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 guofu-shiqu/ux-expert-skills --skill exp-orchestration-designgit clone --depth 1 https://github.com/guofu-shiqu/ux-expert-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/guofu-shiqu/ux-expert-skills/exp-orchestration-design)<a href="https://agentmods.dev/skills/guofu-shiqu/ux-expert-skills/exp-orchestration-design"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-orchestration-design/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/guofu-shiqu/ux-expert-skills/exp-orchestration-design"><img src="https://agentmods.dev/badge/skills/guofu-shiqu/ux-expert-skills/exp-orchestration-design.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 | $0.00031 | $0.00788 |
| Opus 5 | $0.00015 | $0.00394 |
| Sonnet 5 | $0.00006 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
exp-orchestration-design 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.
This is a copy
91% identical to chat_with_agent — 146 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
体验编排设计
围绕"触发条件→判断规则→响应动作→人工介入→指标监测→资产回写"结构，设计 Agent 自动化机制。
触发条件
- 需要将旅程中的关键节点转化为 Agent 可执行的自动化机制
- 需要设计 Agent 的触发条件、判断规则和响应动作
- 需要定义何时升级转人工
- 需要建立自动化的监测和回写机制
核心能力
编排设计结构
围绕以下结构进行编排设计：
触发条件 → 判断规则 → 响应动作 → 人工介入 → 指标监测 → 资产回写
1. 触发条件设计
定义什么条件下自动触发：
- 用户行为触发（如：完成某个动作、停留超过 N 秒、重复操作等）
- 数据阈值触发（如：指标低于 X、频次超过 Y 等）
- 时间触发（如：注册后 N 天、到期前 N 天等）
- 情绪触发（如：检测到负面情绪、投诉等）
2. 判断规则设计
定义触发后如何判断和处理：
- 用户分层判断（新用户/老用户/流失用户等）
- 场景匹配判断（匹配哪个场景卡）
- 优先级判断（问题的严重程度）
- 渠道判断（用户在哪个渠道）
3. 响应动作设计
定义 Agent 自动执行什么动作：
- 推送什么内容
- 提供什么帮助
- 执行什么操作
- 记录什么数据
4. 人工介入设计
定义何时升级转人工：
- 用户明确要求人工
- Agent 无法解决问题
- 问题涉及高风险或敏感内容
- 用户情绪升级
5. 指标监测设计
定义如何监测编排效果：
- 监测哪些指标
- 如何评估效果
- 如何持续优化
6. 资产回写设计
定义如何将编排经验沉淀为资产：
- 哪些规则可以复用
- 哪些场景可以沉淀
- 哪些话术可以复用
输出格式：旅程编排卡
【旅程编排卡】
▸ 关键场景：[...]
▸ 旅程节点：[...]
▸ 触发条件：
[什么条件下自动触发]
条件类型：[行为/数据/时间/情绪]
具体条件：[...]
▸ 判断规则：
1. [规则描述]，动作：[...]
2. [...]
...
▸ Agent 动作：
[Agent 自动执行什么动作]
▸ 员工动作：
[员工需要配合做什么动作]
▸ 用户可见反馈：
[用户会看到/感受到什么]
▸ 升级条件：
[什么情况下升级转人工]
▸ 指标监测：
监测指标：[...]
评估方式：[...]
▸ 资产回写：
[哪些产出可以沉淀为 reusable asset]
使用方法
当需要将旅程中的关键节点转化为自动化机制时，调用本 skill 设计体验编排，明确触发条件、判断规则、响应动作和升级条件。
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 · 114 lines · 31 tokens per session scan A 4c2424f160a1
exp-orchestration-design is a skill published in the GitHub repository guofu-shiqu/ux-expert-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 788 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to chat_with_agent, differing in 146 lines, and is treated as a copy.
Other skills, from other repositories
api-design
Design public interfaces for libraries and tools that other people depend on. Use when designing or reviewing a public API surface, deciding what to export, naming functions and CLI flags, adding configuration options, planning deprecations, or when the user asks "is this a good API" or "how do I change this without…
code-review
Review a pull request the way a good open-source maintainer does. Use when reviewing an incoming PR, when the user asks "review this PR" or "is this ready to merge", when triaging a stale PR queue, or when writing review feedback to an external contributor. Covers what to check and in what order, severity levels…
governance-and-sustainability
Keep a project and its maintainers alive over years. Use when deciding how decisions get made, writing GOVERNANCE.md or a code of conduct enforcement process, adding or removing maintainers, handling burnout or stepping away, setting up funding (GitHub Sponsors, Open Collective, a foundation), handling a fork or a…
open-source
Generates the complete open-source governance of a repository: README, LICENSE, REUSE.toml and SPDX headers, CONTRIBUTING, SECURITY, CODEOFCONDUCT, GOVERNANCE, CHANGELOG, .github issue/PR templates, GitHub Actions, Dependabot, conventional commits, GPG/DCO signing, git flow and ADRs. Use whenever the user wants to…
contributor-experience
Turn users into contributors and make their first PR succeed. Use when a project gets stars but no contributions, when first-time PRs stall or get abandoned, when writing or improving CONTRIBUTING.md, when setting up a dev environment that works on the first try, or when the user asks "how do I get contributors" or…
dependency-hygiene
Manage a project's dependencies so they stay small, current, and safe. Use when deciding whether to add a dependency, auditing an existing dependency tree, configuring Dependabot or Renovate, dealing with upgrade churn or a flood of bot PRs, resolving version conflicts, choosing between dependency ranges and pinning…