AD shop-ad-guard
电商广告合规护栏 (shop-ad-guard) v1.0.0。 在商品标题、详情页、直播话术、促销文案发布前，实时检测高频违规用语， 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: 需要在发布电商文案（标题/详情/直播话术/促销）前，实时拦截 绝对化用语、医疗功效违规宣称、虚假夸大、虚假促销、比较贬低、迷信诱导等 高频违规表达；防止触碰《广告法》第九条（罚款 20 万起）、第十七条等红线； 为商家/运营/主播加装一道轻量实时合规护栏。 核心能力： - 🛡️ 实时检测 6 类高频违规用语：绝对化用语 / 医疗功效宣称 / 虚假夸大 / 虚假促销 / 比较贬低 / 迷信诱导 - 📊 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：电商合规、广告法、极限词、绝对化用语、违规词检测、直播话术合规、 商品标题审核、促销合规、广告违规拦截、shop-ad-guard、广告法第九条 适用范围：电商商品标题 / 详情页 / 直播话术 / 促销文案的发布前实时检测 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。
电商广告合规护栏 (shop-ad-guard) v1.0.0。 在商品标题、详情页、直播话术、促销文案发布前，实时检测高频违规用语， 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: 需要在发布电商文案（标题/详情/直播话术/促销）前，实时拦截…
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 866 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 688: enough signal without eating the budget
- +4Structure: 16 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: 87.