exa-contents

Name: exa-contents
Author: MoizIbnYousaf

27stars5forks

How to install exa-contents?

moizibnyousaf/marketing-cli/exa-contents

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

Installs into the current project.

Summary

Call Exa Contents (POST /contents) for LLM-ready extraction from known URLs: text, highlights, summaries, links, image links, subpages, freshness-controlled crawl. Use when the agent already has URLs. Prefer Exa MCP web_fetch_exa when available; otherwise raw HTTP with EXA_API_KE

Files · 1

View on GitHub

SKILL.md

1	## On Activation
2
3	1. Read `brand/competitors.md` / `brand/landscape.md` if present for URL shortlists. Optional.
4	2. Confirm Exa auth (MCP or `EXA_API_KEY`) via `mktg doctor` if unsure.
5	3. Prefer MCP `web_fetch_exa` when available; otherwise use the cURL examples below.
6	4. If the page is auth-walled (X/Twitter login stub), route to `mktg-x` instead.
7
8	# Exa Contents
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/contents` when the agent already knows the URLs and needs clean, LLM-ready extraction without running a new search. Start with one content mode: `highlights` for compact agent context, `text` for broad page context, or `summary` for Exa-side compression.
15
16	## Quick Start (cURL)
17
18	### Basic text extraction
19
20	```bash
21	curl -sS -X POST "https://api.exa.ai/contents" \
22	-H "Content-Type: application/json" \
23	-H "x-api-key: $EXA_API_KEY" \
24	-d '{
25	"urls": ["https://example.com"],
26	"text": true
27	}'
28	```
29
30	### Highlights with freshness control
31
32	```bash
33	curl -sS -X POST "https://api.exa.ai/contents" \
34	-H "Content-Type: application/json" \
35	-H "x-api-key: $EXA_API_KEY" \
36	-d '{
37	"urls": ["https://arxiv.org/abs/2307.06435"],
38	"highlights": {
39	"query": "methodology and results"
40	},
41	"maxAgeHours": 24,
42	"livecrawlTimeout": 12000
43	}'
44	```
45
46	## Endpoint
47
48	```text
49	POST https://api.exa.ai/contents
50	```
51
52	Authentication: `x-api-key: <API_KEY>` header. Exa also accepts `Authorization: Bearer <API_KEY>`, but prefer `x-api-key` in cURL examples for consistency.
53
54	Use this endpoint for known-URL extraction. If the agent needs discovery or ranking first, use `POST /search`.
55
56	## Parameters
57
58	### Core request parameters
59
60	\| Parameter \| Type \| Required \| Default \| Description \|
61	\| --- \| --- \| --- \| --- \| --- \|
62	\| `urls` \| string[] \| Yes \| - \| URLs to extract content from. Use this for known URLs. \|
63	\| `text` \| boolean or object \| No \| - \| Return full page text as markdown. Object form supports `maxCharacters`, `includeHtmlTags`, `verbosity`, `includeSections`, and `excludeSections`. \|
64	\| `highlights` \| boolean or object \| No \| - \| Return key excerpts. Prefer `true` for agent workflows unless a custom focus is needed. \|
65	\| `summary` \| boolean or object \| No \| - \| Return per-page LLM summaries. Use when the caller wants Exa-side compression or structured extraction. \|
66	\| `maxAgeHours` \| integer \| No \| - \| Freshness control. `0` always live crawls; `-1` uses cache only; omit for default cache-first behavior with crawl fallback. \|
67	\| `livecrawlTimeout` \| integer \| No \| `10000` \| Timeout for live crawling in milliseconds. Use `10000` to `15000` for most freshness-sensitive calls. \|
68	\| `subpages` \| integer \| No \| `0` \| Number of linked subpages to crawl from each URL. \|
69	\| `subpageTarget` \| string or string[] \| No \| - \| Terms used to prioritize which subpages matter, such as `["api", "reference", "pricing"]`. \|
70	\| `extras.links` \| integer \| No \| `0` \| Number of links to extract from each page. \|
71	\| `extras.imageLinks` \| integer \| No \| `0` \| Number of image URLs to extract from each page. \|
72	\| `compliance` \| string \| No \| - \| Enterprise-only compliance mode, such as `hipaa`, when enabled for the account. \|
73
74	### Text object options
75
76	\| Parameter \| Type \| Default \| Description \|
77	\| --- \| --- \| --- \| --- \|
78	\| `maxCharacters` \| integer \| - \| Character limit for returned text. Use this instead of `tokensNum`. \|
79	\| `includeHtmlTags` \| boolean \| `false` \| Preserve HTML tags in output. \|
80	\| `verbosity` \| string \| `compact` \| `compact`, `standard`, or `full`. Pair fresh section-aware extraction with `maxAgeHours: 0`. \|
81	\| `includeSections` \| string[] \| - \| Only include selected sections: `header`, `navigation`, `banner`, `body`, `sidebar`, `footer`, `metadata`. \|
82	\| `excludeSections` \| string[] \| - \| Exclude selected sections from the same section list. \|
83
84	### Highlights object options
85
86	Prefer `highlights: true` for the highest-quality default. Only use object form when the agent needs a custom focus or budget.
87
88	\| Parameter \| Type \| Default \| Description \|
89	\| --- \| --- \| --- \| --- \|
90	\| `query` \| string \| - \| Custom query guiding which excerpts are returned. \|
91	\| `maxCharacters` \| integer \| - \| Cap highlight characters per URL. Omit unless the caller has a strict budget. \|
92
93	### Summary object options
94
95	\| Parameter

