AD pangolinfo-amazon-niche
Use when: 用户要"浏览/搜索 Amazon 类目树" / "批量把 categoryId 解析成完整路径面包屑" / "按销量/搜索量/退货率/竞争度筛类目" / "找低竞争蓝海利基(niche)" / "分析某类目销量趋势" / "browse Amazon category tree" / "find low-competition niches" / "filter categories by metrics". Covers: Amazon 底层类目 & 利基情报 —— 类目树下钻、关键词搜类目节点、批量类目路径解析、类目级商业指标筛选(销量/GMV/搜索量/退货率/价格档/竞争密度)、利基级筛选(搜索量×竞争×增长×退货率)。给 Agent 做自主选品类目挖掘与 BSR 验证。 NOT for: 抓具体商品/评论/榜单(用 pangolinfo-amazon-scraper)/ 完整 GTM 选品报告(用 amazon-product-explorer)/ 写 Listing(用 amazon-listing-optimization)/ Google 站外搜索(用 pangolinfo-ai-serp)。
As a process D 48/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:111High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"top5…Max": 0.40,
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:121High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)**经典蓝海组合**: 高 `sear…Min` + 低 `top5…Max`(≤0.40) + 适中 `productCountMax` + 正 `sear…Min` + 低 `retu…Max`。
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:150High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- ❌ snake_case 字段名（`niche_title` / `sear…min` / `top5…max`）—— 真实是 `nicheTitle` / `sear…Min` / `top5…Max`（products 不是 brands）。见 R-10。
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:323High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| `top5…max` | `top5…Max`（products 不是 brands）|
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:373High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| filter_niches 入参 | 传 `categoryId` | 只认 `nicheId`/`nicheTitle`;0-1 小数字段(`top5…Max`/`retu…Max`)别传整数 |
table
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "mcp_tools_used" - note
frontmatter-keyunknown frontmatter key "applies_to"
Process rating: all ten parameters 48/100
- 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
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 4409 tokens
- 100Steps. 68 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 20 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 tags): a typed call is more reliable
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
- +3Output format is not stated: the model decides each time
- -240 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 521: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 68 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.