BF b2b-product-search
给企业采购人（买家）用的找货比价助手：覆盖工业设备、机械加工、五金配件、电子电气、 化工原料、检测仪器、包装耗材、农林牧渔等 B2B 常购品类，把一句"要买什么"变成一份 能直接比价的候选商品清单，每款商品带可点击的商品详情页与供应商报价，供采购比价选型、 直接进店询价。接住商品词及规格型号约束（材质/功率/尺寸/型号/容量/压力等，如 304不锈钢法兰、5匹冷水机、2.2kW电机、PA66塑料粒子、dn50球阀），以及预算、发货地、 数量等口语化采购需求 → 归一成检索条件 → 查在售商品库（爱采购及已授权平台， 来源平台随结果标注）→ 归一价格、规格、起订量 → 输出带链接的候选清单 （文本/Markdown/HTML 三形态可选）。只报取到的商品与展示价，取不到就说取不到， 绝不编价、编货期、编供应商；只做查询整理，不代下单、不代发询盘； 联系方式不直出，由用户点击跳转查看。 触发词: 采购帮我找货, 想买…推荐几个, 这个多少钱, 哪家便宜, 预算…以内找, 报价对比, 整理采购清单, 起订量多少, 现货在哪, 有没有卖…的, 选型比价
给企业采购人（买家）用的找货比价助手：覆盖工业设备、机械加工、五金配件、电子电气、 化工原料、检测仪器、包装耗材、农林牧渔等 B2B 常购品类，把一句"要买什么"变成一份 能直接比价的候选商品清单，每款商品带可点击的商品详情页与供应商报价，供采购比价选型、…
As a process F 35/100 · Will not run — References files that are not bundled: 详情页链接
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: 详情页链接
Process rating: all ten parameters 35/100
- 0Tools and files. 1 referenced file(s) missing: 详情页链接
- 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
- 20When it triggers. No condition that starts the skill
- 100Steps. 34 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 804 tokens
- 100Running it twice. No mutating operations
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 479: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 34 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: 73.