BF industrial-park-investment-assistant
产业园招商 AI 个人助手。面向招商人员，四步工作流：今天客户 → 客户情况 → 客户推进 → 处理完成。 AI 贯穿全程（排序优先级·推荐下一步·分析客户·自动记录），不替代人做决策。 核心场景：客户管理·房源查询·客户接待·报价方案·选址建议·合同生成·渠道管理。 含时效性校验、No Agency护栏（金额让步需审批）、每日09:00自动推送今日客户列表。 支持多项目架构和知识库分离（SQLite本地库 + IMA知识库）。
产业园招商 AI 个人助手。面向招商人员，四步工作流：今天客户 → 客户情况 → 客户推进 → 处理完成。 AI 贯穿全程（排序优先级·推荐下一步·分析客户·自动记录），不替代人做决策。 核心场景：客户管理·房源查询·客户接待·报价方案·选址建议·合同生成·渠道管理。 含时效性校验、No…
As a process F 35/100 · Will not run — References files that are not bundled: templates/跟进邮件模板.md, templates/带看总结模板.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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
-
medium Broad scope
meta-agent-memory-dumpIDENTITY.mdAgent memory / workspace files bundled with the skill (2) — likely a workspace dump with personal data or tokensIDENTITY.md, SOUL.md
Files scanned: 61. 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 ≈ 18438 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: templates/跟进邮件模板.md - warning
missing-refreference to a missing file: templates/带看总结模板.md - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 35/100
- 0Tools and files. 2 referenced file(s) missing: templates/跟进邮件模板.md, templates/带看总结模板.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 10Execution cost. Instruction body is 18438 tokens: crowds the task out of the window
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 607 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 31 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
- -5TODO / placeholder text left in the skill
- -2258 emoji in the instructions: noise for the model
- -313 of 24 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 216: enough signal without eating the budget
- +4Structure: 149 headings
- +3Step-by-step instructions: 607 items
- +4Has examples (85 code blocks)
- +4Reference files are cited in the instructions (9 of 13)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 46.