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 zxc663/shisan-xinuo-workflow --skill shisan-xinuo-productgit clone --depth 1 https://github.com/zxc663/shisan-xinuo-workflowWrote 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/zxc663/shisan-xinuo-workflow/shisan-xinuo-product)<a href="https://agentmods.dev/skills/zxc663/shisan-xinuo-workflow/shisan-xinuo-product"><img src="https://agentmods.dev/badge/skills/zxc663/shisan-xinuo-workflow/shisan-xinuo-product/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/zxc663/shisan-xinuo-workflow/shisan-xinuo-product"><img src="https://agentmods.dev/badge/skills/zxc663/shisan-xinuo-workflow/shisan-xinuo-product.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 | $0.00294 | $0.05126 |
| Opus 5.5 | $0.00118 | $0.02050 |
| Sonnet 5.5 | $0.00059 | $0.01025 |
| Haiku 4.5 | $0.00029 | $0.00513 |
Grade A, and why
shisan-xinuo-product 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
产品工程包 · 联通层(结构层核心)
家族:十三希诺工作流第四包(与 workflow 核心/flows/roles 并列)——独立可装、建议同装、按需加载。同装时三缝合点经核心包
references/skill-usage.md§8 钩子自动生效;单装本包时自行执行本文件全流程。 定位:设计 Skill 的红海=手法层(怎么做才好看——样式/组件/动效);本包=结构层——一个尚未形成成熟统一范式的工程层(不证明无人做,只补生态缺的「统一、可执行、可验证的桥接层」)。规定「这个功能应怎么来」:有哪些态、怎么流转、流转怎么被感知、走不通怎么办。边界:本包=交互工程,是 Product Contracts 规范层的第一垂直域;其余域未实现(占位声明见references/contract-schema.md§4)。主题与组件一概不定义(registry 只做检查者不做定义者)。 目的(§目的态):真实用户使用产品时的体验——3 万与 30 万的功能清单可以完全相同,差价全在旅程完整性;本包把差价变成可判定、可生产的清单。
§1 何时用 / 何时不用
用:新增或修改用户可见功能面(页面/弹窗/流程);「难用/丑/反直觉/为什么这样交互」的审查;功能落地前的交互设计;交付前的联通验收。 不用:纯后端任务(无用户可见面);纯视觉调色(不涉及功能流程);档0 文案/样式小改(豁免梯度,见 §7);产品创新决策(该创造什么/市场机会/商业模式/增长——产品决策侧的活;本包管「既然决定做,它具体应该是什么」)。
§2 跑道(联通工序,唯一入口)
任何用户可见功能,按八步走(0-7);每步有出口产物,无产物不进下一步。唯一入口=步骤 0 的层级门:先定位「在回答哪一层的问题」,再答上游定义。
-
层级定位与上游闸门(0a 层级定位 → 0b 产品对象六问):0a 层级门——①先声明「现在在解决什么问题、属于哪一层」(L0-L10 层栈,
references/layer-stack.md,含触发拦截表:讨论按钮位置=L8、新建组件/接口=L9、改布局=L5…)②逐层向上检查上游是否已确认(L1-L4 必查:职责/能力/主次与完整性/运营与后台),项目工件中已有答案→读档引用、不打断用户 ③未确认→停下回补,不得越级下沉。铁律:实现层完整性 ≠ 产品工程完整性——下游全绿不能补上游的缺。0b 产品对象六问(回补工具,缺答不得进后续任何步)——①Purpose 为什么存在(解决什么/不解决什么)②Responsibility 职责句(「X 管理/运营」形态,不是「展示 X 数据」)③Capability 能力清单④Priority 主次(恰好一个主功能 + 产品角色分层:核心任务/业务操作/辅助/高阶/风险操作)⑤Completeness 能力是否完整(页面级闭环八组)⑥Operability 能否被产品系统管理运行(谁管理/数据来源/权限/审核/fallback;无管理路径须显式裁决「本期无后台+谁管内容」)。细则与两类清单=references/product-object.md;边界:L0 只检查是否被陈述、不生产——产品工程≠产品创新。 -
功能面盘点 + 功能句:先枚举用户在应用中会看到的一切可见面——主功能面、导航/入口、空态、错误页、加载、帮助/说明、边界场景(移动端/弱网/深色)、管理面(第五类:后台/运营侧,内容与数据谁管、在哪管)——任务描述模糊时按用户旅程推导,不按「任务说了几件事」偷懒;再对每个面写一句承诺(谁、在什么场景、完成什么)。漏盘点面=后续一切工序对它失效。
-
六问翻译表(
references/interaction-bridge.md§2):功能天生六问逐问答——①输入什么(执行鸿沟)②何时发生/多久(反馈+Nielsen 三阈值 0.1/1/10s)③成功长什么样、落在哪(评估鸿沟)④怎么防失败→没防住怎么恢复→出路(#5 预防>#9 恢复)⑤能否反悔、代价(#3 用户控制)⑥下次/换环境还认吗(持久/一致/设备/语言/弱网)。任问无答案=交互债,停下补设计;答案用户猜=反人类。劝导级第 7 列:情绪目标。 -
statechart(
scripts/statechart-gate.py,判据 C1-C7):把态+转换落成机器可读 JSON(states内每态的on事件表 +initial)——无死端(非终态全有出边)、全可达、错误态必有恢复转换(错误态识别=声明"type":"error"∪ 名含 error/fail ∪ 契约 recovery 提及)、引用完整性(每条转换 target ∈ states)、契约 recovery 行双向对账(加--contract <json>启用:缺边=承诺落空/多边=未登记发明;recovery 须有机器可读载体——markdown 契约不构成 C7 对账输入,存量项目先按忠实转写补contract.json的recovery键再跑,--contract在场但无 recovery 行时 gate 输出跑法提醒;--probe-recovery <目录>探测存量疑似 recovery 语义 markdown(标题「语义词×状态域词」共现|恢复列表头——只提醒不 FAIL,引导忠实转写));表格与走查路径都从它派生。作用域=≥3 状态或含异步流转的功能面;单态小件豁免;结构门禁查不到「放弃路径缺席」(取消/中断未建模时结构合法)——进行中/持有中态按 interaction-bridge §4「放弃路径三问」语义走查。 -
承诺清单+六态(态+转换)矩阵:每个交互元素一句承诺(点了会发生什么)+六态逐格(loading/empty/error/edge/disabled/success)+每条态间箭头标注过渡语义/时长/可中断性(变化盲视:无标记突变是缺陷)。
-
