LeoYeAI/agent-master-skills / skills/anti-seo-researcher
anti-seo-researcher
VerifiedAnti-SEO deep consumer research tool. When a user wants to buy a product or make a consumer decision, use this Skill. Automatically detects user language and adapts to regional platforms and search strategies. Works with or without web_search — gracefully degrades to built-in Bing scraping when web_search is unavailable.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 21.2 KB |
| SKILL.md | skill md | 23.7 KB |
| _meta.json | config | 290 B |
| examples/category_profile_gaming_chair.json | config | 5.6 KB |
| examples/category_profile_office_chair_en.json | config | 7.2 KB |
| examples/task_config_gaming_chair.json | config | 413 B |
| examples/task_config_office_chair_en.json | config | 448 B |
| references/SKILL_REFERENCE.md | markdown | 10.2 KB |
| references/credibility_rules.md | markdown | 6.5 KB |
| scripts/ai_credibility_analyzer.py | script | 18.1 KB |
| scripts/brand_scorer.py | script | 17.7 KB |
| scripts/conflict_resolver.py | script | 20.2 KB |
| scripts/credibility_scorer.py | script | 34.8 KB |
| scripts/deep_dive_search.py | script | 40.3 KB |
| scripts/generate_report.py | script | 24.7 KB |
| scripts/platform_search.py | script | 54.1 KB |
| scripts/web_search_fallback.py | script | 14.5 KB |
examples/category_profile_gaming_chair.json
View on GitHub{
"category": "电竞椅",
"category_type": "durable_goods",
"evaluation_dimensions": [
{
"name": "坐感舒适度",
"weight": 0.30,
"description": "久坐体验,包括坐垫软硬、腰部支撑、头枕舒适度、坐姿引导",
"key_parameters": ["坐垫填充材料", "腰靠调节范围", "头枕高度调节", "坐深调节", "座椅宽度"],
"data_sources": ["用户长期使用反馈", "人体工学评测", "久坐体验报告"]
},
{
"name": "透气散热",
"weight": 0.20,
"description": "网布材质透气性、夏天久坐闷热程度、出汗体验",
"key_parameters": ["网布材质类型", "网布克重/密度", "坐垫透气设计", "靠背透气面积"],
"data_sources": ["夏季使用反馈", "材质测评", "长期使用体验"]
},
{
"name": "做工与耐久性",
"weight": 0.20,
"description": "用料质量、组装精度、长期使用后的耐久表现(气压棒、轮子、扶手、网布松弛)",
"key_parameters": ["气压棒等级", "底盘材质", "滚轮类型", "扶手材质", "网布耐久性", "质保年限"],
"data_sources": ["1年以上使用报告", "拆解评测", "售后反馈"]
},
{
"name": "功能调节",
"weight": 0.15,
"description": "可调节维度(扶手、靠背角度、坐深、腰靠高度等),调节便利性",
"key_parameters": ["扶手调节维度(1D/2D/3D/4D)", "靠背后仰角度", "腰靠调节方式", "坐深可调", "座椅升降范围"],
"data_sources": ["评测对比", "用户反馈"]
},
{
"name": "性价比",
"weight": 0.15,
"description": "相对于同价位竞品的配置水平、用料水平、品牌溢价合理性",
"key_parameters": ["价格", "同价位竞品配置对比", "促销价格", "赠品/配件"],
"data_sources": ["价格对比", "促销信息", "用户性价比评价"]
}
],
"pain_point_keywords": {
"safety": ["气压棒爆炸", "底盘断裂", "倾倒", "甲醛超标", "气味刺鼻"],
"quality": ["网布松弛", "坐垫塌陷", "扶手断裂", "螺丝松动", "气压棒下沉", "轮子碎裂", "掉漆", "开裂", "异响", "生锈"],
"experience": ["久坐腰疼", "坐着闷热", "硌屁股", "头枕不舒服", "扶手太硬", "坐垫太窄", "腰靠顶腰", "坐深不够"],
"trust": ["虚假宣传", "刷单", "水军", "好评返现", "广告软文", "实物与图片不符", "虚标参数"]
},
"safety_risk_types": {
"critical": ["气压棒爆炸", "底盘断裂致伤"],
"high": ["甲醛超标", "有害气体释放", "倾倒风险"],
"medium": ["气压棒下沉", "滚轮碎裂"],
"low": ["螺丝松动", "异响"]
},
"platform_relevance": {
"v2ex": 0.85,
"chiphell": 0.90,
"nga": 0.80,
"smzdm": 0.75,
"zhihu": 0.60,
"tieba": 0.70,
"xiaohongshu": 0.35,
"douban": 0.40,
"bilibili": 0.70
},
"category_positive_signals": [
{"pattern_description": "提到具体使用时长", "regex_hint": "用了[半一二三四五六七八九十\\d]+[年个月天]", "score": 15, "label": "长期用户"},
{"pattern_description": "身高体重匹配讨论", "regex_hint": "(身高|体重|\\d{3}cm|\\d{2,3}斤|\\d{2,3}kg)", "score": 10, "label": "体型适配反馈"},
{"pattern_description": "多椅对比体验", "regex_hint": "(之前|以前|换过|对比|从.*换)", "score": 12, "label": "多品对比"},
{"pattern_description": "拆解或细节展示", "regex_hint": "(拆[解开]|内部|用料|气压棒[等级型号]|底盘)", "score": 12, "label": "拆解评测"},
{"pattern_description": "久坐后腰部反馈", "regex_hint": "(腰[不没]?[酸疼痛]|腰部支撑|护腰)", "score": 10, "label": "腰部体验反馈"}
],
"has_variant_issue": true,
"variant_types": ["网布款vs皮质款", "标准版vs高配版", "不同尺码(S/M/L)"],
"variant_search_keywords": ["网布", "透气", "mesh"],
"non_commercial_indicators": [
"用了一年后来更新",
"当初买的时候没做功课",
"自费购买",
"不是广告",
"第N把椅子了",
"坐了半年回来补评"
],
"commercial_bias_sources": [
"品牌官方旗舰店好评",
"什么值得买爆料含返利链接",
"带有优惠券/返利链接的推荐",
"品牌赞助的UP主评测",
"带有#广告 #推广标签的内容"
],
"ecommerce_search_strategy": {
"enabled": true,
"primary_platforms": ["京东", "淘宝"],
"search_templates": {
"review_aggregation": ["[商品] 京东评论 追评 真实", "[商品] 淘宝评价 追评 差评"],
"negative_reviews": ["[商品] 京东差评 一星 退货", "[商品] 淘宝差评 避坑 后悔"],
"long_term_reviews": ["[商品] 追评 半年 一年 使用感受", "[商品] 京东追评 长期使用"]
},
"high_value_indicators": ["追评", "用了几个月后", "补充评价", "再来更新"],
"low_value_indicators": ["默认好评", "好评返现", "此用户未填写评价"]
},
"comment_section_strategy": {
"enabled": true,
"primary_platforms": ["小红书", "知乎"],
"search_templates": {
"debunk_feedback": ["[商品] 小红书 评论区 真实", "[商品] 种草 拔草 后悔"],
"experience_sharing": ["[商品] 买了 翻车 评论", "[商品] 知乎 评论区 实际体验"]
},
"high_value_indicators": ["我也买了", "同款翻车", "用了之后发现", "评论区才是真相"],
"low_value_indicators": ["求链接", "已入手", "好种草"]
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |