AD finance-consumer-guard
金融消保合规护栏 (finance-consumer-guard) v1.0.0。 在银行理财 / 保险 / 基金 / 资管等金融产品的营销文案、销售话术、广告投放、官网介绍、 对外宣传发布前，实时检测"保本保收益（刚兑）、收益承诺夸大、风险弱化误导、 过往业绩误导、无资质代客理财、广告极限词"相关的高频违规 / 高风险表述， 按风险分级输出命中与整改建议，供 Agent 主动调用。区别于事后深度审计，这是事前拦截。 Use when: 需要在金融产品营销文案、销售话术、广告、官网介绍、对外宣传发布前， 实时拦截"保本保收益 / 稳赚不赔 / 低风险高收益 / 代客理财 / 最佳理财"等高频危险表述； 防止触碰资管新规（打破刚兑）、《商业银行理财业务监督管理办法》、 《理财公司理财产品销售管理暂行办法》、《保险销售行为管理办法》、 《广告法》第二十五条的金融消保红线；为金融机构 / 理财经理 / 合规 / 运营加装一道轻量实时护栏。 核心能力： - 🛡️ 实时检测 6 类高频危险表述：保本保收益(刚兑) / 收益承诺夸大 / 风险弱化误导 / 过往业绩误导 / 无资质代客理财 / 广告极限词 - 📊 风险分级（high / medium / low）与逐条整改建议 - 🔍 重叠命中智能去重（保留高 severity / 更长匹配），降低误报 - 📋 结构化 JSON 输出，便于 Agent 程序化调用与批量扫描 - 🧱 内核与规则分离：规则集中在 scripts/rules/terms.py，追加词即可扩展 触发关键词：保本保收益、稳赚不赔、低风险高收益、代客理财、最佳理财、金融消保、 理财合规、finance-consumer-guard、资管新规 适用范围：银行理财 / 保险 / 基金 / 资管等金融产品营销文案、销售话术、广告、官网介绍、对外宣传的发布前实时检测 运行模式：纯本地，零网络请求，零动态执行 外部依赖：Python 标准库（无需额外安装） 本产品为免费护栏，纯本地运行，零网络请求，文本输入即可评估。
金融消保合规护栏 (finance-consumer-guard) v1.0.0。 在银行理财 / 保险 / 基金 / 资管等金融产品的营销文案、销售话术、广告投放、官网介绍、 对外宣传发布前，实时检测"保本保收益（刚兑）、收益承诺夸大、风险弱化误导、 过往业绩误导、无资质代客理财、广告极限词"相关的高频违规 /…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 46/100
- 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
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 839 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)
- +3Description length 884: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (1 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.