验收标准前置:3-5 条可验证验收标准(Given/When/Then),先于任何实现。
-
实现:落地第一动作=查表(registry/capability-map),自研必须归因;组件驱动设计(先选控件后定交互)=一票否决级反面。
-
验收三件:①spec-trace 双向追溯(正向:每条功能行有元素兑现;反向:每个界面元素可回指功能行)②实机取证(无真渲染证据不得声称交互已验证)③裁决写回
decision-ledger。档3 加第四件:回归——改动后重跑既有功能的门禁+走查清单(golden sample),判据=同一可重跑命令 exit 0。
What ships with it
18 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.
- references/anti-excuses.md 3.2 KB
- references/capability-map.md 1.8 KB
- references/contract-schema.md 4.6 KB
- references/decision-ledger.md 1.7 KB
- references/interaction-bridge.md 5.4 KB
- references/judgement-table.md 13 KB
- references/layer-stack.md 7.3 KB
- references/product-object.md 5.8 KB
- references/registry.md 1.6 KB
- scripts/a11y-gate.py 13 KB runs code
- scripts/frontend-lint-gate.py 13 KB runs code
- scripts/l0-l5-gate.py 16 KB runs code
- scripts/product-object-gate.py 11 KB runs code
- scripts/registry-gate.py 6.2 KB runs code
- scripts/spec-trace-extract.py 6.2 KB runs code
- scripts/spec-trace-gate.py 14 KB runs code
- scripts/statechart-gate.py 17 KB runs code
- scripts/usage-probe.py 3.2 KB runs code
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.
- 6d ago Changed · -292 tokens per session b0cfd31c46cf
- 9d ago Changed d9f1c5b077ab
- 16d ago Changed a1fede624f11
- 17d ago Changed · +11 lines c5681968aa58
- 21d ago Changed · +70 tokens per session cfac77ba4328
- 23d ago Changed · +9 lines · +239 tokens per session 8200784013b6
- 25d ago First seen · 75 lines · 277 tokens per session scan A 505ba733dbeb
shisan-xinuo-product is a skill published in the GitHub repository zxc663/shisan-xinuo-workflow (38 stars, last pushed 3d ago), licensed MIT. It adds 294 tokens to every session and 5,126 once invoked, about $0.0012 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 2026-09-21.
Other skills, from other repositories
cocosketch
Generate visual draw.io diagrams from CocoPlus artifacts via a deterministic seven-step pipeline.
nous-branding
Generate images and content consistent with the Nous Research brand identity. Use when creating visuals in the Nous / Theia / Hermes ecosystem: a "cyber-classical" style blending neo-classical statuary, cyberpunk/industrial grunge, and retro anime illustration. Covers official brand color palette, typography…
design-thinking
Facilitate a full design-thinking engagement (Empathize, Define, Ideate, Prototype, Test) grounded in real user evidence. Use whenever the user wants to understand users deeply and design a solution for them: "run design thinking", "understand our users", "design user interviews", "synthesize these interview notes"…
techwolf-logo
Provides official TechWolf logo files in multiple variants (dark, white, monochrome) as SVG and PNG. Use when any output needs a TechWolf logo.
product-design-and-ux
Define user-facing product behavior from validated evidence and approved scope. Use for information architecture, task flows, state and recovery models, interface contracts, usability-study plans, interaction-pattern tradeoffs, AI recommendations and generated outputs, uncertainty, human control, feedback, or…
web-accessibility
Design, build, and review accessible web interfaces with native semantics, keyboard and focus behavior, forms and recovery, responsive input, motion, assistive-technology testing, and WCAG 2.2-informed evidence. Use for a11y, WCAG, ARIA, screen-reader, keyboard, focus, dialog, form, widget, or accessibility review…