People who liked this also viewed

6 picks

Type

exa-contents

27stars5forks

View on GitHub

How to install exa-contents?

moizibnyousaf/marketing-cli/exa-contents

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## On Activation
2
3	1. Read `brand/competitors.md` / `brand/landscape.md` if present for URL shortlists. Optional.
4	2. Confirm Exa auth (MCP or `EXA_API_KEY`) via `mktg doctor` if unsure.
5	3. Prefer MCP `web_fetch_exa` when available; otherwise use the cURL examples below.
6	4. If the page is auth-walled (X/Twitter login stub), route to `mktg-x` instead.
7
8	# Exa Contents
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/contents` when the agent already knows the URLs and needs clean, LLM-ready extraction without running a new search. Start with one content mode: `highlights` for compact agent context, `text` for broad page context, or `summary` for Exa-side compression.
15
16	## Quick Start (cURL)
17
18	### Basic text extraction
19
20	```bash
21	curl -sS -X POST "https://api.exa.ai/contents" \
22	-H "Content-Type: application/json" \
23	-H "x-api-key: $EXA_API_KEY" \
24	-d '{
25	"urls": ["https://example.com"],
26	"text": true
27	}'
28	```
29
30	### Highlights with freshness control
31
32	```bash
33	curl -sS -X POST "https://api.exa.ai/contents" \
34	-H "Content-Type: application/json" \
35	-H "x-api-key: $EXA_API_KEY" \
36	-d '{
37	"urls": ["https://arxiv.org/abs/2307.06435"],
38	"highlights": {
39	"query": "methodology and results"
40	},
41	"maxAgeHours": 24,
42	"livecrawlTimeout": 12000
43	}'
44	```
45
46	## Endpoint
47
48	```text
49	POST https://api.exa.ai/contents
50	```
51
52	Authentication: `x-api-key: <API_KEY>` header. Exa also accepts `Authorization: Bearer <API_KEY>`, but prefer `x-api-key` in cURL examples for consistency.
53
54	Use this endpoint for known-URL extraction. If the agent needs discovery or ranking first, use `POST /search`.
55
56	## Parameters
57
58	### Core request parameters
59
60	\| Parameter \| Type \| Required \| Default \| Description \|
61	\| --- \| --- \| --- \| --- \| --- \|
62	\| `urls` \| string[] \| Yes \| - \| URLs to extract content from. Use this for known URLs. \|
63	\| `text` \| boolean or object \| No \| - \| Return full page text as markdown. Object form supports `maxCharacters`, `includeHtmlTags`, `verbosity`, `includeSections`, and `excludeSections`. \|
64	\| `highlights` \| boolean or object \| No \| - \| Return key excerpts. Prefer `true` for agent workflows unless a custom focus is needed. \|
65	\| `summary` \| boolean or object \| No \| - \| Return per-page LLM summaries. Use when the caller wants Exa-side compression or structured extraction. \|
66	\| `maxAgeHours` \| integer \| No \| - \| Freshness control. `0` always live crawls; `-1` uses cache only; omit for default cache-first behavior with crawl fallback. \|
67	\| `livecrawlTimeout` \| integer \| No \| `10000` \| Timeout for live crawling in milliseconds. Use `10000` to `15000` for most freshness-sensitive calls. \|
68	\| `subpages` \| integer \| No \| `0` \| Number of linked subpages to crawl from each URL. \|
69	\| `subpageTarget` \| string or string[] \| No \| - \| Terms used to prioritize which subpages matter, such as `["api", "reference", "pricing"]`. \|
70	\| `extras.links` \| integer \| No \| `0` \| Number of links to extract from each page. \|
71	\| `extras.imageLinks` \| integer \| No \| `0` \| Number of image URLs to extract from each page. \|
72	\| `compliance` \| string \| No \| - \| Enterprise-only compliance mode, such as `hipaa`, when enabled for the account. \|
73
74	### Text object options
75
76	\| Parameter \| Type \| Default \| Description \|
77	\| --- \| --- \| --- \| --- \|
78	\| `maxCharacters` \| integer \| - \| Character limit for returned text. Use this instead of `tokensNum`. \|
79	\| `includeHtmlTags` \| boolean \| `false` \| Preserve HTML tags in output. \|
80	\| `verbosity` \| string \| `compact` \| `compact`, `standard`, or `full`. Pair fresh section-aware extraction with `maxAgeHours: 0`. \|
81	\| `includeSections` \| string[] \| - \| Only include selected sections: `header`, `navigation`, `banner`, `body`, `sidebar`, `footer`, `metadata`. \|
82	\| `excludeSections` \| string[] \| - \| Exclude selected sections from the same section list. \|
83
84	### Highlights object options
85
86	Prefer `highlights: true` for the highest-quality default. Only use object form when the agent needs a custom focus or budget.
87
88	\| Parameter \| Type \| Default \| Description \|
89	\| --- \| --- \| --- \| --- \|
90	\| `query` \| string \| - \| Custom query guiding which excerpts are returned. \|
91	\| `maxCharacters` \| integer \| - \| Cap highlight characters per URL. Omit unless the caller has a strict budget. \|
92
93	### Summary object options
94
95	\| Parameter

People who liked this also viewed

6 picks

Type