SKILLEMALL.ai

BC web-crawler

Use this skill whenever the user wants to create Python web crawlers/scrapers based on a given URL. Supports Vue, React, Next.js, Nuxt, Angular, Svelte and other frontend architectures by analyzing API calls, handling dynamic content with headless browsers. Main language is Python. Features: - Static & dynamic crawling (requests, httpx, playwright, selenium, drissionpage) - JS reverse engineering (webpack unpacking, AST analysis, hook injection) - Anti-bot bypass (Cloudflare, Akamai, reCAPTCHA, fingerprint spoofing) - Login & session management (cookie, JWT, OAuth, signature replay) - Encryption & signing (AES/RSA/MD5/SHA, custom signing algorithms) - Pagination strategies (page number, cursor, waterfall, infinite scroll) - Data export (CSV, XLSX, JSON, SQLite, MySQL, MongoDB, images, files) - Distributed crawling (Redis queue, Scrapy-Redis, task scheduling) - Anti-detection (UA rotation, proxy pool, fingerprint randomization, behavior simulation) - Compliance (robots.txt, rate limiting, terms of service, legal boundaries) Triggers: "写爬虫", "爬取", "抓取数据", "scraper", "crawler", "scrape", "spider", "Vue 爬虫", "React 爬虫", "动态网页", "反爬", "加密参数", "签名"

ClawHub Agent Skills author: 末心 v1.0.0 MIT-0 2 files body ≈ 5 163 tokens Open the sourceclawhub.ai analyzed 2 d ago

Supports Vue, React, Next.js, Nuxt, Angular, Svelte and other frontend architectures by analyzing API calls, handling dynamic content with headless browsers.…

As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, progress reporting

GeneratorPlaywrightCloudflareExcelMySQLSoftware developmentSecuritytype and topics are labelled automatically from the skill text
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
100
Quality 40%
52
Run on models
none yet
Process rating
C
62/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Failures and branches w 10
50
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1191 chars, limit 1024
  • warning body-long SKILL.md body ≈ 5163 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 62/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5163 tokens
  • 85Steps. 80 steps, 2 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. No mutating operations
  • low 13 top-level sections: this looks like several domains in one skill

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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1190: 120–800 characters recommended
  • -242 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 6 example trigger phrases
  • +4Structure: 47 headings
  • +3Step-by-step instructions: 80 items
  • +3Output format is stated explicitly
  • +4Has examples (17 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.

External checks

ClawHub: suspicious
This skill is a disclosed web-scraping helper, but it also teaches anti-bot bypass, CAPTCHA handling, fingerprint spoofing, and session use that users should review carefully before installing.
LLM: suspicious (medium) · VirusTotal: · 22 Jun 2026