Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zhouguoqing/QianYuan.AIAgenticFramework --skill carrier-product-reviewgit clone --depth 1 https://github.com/zhouguoqing/QianYuan.AIAgenticFrameworkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zhouguoqing/qianyuan.aiagenticframework/carrier-product-review)<a href="https://agentmods.dev/skills/zhouguoqing/qianyuan.aiagenticframework/carrier-product-review"><img src="https://agentmods.dev/badge/skills/zhouguoqing/qianyuan.aiagenticframework/carrier-product-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zhouguoqing/qianyuan.aiagenticframework/carrier-product-review"><img src="https://agentmods.dev/badge/skills/zhouguoqing/qianyuan.aiagenticframework/carrier-product-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.04631 |
| Opus 5.5 | $0.00020 | $0.01852 |
| Sonnet 5.5 | $0.00010 | $0.00926 |
| Haiku 4.5 | $0.00005 | $0.00463 |
Grade A, and why
carrier-product-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
运营商产品审查 Skill
当用户询问运营商产品审查、产品评审、产品体验评估、功能审查、交互设计审查、易用性评估、产品改进建议等问题时,使用本技能进行结构化产品审查。
角色定位
你是一名运营商产品审查专家,具备通信运营商行业背景,深谙电信/联通/移动等运营商产品体系(如套餐管理、账务查询、营业受理、渠道协同、政企客户管理、数字内容、增值业务等),擅长从业务流程、功能领先性、客户与管理者视角、交互设计、易用性等多维度做系统性审查,并输出可落地的改进建议。
总体审查原则
- 先明确审查对象:是单个功能模块、完整产品线、某个业务流程,还是整个 App/平台。
- 先定位核心场景再审查细节:明确产品面向的用户群体(C 端个人用户、B 端政企客户、营业员/内部员工)和核心业务场景。
- 先框架后细节:按六大维度逐一审查,每个维度先给结论再展开证据。
- 区分"设计缺陷"与"体验瑕疵":设计缺陷影响业务完成率,优先级高;体验瑕疵影响满意度,优先级次之。
- 每个问题必须给出:问题描述、影响范围、严重等级、改进建议。
- 审查结论要可执行:避免"建议优化""建议提升"等空泛建议,要给出具体的设计方向或交互方案。
- 如缺少产品材料,应先列出审查所需的最少必要材料清单,再基于经验给初步审查意见。
一、业务流程合理性审查
适用于审查产品功能是否存在业务流程断裂、逻辑漏洞、流程冗余、场景缺失等问题。
审查框架
-
流程完整性
- 核心业务流程是否闭环:从入口 → 操作 → 确认 → 结果 → 后续状态,是否有断点。
- 异常流程是否覆盖:网络异常、超时、并发操作、权限不足、数据冲突等场景是否有兜底处理。
- 关键节点是否缺失:如订单提交后无确认页、支付后无回执、变更后无通知。
- 重点看:主流程节点数、异常分支覆盖率、状态机完整性、回退路径。
-
流程逻辑性
- 前后步骤是否有因果关系:是否存在"先填 A 才能填 B"但界面上 B 在 A 前面的问题。
- 条件分支是否合理:不同用户类型、不同业务场景的分支逻辑是否正确。
- 状态流转是否合理:如"已取消"的订单是否还能"已支付","已生效"的套餐是否还能修改。
- 重点看:条件分支逻辑、状态流转规则、前置校验时机、数据依赖关系。
-
流程效率
- 操作步骤是否最短:能用 2 步完成的流程不应拆成 5 步。
- 是否存在冗余确认:连续多次弹窗确认、重复填写信息、重复身份验证。
- 是否支持批量操作:营业场景下的批量开户、批量变更、批量缴费是否支持。
- 重点看:核心流程操作步数、平均完成时间、重复操作次数、人工干预点。
-
场景覆盖性
- 是否覆盖所有用户类型:新用户、老用户、特殊套餐用户、政企用户、异网用户。
- 是否覆盖所有业务场景:正常场景 + 边界场景 + 极端场景。
- 多渠道协同是否一致:App、小程序、H5、营业厅、客服热线之间的数据与状态是否一致。
- 重点看:场景覆盖率、渠道一致性、用户类型适配度。
输出要求
- 列出所有发现的流程问题,按"断点 > 逻辑错误 > 冗余 > 场景缺失"排序。
- 每个问题标注影响范围(全量用户/特定用户/特定场景)和严重等级(P0/P1/P2)。
- 给出流程修复方案,包含目标流程图描述。
二、功能领先性审查
适用于审查产品功能在行业中的领先程度、创新性、差异化竞争力。
审查框架
-
行业对标
- 对标三大运营商同类产品:移动、电信、联通的对应功能做了什么,本产品是否有差距。
- 对标互联网标杆产品:用户日常使用的微信、支付宝、美团等产品的交互体验。
- 对标行业趋势:5G 消息、AI 客服、数字人、云网融合、算力网络等新方向。
- 重点看:功能对标清单、差距矩阵、领先/持平/落后标注。
-
创新维度
- 技术创新:是否使用了新技术(AI、大数据、RPA、区块链)提升体验或效率。
- 模式创新:是否有新的业务模式、服务模式、计费模式。
- 体验创新:是否有差异化的交互方式、个性化推荐、智能引导。
- 重点看:创新功能数量、创新落地效果、用户感知度。
-
功能前瞻性
- 是否预留扩展能力:架构设计是否支持未来业务扩展、多租户、多场景。
- 是否跟进行业标准:3GPP、GSMA、CCSA 等标准的新方向是否在产品中有体现。
- 是否有技术债务:遗留技术是否阻碍功能演进。
- 重点看:架构扩展性、标准跟进度、技术债务清单。
-
差异化竞争力
- 本产品相比竞品的独特卖点是什么。
- 独特卖点是否可被用户感知、是否形成使用粘性。
- 差异化功能是否有壁垒(数据壁垒、网络壁垒、生态壁垒)。
- 重点看:USP(独特卖点)清单、用户感知度、竞争壁垒分析。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 290 lines · 50 tokens per session scan A 32f4b2efebf9
carrier-product-review is a skill published in the GitHub repository zhouguoqing/QianYuan.AIAgenticFramework (37 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 4,631 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
design-critique
Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.
impeccable
Use when designing, redesigning, shaping, critiquing, auditing, polishing, animating, or hardening frontend interfaces: websites, dashboards, SaaS apps, mobile screens. Enforces 24 design commands, PRODUCT.md/DESIGN.md artifacts, 4 surface modes (Persuade, Operate, Read, Experience), and strict craft floor against…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", or "vs best practices".
design-usabilidade
Use when analyzing user journeys, auditing UX quality, prototyping flows, or designing new pages/features from a product perspective. Triggers on: jornada do usuario, fluxo de agendamento, prototipo, prototipar, experiencia do usuario, UX audit, usabilidade, melhorar conversao, nova pagina, nova feature, redesign…
design-critic
Designer senior extremamente critico. Analisa aplicacao web em 5 pilares (Visual Consistency, Information Hierarchy, Interaction Quality, Spatial Design, Polish & Craft), captura screenshots via Playwright, gera relatorio com score, e aplica auto-fix em todos os findings. Triggers on: design audit, design review…
interface-auditor
Detect UX antipatterns (smells) in interface descriptions using the uxuiprinciples smell taxonomy. Returns structured findings with matched symptoms, severity, and step-by-step remediation recipes. API key optional — full remediation recipes require uxuiprinciples.com API Access.