web-crawler skillA
web-crawler is agent-read markdown (skill) from starchild-ai-agent/official-skills: 'Web scraping plus social data: YouTube, TikTok, Instagram, LinkedIn,.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
## Preferred entry: call exports.py (don't hand-roll requests)
Ready-made helpers live in `skills/web-crawler/exports.py`. Prefer them over
writing your own `proxied_get`/`proxied_post` calls — they already inject the
proxy credentials, so **there is no API key to find** (don't read
`$SCRAPECREATORS_API_KEY` / `$FIRECRAWL_API_KEY`, don't check `.env`, don't ask
the user).
```python
import sys; sys.path.insert(0, "/data/workspace/skills/web-crawler")
from exports import scrape_markdown, youtube_transcript, sc_get
scrape_markdown("https://example.com/article") # Firecrawl fallback
youtube_transcript("https://youtube.com/watch?v=ID") # ScrapeCreators
youtube_video("https://youtube.com/watch?v=ID") # metadata: title/description/uploader (+ transcript)
sc_get("/v1/tiktok/profile", handle="charlidamelio") # any SC endpoint
from exports import archive_fallback # paywall / Firecrawl-403
archive_fallback("https://www.nytimes.com/.../article.html") # archive snapshot
```
### Transcript route — ONE entry for any media link
```python
from core.skill_tools import web_crawler
r = web_crawler.get_transcript(url, caller_id="chat:<thread>")
…Read the whole file at its exact version.
How to install
mdr add starchild-ai-agent/official-skills/web-crawler@v2.11.0mdr add starchild-ai-agent/official-skills/web-crawler@sha256:35b716a97c466effPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_3twvpujejay5pulo)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.11.0 latest | 2026-09-17 | ae5f3e8 | 34,700 B | A | view · diff |
| v2.10.0 | 2026-09-17 | ce6c3ca | 34,353 B | A | view · diff |
| v2.9.0 | 2026-09-17 | 72674c4 | 34,100 B | A | view · diff |
| v2.8.0 | 2026-09-17 | 8047f30 | 34,128 B | A | view · diff |
| v2.7.0 | 2026-09-17 | 341c94c | 33,531 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (34700 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
starchild-ai-agent/official-skills · 28 stars · license none · pushed 2026-09-18 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3twvpujejay5pulo GET https://markdownregistry.com/api/v1/resolve?ref=starchild-ai-agent/official-skills/web-crawler GET https://markdownregistry.com/api/v1/blob/35b716a97c466eff522ba80c7fba76fbb871196f46aa099d268c37e739965e6f
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.