mirror of
https://git.openapi.site/https://github.com/desirecore/market.git
synced 2026-06-06 08:30:42 +08:00
feat: add tech-diagram skill (Mermaid 技术图生成) (#18)
## 概述 / Summary 新增市场技能 **tech-diagram**:把自然语言描述转成品牌一致的技术图(架构图/流程图/时序图/状态机/ER/类图/思维导图),在 DesireCore 对话内复用现有 Mermaid 渲染管线即时渲染为 SVG。 Adds a market skill **tech-diagram** that turns natural-language descriptions into brand-consistent technical diagrams, rendered inline as SVG by the existing Mermaid pipeline in the DesireCore chat. 灵感来源 / Inspired by [fireworks-tech-graph](https://github.com/yizhiyanhua-ai/fireworks-tech-graph) 的三个设计思路:语义词汇表即数据、风格系统化、领域 Pattern 内置——并落到 DesireCore 自己的 3+2 设计令牌与领域模型上。 ## 改动 / Changes - `skills/tech-diagram/SKILL.md` + `SKILL.zh-CN.md`:双语技能正文(强制风格规则 + 语义词汇表 + 输出约定) - `skills/tech-diagram/references/semantic-vocabulary.md`:概念→Mermaid 形状→3+2 classDef 完整映射 - `skills/tech-diagram/references/templates.md`:4 个 DesireCore 领域模板(Agent 架构 / Delegate 6 模式 / 三层记忆 / 关系图谱)+ 时序图示例 - `builtin-skills.json`:加入 `tech-diagram` - `manifest.json`:`version` 1.2.1→1.2.2,`stats.totalSkills` 21→22,`lastUpdated` ## 设计要点 / Design - **风格一致性**:每张图以 `%%{init}%%` 注入品牌主题(覆盖对话全局暗色),用 5 个 `classDef` 绑定 DesireCore 3+2 配色(green/blue/purple + warning orange / error red)。 - **语义优于视觉**:Agent→六边形、系统/记忆→圆角/圆柱、决策→菱形;箭头编码主数据流/记忆写入/异步/层级/上报。 - **领域内置**:直接对照 `delegate.ts` / `conversation-memory.ts` / `relations/projector.ts` 给出可套用模板。 ## 验证 / Verification - ✅ `scripts/i18n/validate-i18n.py`:无 i18n 问题 - ✅ 用 app 同版本 **mermaid 11.15.0**(securityLevel: loose)解析 `templates.md` 全部 5 个图块,全部通过
This commit is contained in:
78
skills/tech-diagram/references/semantic-vocabulary.md
Normal file
78
skills/tech-diagram/references/semantic-vocabulary.md
Normal file
@@ -0,0 +1,78 @@
|
||||
# Semantic Vocabulary (语义词汇表)
|
||||
|
||||
The full mapping from concept → Mermaid shape → DesireCore 3+2 class. Shape and
|
||||
color encode meaning, so a reader understands a diagram without a legend.
|
||||
|
||||
## The brand header (paste verbatim as the first line of every diagram)
|
||||
|
||||
```
|
||||
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#F0F5FF','primaryBorderColor':'#007AFF','primaryTextColor':'#1d1d1f','lineColor':'#6e6e73','fontFamily':'-apple-system,SF Pro Text,Noto Sans SC,sans-serif'}}}%%
|
||||
```
|
||||
|
||||
## The 5 color classes (the only allowed palette)
|
||||
|
||||
```
|
||||
classDef agent fill:#F6F3FF,stroke:#AF52DE,color:#1d1d1f
|
||||
classDef system fill:#F0F5FF,stroke:#007AFF,color:#1d1d1f
|
||||
classDef biz fill:#F0FDF4,stroke:#34C759,color:#1d1d1f
|
||||
classDef warn fill:#FFFBF0,stroke:#FF9500,color:#1d1d1f
|
||||
classDef error fill:#FFF0F0,stroke:#FF3B30,color:#1d1d1f
|
||||
```
|
||||
|
||||
`fill` = `cardBgColors`, `stroke` = the 3+2 accent, `color` = `systemColors.label`
|
||||
(`#1d1d1f`). Source of truth: `app/theme/tokens/index.ts` and
|
||||
`app/theme/presets/agent-colors.ts` **in the DesireCore application codebase**
|
||||
(where this skill runs) — these paths are not part of this market repository.
