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 tranfu-labs/tranfu-skills --skill product-ui-risk-reviewgit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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/tranfu-labs/tranfu-skills/product-ui-risk-review)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/product-ui-risk-review"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/product-ui-risk-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/tranfu-labs/tranfu-skills/product-ui-risk-review"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/product-ui-risk-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00145 | $0.03495 |
| Opus 5 | $0.00072 | $0.01747 |
| Sonnet 5 | $0.00029 | $0.00699 |
| Haiku 4.5 | $0.00015 | $0.00349 |
Grade A, and why
product-ui-risk-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 12d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产品 UI 风险审查
目的
使用这个 skill 审查资产、账户、授权、签名确认、交易提交、跨系统流转等产品 UI 流程是否足够清楚、可信、可恢复,并且适合交给真实用户使用。重点关注用户点按钮前是否理解后果、关键状态是否完整、失败后是否能恢复、风险文案是否具体,以及高风险操作是否容易误触或重复提交。
默认工作权限是只审查:输出发现和建议,NEVER 编辑文件,除非用户明确要求修复、实现或改写。 如果用户意图在「审查」和「完善/修复」之间模糊,MUST 默认走审查模式,并在输出中说明没有改文件。
这个 skill 主要做两件事:
- 审查模式:找出资产型、授权型、交易型产品 UI 在上线前会伤害用户决策、操作安全或恢复路径的问题。
- 完善模式:当用户明确说「完善」「修复」「按产品 UI 要求补齐」「直接改」时,把审查发现落成 PRD、文案、交互状态或代码修改。
工作流
CREATE A TODO LIST FOR THE TASKS BELOW:
- 识别审查目标。如果用户提供 PRD、设计稿、截图、代码库、路由或线上 URL,就以该材料为目标;如果没有目标,要求用户补充材料并停止。
- 归类产品流程:资产查看、资产兑换、领取、支付、授权、签名确认、交易提交、转账、账号安全、开通/关闭服务、审批、数据导入/导出、跨系统流转、异步任务、批量操作,或其他高风险流程。
- 提取用户决策路径。记录主要用户、目标动作、前置条件、涉及对象、金额/数量/范围、目标账户或目标系统、费用/耗时/限制,以及成功后果。未知项必须显式标记。
- 为每一步归类动作风险:只读、表单提交、授权、签名确认、支付、交易提交、转账、批量变更、不可逆操作、跨系统流转,或长时间异步操作。
- 按下方清单审查产品。优先处理可能造成用户损失、误操作、重复提交、不可逆误解、恢复路径中断或上线混乱的问题。
- 使用可用材料验证证据。对于代码,检查相关文件;对于可运行应用或线上 URL,在工具可用时做浏览器验证;对于截图或 PRD,不要声称做过运行时验证。
- 按用户意图路由输出。如果用户只要求审查,输出
PRODUCT_UI_RISK_REVIEW_REPORT,先列阻塞问题,再列改进建议、验证记录和未解决假设,然后结束。 - 如果用户明确要求完善或修复,先按「强制完善规则」修改可编辑目标,再输出改动文件、已运行验证、未验证项和
PRODUCT_UI_RISK_REVIEW_REPORT摘要,然后结束。
失败路径:
- 如果目标不可用或不可读,报告 blocker,说明缺失的材料并停止。
- 如果用户、对象、金额/数量、目标系统、权限或操作后果未知,默认带着明确假设继续;只有当缺失值会改变风险判断时,才问一个简短问题。
- 如果用户要求法律合规、安全漏洞、投资建议、财务收益判断或底层系统正确性结论,说明本 skill 只覆盖产品 UI 风险,并询问是否继续做 UI 风险范围内的审查。
- 如果无法真实操作关键流程,就做静态审查,并把真实交互验证列为未验证。
- 如果用户要求修复但没有提供可编辑源文件,返回审查结果,并说明需要哪些文件或材料才能打补丁。
强制完善规则
进入完善模式后,MUST 优先修复 critical 和 high 问题;只有在高风险问题已经处理或明确不可编辑时,才处理 medium 和 low 打磨项。
必须补齐的信息
- 任何资产、账户、支付、授权、签名确认、交易提交、转账、批量变更或跨系统流转按钮附近,MUST 显示对象、范围、金额/数量、目标、费用/耗时、权限变化和完成后果中的相关项。
- 按钮文案 MUST 具体。使用「支付 128 元」「授权访问客户名单」「确认兑换 100 USDC」「提交交易」「转出 2.5 ETH」「导出全部订单」这类动作文案,不用只有「Confirm」「Submit」「OK」「继续」的泛化文案。
- 如果数据未知、加载中、过期或读取失败,MUST 阻断高风险操作或清楚标注状态,NEVER 让用户基于不完整数据提交高风险动作。
必须补齐的状态
- 未满足前置条件:说明缺什么、为什么需要,以及满足后能做什么。
- 权限不足:说明缺少哪类权限,并给出申请、切换账号或联系管理员路径。
- 数据为空或不完整:说明当前能否继续;高风险操作必须被阻断或降级。
- 用户取消或拒绝:页面保持可恢复,并说明用户可以重试或返回。
- 操作处理中:阻止重复提交,说明正在等待系统确认或任务执行。
- 操作成功:说明结果,并提供下一步、详情页、记录或返回路径。
- 操作失败:说明可能原因,提供重试、修改输入、联系支持或查看详情路径。
授权、签名确认和交易提交
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 224 lines · 145 tokens per session scan A e97504c6e817
product-ui-risk-review is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 145 tokens to every session and 3,495 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.