citedy-content-ingestion

Name: citedy-content-ingestion
Author: citedy

17stars6forks

How to install citedy-content-ingestion?

citedy/citedy-seo-agent/citedy-content-ingestion

$npx -y skills add citedy/citedy-seo-agent --skill citedy-content-ingestion

Installs into the current project.

Summary

Turn any URL into structured content — YouTube videos (via Gemini Video API), web articles, PDFs, and audio files. Extract transcripts, summaries, and metadata for use in any LLM pipeline. Powered by Citedy.

Files · 1

View on GitHub

SKILL.md

1	# Content Ingestion — Skill Instructions
2
3	Connection: REST API over HTTPS
4	Base URL: `https://www.citedy.com`
5	Auth: `Authorization: Bearer $CITEDY_API_KEY`
6
7	---
8
9	## Overview
10
11	Turn any URL into structured content your agent can use. Pass a link — the skill extracts the full text, transcript, metadata, and summary — and returns it as clean structured data ready for your LLM pipeline.
12
13	Supported content types:
14
15	- YouTube videos — full transcription via Gemini Video API (not just captions)
16	- Web articles — clean article text with metadata
17	- PDF documents — text extraction from public PDF URLs
18	- Audio files — transcription from MP3/WAV/M4A files
19
20	Differentiator: YouTube ingestion uses the Gemini Video API for deep video understanding — it goes beyond auto-generated captions, capturing speaker intent, visual context, and structure.
21
22	Use this skill as a standalone input node for any LLM pipeline. Feed the output directly into summarization, Q&A, article generation, or knowledge base indexing.
23
24	---
25
26	## When to Use
27
28	Use this skill when the user:
29
30	- Asks to extract, transcribe, or summarize a URL
31	- Shares a YouTube video and wants the content analyzed or repurposed
32	- Shares a PDF link and wants the text extracted
33	- Wants to ingest audio content for transcription
34	- Is building a pipeline that needs to pull content from the web
35
36	---
37
38	## Instructions
39
40	### Setup
41
42	To authenticate, register your agent and obtain an API key:
43
44	1. Register your agent:
45
46	```
47	POST https://www.citedy.com/api/agent/register
48	Content-Type: application/json
49
50	{
51	"agent_name": "My Agent"
52	}
53	```
54
55	2. Approve the registration — you will receive an approval URL in the response. Open it in your browser to confirm.
56
57	3. Save your API key — after approval, the key (prefixed `citedy_agent_`) is returned. Store it as `CITEDY_API_KEY` in your environment.
58
59	All subsequent requests use `Authorization: Bearer $CITEDY_API_KEY`.
60
61	---
62
63	## Core Workflow
64
65	### Single URL Ingestion
66
67	Step 1 — Submit URL:
68
69	```
70	POST /api/agent/ingest
71	Authorization: Bearer $CITEDY_API_KEY
72	Content-Type: application/json
73
74	{
75	"url": "https://www.youtube.com/watch?v=example"
76	}
77	```
78
79	Returns `202 Accepted` with:
80
81	```json
82	{
83	"id": "job_abc123",
84	"status": "processing",
85	"poll_url": "/api/agent/ingest/job_abc123"
86	}
87	```
88
89	If the URL was already ingested (cache hit), returns `200 OK` with `"cached": true` — costs 1 credit.
90
91	Step 2 — Poll for completion:
92
93	```
94	GET /api/agent/ingest/{id}
95	```
96
97	Returns current status: `processing`, `completed`, or `failed`. Poll every 5–15 seconds. No credit cost.
98
99	Step 3 — Retrieve content:
100
101	```
102	GET /api/agent/ingest/{id}/content
103	```
104
105	Returns the full extracted content, transcript, and metadata. No credit cost.
106
107	---
108
109	### Batch Ingestion
110
111	Submit up to 20 URLs in a single request:
112
113	```
114	POST /api/agent/ingest/batch
115	Authorization: Bearer $CITEDY_API_KEY
116	Content-Type: application/json
117
118	{
119	"urls": [
120	"https://example.com/article",
121	"https://www.youtube.com/watch?v=abc",
122	"https://example.com/doc.pdf"
123	],
124	"callback_url": "https://your-service.com/webhook" // optional
125	}
126	```
127
128	Returns an array of job IDs. If `callback_url` is provided, a POST request is sent to it when all jobs complete.
129
130	---
131
132	### List Jobs
133
134	```
135	GET /api/agent/ingest?status=completed&limit=20&offset=0
136	```
137
138	Filter by status, paginate with limit/offset.
139
140	---
141
142	## Examples
143
144	### Example 1 — YouTube Video
145
146	User: "Transcribe this YouTube video: https://www.youtube.com/watch?v=dQw4w9WgXcQ"
147
148	```bash
149	# Step 1: Submit
150	curl -X POST https://www.citedy.com/api/agent/ingest \
151	-H "Authorization: Bearer $CITEDY_API_KEY" \
152	-H "Content-Type: application/json" \
153	-d '{"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"}'
154
155	# Step 2: Poll
156	curl https://www.citedy.com/api/agent/ingest/job_abc123 \
157	-H "Authorization: Bearer $CITEDY_API_KEY"
158
159	# Step 3: Get content
160	curl https://www.citedy.com/api/agent/ingest/job_abc123/content \
161	-H "Authorization: Bearer $CITEDY_API_KEY"
162	```
163
164	Response includes full transcript, video title, duration, and chapter breakdown.
165
166	---
167
168	### Example 2 — Web Article
169
170	User: "Extract the main content from https://techcrunch

