AC amazon-scraper
Containerized Amazon.com scraper (Docker + Playwright) for BSR/new-releases/movers rankings, keyword search results, and product detail pages. Requires a paid ISP/residential proxy. Use when the request is specifically about Amazon product or marketplace data: 亚马逊/Amazon, ASIN, BSR, Best Sellers, 畅销榜, 新品榜, 飙升榜, 选品, 竞品分析, 类目分析, listing 分析, 月销量 (bought in past month), 评分分布, 评论分析, Amazon 关键词搜索结果, Amazon 产品详情. Do NOT use for general-purpose web scraping just because the user said 爬取/抓取/采集/scrape/crawl. Every run spends metered proxy bandwidth, and the generic mode exists only as a fallback for pages related to an Amazon task. For unrelated sites prefer web_search/web_fetch, or ask first.
Containerized Amazon.com scraper (Docker + Playwright) for BSR/new-releases/movers rankings, keyword search results, and product detail pages. Requires a paid…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-privilegeassets/fingerprint.js:177Privilege escalation / world-writable permissions (string literal in code, not executed)'--disable-setuid-sandbox',
code literal
Files scanned: 31. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 76 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3157 tokens
- low 10 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- -33 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 692: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 76 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (12 of 13)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.