fusion-research
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseFusion Research
Fusion研究
When to use
适用场景
Use this skill when a user needs a source-backed answer about the Fusion ecosystem.
Typical triggers:
- "Research this Fusion Framework hook and show me the supporting source."
- "What props does this EDS component accept?"
- "Which skill handles X in a Fusion workflow?"
- "Find a source-backed example for…"
- "Which Fusion package or module owns this API?"
- "Is there an EDS design token for this value?"
- "How can I persist user preferences in a Fusion app?"
- "What's the recommended pattern for X in Fusion?"
- "Show me a Fusion Framework example for building X."
- "What are the design tokens for color and spacing in EDS?"
当用户需要关于Fusion生态系统的、有来源支撑的答案时,使用此skill。
典型触发场景:
- "研究这个Fusion Framework钩子并向我展示支撑的源文件。"
- "这个EDS组件接受哪些props?"
- "在Fusion工作流中,哪个skill负责处理X?"
- "找一个有来源支撑的示例用于…"
- "哪个Fusion包或模块拥有这个API?"
- "是否存在对应此值的EDS设计令牌?"
- "如何在Fusion应用中持久化用户偏好?"
- "在Fusion中实现X的推荐模式是什么?"
- "给我一个用于构建X的Fusion Framework示例。"
- "EDS中颜色和间距的设计令牌有哪些?"
When not to use
不适用场景
Do not use this skill for:
- implementing code changes — use or the relevant dev skill; if the research is for a specific app you are actively building, use
fusion-app-react-devfirst — it will call this skill when neededfusion-app-react-dev - finding, installing, updating, or removing skills — use ; use this skill only to understand a skill's scope, relationships, or catalog fit — not to discover what to install
fusion-discover-skills - creating or editing skill files — use for authoring-time research
fusion-skill-authoring - Fusion MCP installation or troubleshooting — use ; once MCP is running, return here for research
fusion-mcp - pure conceptual Fusion questions with no specific artifact name (hook, component, package, token) — ask the user for a concrete artifact reference first
请勿将此skill用于:
- 实施代码变更 — 使用或相关开发skill;如果研究是针对你正在开发的特定应用,请先使用
fusion-app-react-dev— 它会在需要时调用此skillfusion-app-react-dev - 查找、安装、更新或移除skill — 使用;仅可使用此skill来了解skill的范围、关系或目录适配性 — 不可用于发现需要安装的内容
fusion-discover-skills - 创建或编辑skill文件 — 在创作阶段进行研究时使用
fusion-skill-authoring - Fusion MCP安装或故障排查 — 使用;MCP运行后,可返回此skill进行研究
fusion-mcp - 无具体工件名称(钩子、组件、包、令牌)的纯概念性Fusion问题 — 先要求用户提供具体的工件参考
Instructions
操作步骤
Step 0 — Sharpen scope (optional)
步骤0 — 明确范围(可选)
Before classifying, you may use the domain-specific follow-up questions to narrow the user's exact need:
- Framework scope: assets/framework.follow-up.md
- EDS scope: assets/eds.follow-up.md
- Skills catalog scope: assets/skills.follow-up.md
Skip this step if the question already names a specific artifact (hook, component, package, token, or skill).
在分类之前,你可以使用特定领域的跟进问题来缩小用户的确切需求:
- Framework范围:assets/framework.follow-up.md
- EDS范围:assets/eds.follow-up.md
- 技能目录范围:assets/skills.follow-up.md
如果问题已经指定了具体工件(钩子、组件、包、令牌或skill),则跳过此步骤。
Step 1 — Classify the research question
步骤1 — 分类研究问题
Determine which domain the question belongs to:
| Domain | Indicators | Agent |
|---|---|---|
| Framework | Fusion Framework hooks, packages, modules, TypeScript APIs, cookbook examples | |
| EDS | EDS component props, usage examples, accessibility, design tokens | |
| Skills | Skill catalog lookup, scope boundaries, companion/orchestrator relationships | |
If the question spans multiple domains, answer each domain separately using the appropriate agent in sequence.
