BF xpeng-monitor
小鹏汽车综合数据监控工具，持续集成各市场、各维度的数据。 XPeng comprehensive data monitor, aggregating metrics across markets and dimensions. 目前已支持（其他数据持续补充中）： - 【中国市场】各车型配置版本的交付周期（单位：周） - 【欧洲市场】纯电动车（BEV）日更交付/上牌销量，支持最近 12 个月环比对比 Currently supported (more data to be added): - China: vehicle model delivery lead time / wait time in weeks - Europe: BEV daily registration/delivery volume with 12-month MoM comparison 当用户提到以下任何场景时，都应使用此 Skill： **中国市场交付周期：** - "小鹏交付周期"、"小鹏交付时间"、"小鹏提车周期"、"小鹏提车时间"、"小鹏交付监控"、"小鹏交付周期监控" - "小鹏购车要等多久"、"小鹏订车到提车要多久"、"小鹏什么时候能提车"、"小鹏等车多久" - "小鹏G6交付多久"、"小鹏GX交付周期"、"G7等几周"、"小鹏M03多久能到"、"P7+提车时间" - "查询小鹏车型交付"、"小鹏各配置交付周期"、"小鹏交付数据" - 小鹏具体车型名称：G6、G9、GX、G7、P7、P7+、M03、X9、F30 等结合交付/提车/等车话题 - XPeng delivery time, XPeng delivery lead time, XPeng delivery wait, XPeng wait time, XPeng delivery period, XPeng delivery estimate, XPeng delivery weeks, XPeng delivery schedule - When will my XPeng be delivered, XPeng how long to deliver **欧洲市场交付销量：** - "小鹏欧洲销量"、"小鹏欧洲交付"、"小鹏欧洲上牌"、"小鹏海外销量"、"小鹏欧洲数据" - "XPeng欧洲销量"、"XPeng欧洲交付"、"XPeng Europe delivery"、"XPeng Europe sales" - "小鹏欧洲市场"、"小鹏出海"、"XPeng EU"、"XPeng海外" - "小鹏欧洲纯电动"、"小鹏BEV"、"XPeng registrations"、"XPeng European market data" - XPeng Europe registrations, XPeng EU sales, XPeng European market data, XPeng BEV Europe **通用入口：** - "/xpeng-monitor" **隐式命中规则：** - 当用户询问小鹏汽车某个/某些车型的交付等待时间、提车周期、订车到交付需要多久时，即使没有明确说"交付周期"，也使用此 Skill - 当用户询问小鹏在欧洲的销量、交付数据、上牌量、市场份额时，也使用此 Skill - When a user asks about XPeng vehicle delivery time, wait time, or lead time for any model, even without explicitly saying "delivery", use this Skill - When a user asks about XPeng Europe delivery/sales/registration volume or market share, use this Skill
小鹏汽车综合数据监控工具，持续集成各市场、各维度的数据。 XPeng comprehensive data monitor, aggregating metrics across markets and dimensions.
As a process F 35/100 · Will not run — References files that are not bundled: scripts/fetch_car_series.js, scripts/.eu-session.json
How to improve
- Shorten the description to 1024 characters.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1663 chars, limit 1024 - warning
missing-refreference to a missing file: scripts/fetch_car_series.js - warning
missing-refreference to a missing file: scripts/.eu-session.json - note
description-budgetdescription takes 1663 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 35/100
- 0Tools and files. 2 referenced file(s) missing: scripts/fetch_car_series.js, scripts/.eu-session.json
- 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. 73 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3560 tokens
- 100Running it twice. No mutating operations
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1662: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 34 example trigger phrases
- +4Structure: 32 headings
- +3Step-by-step instructions: 73 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.