BF cnsdoce
中国工程造价技能，支持安装工程/建筑工程/市政工程/园林绿化工程定额查询、组价计算与报价表生成。 数据源支持两种模式（见下方说明）： · 默认模式：大模型推理数据（无需本地数据库，推荐新手） · 唯一来源模式：严格限定为山东省消耗量定额(2025版) + 济南市价目表(2026版) 核心依据：《建设工程工程量清单计价标准》GB/T 50500-2024（2025年9月1日起实施）。 当用户询问以下场景时触发本技能：定额子目查询（章节号+条款号溯源）、 安装工程组价（13分册）、建筑工程/市政工程/园林绿化工程取费计算、 Excel报价表生成、山东/济南价目表查询。 技能内置 quota_reference.db（34条全专业费率）与 fee_standard.md（完整取费标准）。 ⚡v2.0.0：组价前强制比对清单单位与定额单位（Step 0）；LLM端点迁移TokenHub； 信息价更新至2026年第6期；新增AI组价引擎/价格自检/指标引擎三大能力。
中国工程造价技能，支持安装工程/建筑工程/市政工程/园林绿化工程定额查询、组价计算与报价表生成。 数据源支持两种模式（见下方说明）： · 默认模式：大模型推理数据（无需本地数据库，推荐新手） · 唯一来源模式：严格限定为山东省消耗量定额(2025版) + 济南市价目表(2026版)…
As a process F 34/100 · Will not run — References files that are not bundled: assets/quota_reference.db, assets/报价模板.xlsx
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-high-entropy-tokenscripts/search_quota.py:483High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)model = SentenceTransformer('para…-v2')quoted
Files scanned: 32. 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
body-longSKILL.md body ≈ 7042 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: assets/quota_reference.db - warning
missing-refreference to a missing file: assets/报价模板.xlsx - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 34/100
- 0Tools and files. 2 referenced file(s) missing: assets/quota_reference.db, assets/报价模板.xlsx
- 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
- 70Execution cost. Instruction body is 7042 tokens
- 100Steps. 166 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 21 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -263 emoji in the instructions: noise for the model
- -31 of 9 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 434: enough signal without eating the budget
- +4Structure: 85 headings
- +3Step-by-step instructions: 166 items
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (6 of 19)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 48.