People who liked this also viewed

6 picks

Type

citedy-content-ingestion

17stars6forks

View on GitHub

How to install citedy-content-ingestion?

citedy/citedy-seo-agent/citedy-content-ingestion

$npx -y skills add citedy/citedy-seo-agent --skill citedy-content-ingestion

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Content Ingestion — Skill Instructions
2
3	Connection: REST API over HTTPS
4	Base URL: `https://www.citedy.com`
5	Auth: `Authorization: Bearer $CITEDY_API_KEY`
6
7	---
8
9	## Overview
10
11	Turn any URL into structured content your agent can use. Pass a link — the skill extracts the full text, transcript, metadata, and summary — and returns it as clean structured data ready for your LLM pipeline.
12
13	Supported content types:
14
15	- YouTube videos — full transcription via Gemini Video API (not just captions)
16	- Web articles — clean article text with metadata
17	- PDF documents — text extraction from public PDF URLs
18	- Audio files — transcription from MP3/WAV/M4A files
19
20	Differentiator: YouTube ingestion uses the Gemini Video API for deep video understanding — it goes beyond auto-generated captions, capturing speaker intent, visual context, and structure.
21
22	Use this skill as a standalone input node for any LLM pipeline. Feed the output directly into summarization, Q&A, article generation, or knowledge base indexing.
23
24	---
25
26	## When to Use
27
28	Use this skill when the user:
29
30	- Asks to extract, transcribe, or summarize a URL
31	- Shares a YouTube video and wants the content analyzed or repurposed
32	- Shares a PDF link and wants the text extracted
33	- Wants to ingest audio content for transcription
34	- Is building a pipeline that needs to pull content from the web
35
36	---
37
38	## Instructions
39
40	### Setup
41
42	To authenticate, register your agent and obtain an API key:
43
44	1. Register your agent:
45
46	```
47	POST https://www.citedy.com/api/agent/register
48	Content-Type: application/json
49
50	{
51	"agent_name": "My Agent"
52	}
53	```
54
55	2. Approve the registration — you will receive an approval URL in the response. Open it in your browser to confirm.
56
57	3. Save your API key — after approval, the key (prefixed `citedy_agent_`) is returned. Store it as `CITEDY_API_KEY` in your environment.
58
59	All subsequent requests use `Authorization: Bearer $CITEDY_API_KEY`.
60
61	---
62
63	## Core Workflow
64
65	### Single URL Ingestion
66
67	Step 1 — Submit URL:
68
69	```
70	POST /api/agent/ingest
71	Authorization: Bearer $CITEDY_API_KEY
72	Content-Type: application/json
73
74	{
75	"url": "https://www.youtube.com/watch?v=example"
76	}
77	```
78
79	Returns `202 Accepted` with:
80
81	```json
82	{
83	"id": "job_abc123",
84	"status": "processing",
85	"poll_url": "/api/agent/ingest/job_abc123"
86	}
87	```
88
89	If the URL was already ingested (cache hit), returns `200 OK` with `"cached": true` — costs 1 credit.
90
91	Step 2 — Poll for completion:
92
93	```
94	GET /api/agent/ingest/{id}
95	```
96
97	Returns current status: `processing`, `completed`, or `failed`. Poll every 5–15 seconds. No credit cost.
98
99	Step 3 — Retrieve content:
100
101	```
102	GET /api/agent/ingest/{id}/content
103	```
104
105	Returns the full extracted content, transcript, and metadata. No credit cost.
106
107	---
108
109	### Batch Ingestion
110
111	Submit up to 20 URLs in a single request:
112
113	```
114	POST /api/agent/ingest/batch
115	Authorization: Bearer $CITEDY_API_KEY
116	Content-Type: application/json
117
118	{
119	"urls": [
120	"https://example.com/article",
121	"https://www.youtube.com/watch?v=abc",
122	"https://example.com/doc.pdf"
123	],
124	"callback_url": "https://your-service.com/webhook" // optional
125	}
126	```
127
128	Returns an array of job IDs. If `callback_url` is provided, a POST request is sent to it when all jobs complete.
129
130	---
131
132	### List Jobs
133
134	```
135	GET /api/agent/ingest?status=completed&limit=20&offset=0
136	```
137
138	Filter by status, paginate with limit/offset.
139
140	---
141
142	## Examples
143
144	### Example 1 — YouTube Video
145
146	User: "Transcribe this YouTube video: https://www.youtube.com/watch?v=dQw4w9WgXcQ"
147
148	```bash
149	# Step 1: Submit
150	curl -X POST https://www.citedy.com/api/agent/ingest \
151	-H "Authorization: Bearer $CITEDY_API_KEY" \
152	-H "Content-Type: application/json" \
153	-d '{"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"}'
154
155	# Step 2: Poll
156	curl https://www.citedy.com/api/agent/ingest/job_abc123 \
157	-H "Authorization: Bearer $CITEDY_API_KEY"
158
159	# Step 3: Get content
160	curl https://www.citedy.com/api/agent/ingest/job_abc123/content \
161	-H "Authorization: Bearer $CITEDY_API_KEY"
162	```
163
164	Response includes full transcript, video title, duration, and chapter breakdown.
165
166	---
167
168	### Example 2 — Web Article
169
170	User: "Extract the main content from https://techcrunch

People who liked this also viewed

6 picks

Type