instead.
92
93	## Parameters
94
95	### Core request parameters
96
97	\| Parameter \| Type \| Required \| Default \| Description \|
98	\| --- \| --- \| --- \| --- \| --- \|
99	\| `query` \| string \| Yes \| - \| Natural-language search query. Long, semantically rich descriptions work well. \|
100	\| `type` \| string \| No \| `auto` \| Search method: `auto`, `fast`, `instant`, `deep-lite`, `deep`, or `deep-reasoning`. \|
101	\| `numResults` \| integer \| No \| `10` \| Number of results to return. Use small values for agent loops; maximum is 100. \|
102	\| `category` \| string \| No \| - \| Specialized result type: `company`, `people`, `research paper`, `news`, `personal site`, or `financial report`. \|
103	\| `includeDomains` \| string[] \| No \| - \| Only return results from these domains, paths, or wildcard patterns. Max 1200. \|
104	\| `excludeDomains` \| string[] \| No \| - \| Exclude these domains, paths, or wildcard patterns. Max 1200. \|
105	\| `startPublishedDate` \| string \| No \| - \| ISO 8601 lower bound for result publication date. \|
106	\| `endPublishedDate` \| string \| No \| - \| ISO 8601 upper bound for result publication date. \|
107	\| `userLocation` \| string \| No \| - \| Two-letter ISO country code such as `US` or `GB`. \|
108	\| `moderation` \| boolean \| No \| `false` \| Filter unsafe content from results. \|
109	\| `additionalQueries` \| string[] \| No \| - \| Extra query variants for deep-search variants. Use alongside the main `query`. \|
110	\| `systemPrompt` \| string \| No \| - \| Instructions for synthesized output and deep-search planning, s

People who liked this also viewed

6 picks

Type