CF forklift-expert
[Bilingual / 中英双语]叉车(工业车辆)领域专家技能。覆盖品牌、产品、参数、 技术、液压、电池、选型、维修、故障诊断、配件、维保、二手评估、国标/ISO/EN 法规、标准检索、市场行情与销量排行。 Forklift & industrial truck expert: brands, specifications, hydraulics, batteries, selection, troubleshooting, parts, maintenance, standards (GB / ISO / EN / OSHA), market data and sales ranking. 语言规则(Language rule):用户用什么语言提问,就用同一语言作答。 中文提问 → 中文输出 + 中文检索通道;英文提问 → 英文输出 + Google 英文 检索通道(Google 不可达时自动降级 Bing 英文版)。 Reply in the same language as the user's query. English queries are answered in English and searched through the Google English channel. 当用户问题涉及叉车或与叉车直接相关的工业车辆时使用本技能。 触发场景(中文):叉车、电叉、柴油叉车、锂电叉车、铅酸叉车、平衡重叉车、 前移式叉车、堆高车、托盘车、AGV、杭叉、合力、柳工、比亚迪叉车、林德、 丰田叉车、永恒力、卡尔玛、港口叉车、冷库叉车、防爆叉车、越野叉车、 集装箱叉车、起升重量、货叉、门架、液压、电池、电机、控制器、BMS、 充电桩、能耗、GB/T 43756、GB/T 44679、GB/T 43657、ISO 23308、 TSG 11、叉车驾照 N1/N2、特种设备责任险、AGV 渗透率、锂电渗透率、 叉车销量、叉车出口、叉车报废、叉车禁用、二手叉车、维保计划、配件 选型、应急处置、标准检索、标准查询、查标准、最新叉车标准、标准全文、 标准状态、标准替代、标准实施日期、叉车销售排行、叉车市场份额、 国产叉车 vs 进口叉车、叉车月报。 触发场景(英文):forklift, electric forklift, diesel forklift, lithium forklift, lead-acid forklift, counterbalance, reach truck, pallet jack, pallet stacker, AGV, AMR, Hangcha, Heli, LiuGong, BYD forklift, Linde, Toyota forklift, Jungheinrich, Konecranes, Kalmar, container handler, explosion-proof forklift, rough terrain forklift, forklift battery, forklift BMS, forklift charging, forklift energy efficiency, ISO 23308, ISO 3691, TSG 11, forklift operator license, special equipment insurance, AGV market share, lithium forklift penetration, forklift sales, forklift sales ranking, forklift market share, forklift export, forklift end-of-life, used forklift, forklift maintenance, forklift parts. 排除场景(不触发 / Excluded):挖掘机 excavator、装载机 loader、推土机 bulldozer、起重机 crane(履带吊/汽车吊)、堆高机(非 ISO 5053 定义)、 AGV 在非叉车领域(如搬运机器人 AMR 通用调度)、叉车二手交易平台报价、 与叉车无关的物流设备。 关键能力 / Key capabilities: (1) 品牌·产品·参数 Brands & specs:brands.md 定位 + web_search 实时校验 (2) 选型·技术·维修 Selection & troubleshooting (3) 配件·维保 Parts & maintenance (4) 二手评估 Used forklift evaluation (5) 标准·法规 Standards & regula
As a process F 31/100 · Will not run — References files that are not bundled: references/standard-retrieval.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 2365 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/standard-retrieval.md - note
description-budgetdescription takes 2365 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "updated" - note
frontmatter-keyunknown frontmatter key "author_contact" - note
frontmatter-keyunknown frontmatter key "copyright" - note
frontmatter-keyunknown frontmatter key "license_full"
Process rating: all ten parameters 31/100
- 0Tools and files. 1 referenced file(s) missing: references/standard-retrieval.md
- 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
- 40Consistency. Frontmatter name (forklift-expert) differs from the folder (forklift)
- 100Steps. 116 steps
- 100Execution cost. Instruction body is 3458 tokens
- 100Running it twice. No mutating operations
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 2364: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 30 headings
- +3Step-by-step instructions: 116 items
- +4Has examples (15 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 33.