SKILLEMALL.ai
GitHub ↗ RU Sign in

BB scraper-builder

Build production-ready web scrapers for any website using Bright Data infrastructure. Guides you through site analysis, API selection, selector extraction, pagination handling, and complete scraper implementation. Use this skill whenever the user wants to build a scraper, create a crawler, extract data from a website, scrape product pages, handle pagination, build a data pipeline from a web source, or automate data collection from any site — even if they don't explicitly say 'scraper'. Triggers on phrases like 'build a scraper for', 'scrape data from', 'extract products from', 'crawl pages on', 'get data from [website]', or 'I need to pull data from'.

ClawHub Agent Skills author: Meir Kadosh v1.0.0 MIT-0 7 files body ≈ 7 019 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, consistency, progress reporting

GeneratorInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
89
Quality 40%
81
Run on models
none yet
Process rating
B
71/100
Nearly there
Progress reporting w 2
0
Inputs and preconditions w 11
30
Consistency w 8
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

✓ No critical or high findings

Medium and low: 3
  • medium Exfiltration net-credential-use references/supported-domains.md:18
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: Bearer $BRIGHTDATA_API_KEY" \
  • medium Exfiltration net-credential-use SKILL.md:52
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: Bearer $BRIGHTDATA_API_KEY" \
  • low Exfiltration net-credential-use SKILL.md:692
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    **Solution:** Verify the key is set: `echo $BRIGHTDATA_API_KEY`. Get a fresh key from `https://brightdata.com/cp/setting/users`.
    quoted

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7019 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 71/100

  • 0Progress reporting. Says nothing while it works
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (scraper-builder) differs from the folder (brightdata-scraper-builder)
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 7019 tokens
  • 100Steps. 74 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 6 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 13 top-level sections: this looks like several domains in one skill
  • medium 3 test cases, all positive: not one "should refuse" or "should ask first"

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +3Description length 659: enough signal without eating the budget
  • +4Structure: 36 headings
  • +3Step-by-step instructions: 74 items
  • +3Output format is stated explicitly
  • +4Has examples (15 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

External checks

ClawHub: clean
This is an instruction-only Bright Data scraper-building skill with expected external API use, but users should understand it sends target URLs and fetched content to Bright Data.
LLM: benign (high) · VirusTotal: · 29 May 2026