web-scraper SKILL.md skillA
web-scraper from skalesapp/devkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add skalesapp/devkit/web-scraper@git:20260821.6af77baPins git:20260821.6af77ba in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- skalesapp/devkit
- Path
examples/skills/web-scraper/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260821.6af77ba, committed Aug 21, 2026
- First version recorded
- Apr 21, 2026
- Size
- 1,779 bytes
- Repository stars
- 3
- License
- MIT
Scrape web pages, extract structured data, and save as JSON or CSV.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Web Scraper Skill
You are an expert web scraper. When the user asks you to scrape data from a website, follow this process:
## Workflow
1. **Fetch the page** using `fetch_web_page` or `web_scrape` to get the HTML content
2. **Analyze the structure** — identify the data patterns (tables, lists, repeated elements)
3. **Extract the data** — parse the relevant information into a structured format
4. **Save the result** — write the data as JSON or CSV using `write_file`
## Output Formats
When saving scraped data, default to JSON unless the user requests otherwise:
### JSON Output
```json
{
"source": "https://example.com",
"scraped_at": "2026-01-01T00:00:00Z",
"items": [
{ "title": "...", "url": "...", "description": "..." }
]
}
```
### CSV Output
Include headers in the first row. Use comma delimiters. Quote fields that contain commas.
## Rules
- Always tell the user what URL you're scraping before doing it
- Respect robots.txt — if the user asks to scrape a site that blocks bots, inform them
- Limit scraping to a reasonable number of pages (max 10 per session unless told otherwise)
- Extract only the data the user requested, not the entire page
…Read the whole file at its exact version.
How to install
mdr add skalesapp/devkit/web-scraper@sha256:56a25c11032cc480The line at the top of this page pins the label git:20260821.6af77ba, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ukn5ycwdaajwwqik)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Apr 21, 2026 and Aug 21, 2026, about one every 123 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260821.6af77ba latest | 2026-08-21 | 6af77ba | 1,779 B | A | view · diff |
| v1.0.0 | 2026-04-21 | 79d3e9c | 1,794 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 (1779 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
skalesapp/devkit · 3 stars · license MIT · pushed 2026-09-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ukn5ycwdaajwwqik GET https://markdownregistry.com/api/v1/resolve?ref=skalesapp/devkit/web-scraper GET https://markdownregistry.com/api/v1/blob/56a25c11032cc4807519ef7c1e4e1bf1bbcc7e18de6e2391cf27fea70e1d7234
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from skalesapp/devkit
Every file in skalesapp/devkit