|
||||
|
||||
### Class selection rule (mirrors agent-colors.ts)
|
||||
|
||||
| Domain | Class | Accent |
|
||||
|--------|-------|--------|
|
||||
| System / generic (DesireCore core, infra, LLM) | system | blue `#007AFF` |
|
||||
| Knowledge / learning (legal, writer, memory) | agent / system | purple `#AF52DE` |
|
||||
| Business / execution (data, real-estate, code) | biz | green `#34C759` |
|
||||
| Project management / warning / decision | warn | orange `#FF9500` |
|
||||
| Error / failure | error | red `#FF3B30` |
|
||||
|
||||
Decorative-only colors `yellow #FFCC00` and `teal #5AC8FA` are for background
|
||||
gradients elsewhere in the product — never use them in diagrams.
|
||||
|
||||
## Shape table
|
||||
|
||||
| Concept | Mermaid syntax | Class | Note |
|
||||
|---------|----------------|-------|------|
|
||||
| Agent / sub-agent | `id{{Name}}` (hexagon) | agent | the signature shape for an autonomous agent |
|
||||
| DesireCore core / orchestrator | `id(Name)` (rounded) | system | central coordinator |
|
||||
| LLM / model | `id(⚡ Model)` (rounded + ⚡) | system | ⚡ prefix marks an LLM call |
|
||||
| Service / tool / skill | `id[Name]` (rect) | biz | a callable capability |
|
||||
| Business / execution step | `id[Step]` (rect) | biz | a unit of work |
|
||||
| Memory / store / DB | `id[(Store)]` (cylinder) | system | persistent state |
|
||||
| User / external actor | `id([User])` (stadium) | biz | the human |
|
||||
| Decision / branch | `id{Choice?}` (diamond) | warn | a fork in control flow |
|
||||
| External service | `subgraph Ext [External]` ... `end` + `style Ext stroke-dasharray:4 3` | — | dashed boundary = outside the system |
|
||||
|
||||
## Arrow / flow encoding
|
||||
|
||||
| Flow type | Edge syntax | Meaning |
|
||||
|-----------|-------------|---------|
|
||||
| Primary data flow | `A --> B` | the main path |
|
||||
| Memory write / persistence | `A -.-> B` | dotted = side-effect write |
|
||||
| Async event | `A -.->|async| B` | dotted + label |
|
||||
| Feedback / retry | `B --> A` (back-edge) | loop |
|
||||
| Hierarchy / containment | `A --o B` | circle edge |
|
||||
| Hard stop / escalation | `A --x B` | cross edge |
|
||||
| Co-participation (equal peers) | `A === B` | thick link |
|
||||
|
||||
## Diagram-type cheatsheet
|
||||
|
||||
| User intent | Mermaid header |
|
||||
|-------------|----------------|
|
||||
| Architecture / data flow | `flowchart TD` or `flowchart LR` |
|
||||
| Sequence / interaction over time | `sequenceDiagram` |
|
||||
| State machine | `stateDiagram-v2` |
|
||||
| ER / data model | `erDiagram` |
|
||||
| Class / type model | `classDiagram` |
|
||||
| Mind map | `mindmap` |
|
||||
|
||||
For `sequenceDiagram`, `classDiagram`, etc. that do not support `classDef`, still
|
||||
keep the `%%{init}%%` brand header so the theme stays light and on-brand.
|
||||
Reference in New Issue
Block a user