AD amazon-review-intelligence
ARI 官方 Amazon 评论采集与消费者洞察 Skill。通过 ARI API 订阅 ASIN、采集评论、 查看星级/关键词/趋势、生成 VOC 或深度洞察报告，并给出痛点、购买动因、用户画像、 使用场景、改进机会和 Listing 建议。**支持开启定期采集持续跟踪新评论**，报告可与上一份 做环比（已解决/新出现/持续恶化），并提供类目雷达（本品 vs 竞品周走势）、高赞差评榜、 情感预警、类目对标排行、差评工作台（AI 回复建议）与评论/报告导出。 Use when the user asks about Amazon review analysis, voice of customer, pain points, complaints, sentiment, consumer insights, competitor reviews, listing copy, review alerts, category benchmark, review reply, review export, review monitoring, scheduled collection, trend over time, report comparison, 评论分析、消费者洞察、差评、卖点、竞品对比、差评预警、行业对标、差评回复、评论导出、 评论监控、定期采集、持续跟踪、报告环比、高赞差评。 Requires an ARI API key (ari_live_*).
ARI 官方 Amazon 评论采集与消费者洞察 Skill。通过 ARI API 订阅 ASIN、采集评论、 查看星级/关键词/趋势、生成 VOC 或深度洞察报告，并给出痛点、购买动因、用户画像、 使用场景、改进机会和 Listing 建议。支持开启定期采集持续跟踪新评论，报告可与上一份…
As a process D 45/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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
- 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
-
medium Exfiltration
net-redirectable-api-keyscripts/ari.py:55Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 8. 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 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (amazon-review-intelligence) differs from the folder (amazon-voc)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 51 steps
- 100Execution cost. Instruction body is 1625 tokens
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 640: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.