AC geo-poison-detector
AI推荐防投毒检测器 / AI Recommendation Poison Detector. 你有没有遇到过：AI推荐了一款产品，买回来才发现是劣质品或根本不存在的品牌？这就是GEO投毒——不法商家花钱批量制造虚假软文，让AI误以为这些产品是市场上的优质选择。这个skill帮你识破这些陷阱。三种使用方式：(1) 自动防护：每当AI向你推荐产品时，自动附上风险标记🟢🟡🔴，无需任何操作；(2) 主动检测：发送「检测 产品名」或「/check product name」，立即获得该产品的可信度分析；(3) 链接检测：把一篇产品推荐文章的链接发给AI，自动分析文章是否为投毒软文。支持国内外产品，中英文双语，覆盖淘宝/京东/Amazon等主流平台验证。无需任何API密钥，开箱即用。 | EN: Protects you from fake AI product recommendations planted by bad actors (GEO poisoning). Auto-flags suspicious products when AI recommends them, lets you quick-check any product by name, and analyzes article URLs for soft-ad poisoning patterns. Supports CN and Global markets, Chinese and English. No API keys needed.
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
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: 4. 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 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 37 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1451 tokens
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)
- +1No license
- +2Single-language instructions
- +3Description length 668: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 37 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.