确定问题所属的领域:
| 领域 | 标识 | Agent |
|---|---|---|
| Framework | Fusion Framework钩子、包、模块、TypeScript API、手册示例 | |
| EDS | EDS组件props、使用示例、可访问性、设计令牌 | |
| Skills | 技能目录查询、范围边界、配套/编排器关系 | |
如果问题涉及多个领域,请分别使用对应的Agent依次回答每个领域的问题。
Step 2 — Dispatch to the correct agent
步骤2 — 调度到正确的Agent
- Framework questions → follow .
agents/framework.agent.md - EDS questions → follow .
agents/eds.agent.md - Skills questions → follow .
agents/skills.agent.md
If the runtime supports skill-local agents, invoke the agent directly. Otherwise, apply the agent's instructions inline.
- Framework相关问题 → 遵循的指引。
agents/framework.agent.md - EDS相关问题 → 遵循的指引。
agents/eds.agent.md - Skills相关问题 → 遵循的指引。
agents/skills.agent.md
如果运行时支持skill本地Agent,请直接调用Agent。否则,内联应用Agent的操作指引。
Step 3 — Return the source-backed answer
步骤3 — 返回有来源支撑的答案
Use the structure in assets/source-backed-answer-template.md:
- State which domain and agent was used.
- Include one to three source-backed evidence bullets.
- End with any remaining assumptions, uncertainty, or the next verification step.
使用assets/source-backed-answer-template.md中的结构:
- 说明使用的领域和Agent。
- 包含1到3条有来源支撑的证据要点。
- 结尾说明任何剩余的假设、不确定性或下一步验证步骤。
Research agents
研究Agent
This skill includes three research agents in . Each covers one Fusion research domain with its own query patterns and evidence checklist.
agents/- — source-backed answers about Fusion Framework hooks, packages, modules, and cookbook examples. Uses
agents/framework.agent.md.mcp_fusion_search_framework - — source-backed answers about EDS component props, usage, accessibility, and design tokens. Uses
agents/eds.agent.md.mcp_fusion_search_eds - — source-backed answers about the Fusion skill catalog: what skills exist, their scope, and how they relate. Uses
agents/skills.agent.md.mcp_fusion_search_skills
此skill在目录下包含三个研究Agent。每个Agent覆盖一个Fusion研究领域,拥有各自的查询模式和证据检查清单。
agents/- — 关于Fusion Framework钩子、包、模块和手册示例的有来源支撑的答案。使用
agents/framework.agent.md。mcp_fusion_search_framework - — 关于EDS组件props、用法、可访问性和设计令牌的有来源支撑的答案。使用
agents/eds.agent.md。mcp_fusion_search_eds - — 关于Fusion技能目录:现有技能、范围边界以及配套/编排器关系的有来源支撑的答案。使用
agents/skills.agent.md。mcp_fusion_search_skills
Assets
资产
- assets/source-backed-answer-template.md
- assets/framework.follow-up.md — pre-dispatch scope questions for Framework research
- assets/eds.follow-up.md — pre-dispatch scope questions for EDS research
- assets/skills.follow-up.md — pre-dispatch scope questions for skills catalog research
- assets/source-backed-answer-template.md
- assets/framework.follow-up.md — Framework研究的调度前范围确认问题
- assets/eds.follow-up.md — EDS研究的调度前范围确认问题
- assets/skills.follow-up.md — 技能目录研究的调度前范围确认问题
Safety & constraints
安全与约束
Never:
- invent Fusion Framework hooks, EDS props, or skill catalog entries
- claim evidence exists when MCP is unavailable or results are weak
- keep refining indefinitely — state uncertainty after one refinement pass per agent
- implement code changes or mutate repositories during a research flow
Always:
- classify the question before choosing an agent
- capture the source path and supporting excerpt before finalizing any claim
- state explicitly which agent and source backed each part of the answer
绝对禁止:
- 虚构Fusion Framework钩子、EDS props或技能目录条目
- 在MCP不可用或结果可信度低时声称存在证据
- 无限期优化 — 每个Agent经过一次优化后仍不确定的话,直接说明不确定性
- 在研究流程中实施代码变更或修改仓库
必须遵守:
- 在选择Agent前先对问题进行分类
- 在最终确定任何结论前,记录源文件路径和支撑摘录
- 明确说明答案的每个部分由哪个Agent和源文件支撑