What makes Business Blueprint Skill notable?

1.1K downloads. Trust evidence available

How should Business Blueprint Skill be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Business Blueprint Skill

Use when turning presales requirements, meeting notes, or solution materials into editable business capability blueprints, swimlane flows, and application ar... Skill: Business Blueprint Skill Owner: kaisersong Summary: Use when turning presales requirements, meeting notes, or solution materials into editable business capability blueprints, swimlane flows, and application ar... Tags: latest:0.15.0 Version history: v0.15.0 | 2026-04-30T14:17:32.981Z | user Domain-knowledge blueprints now produce product-grade strategy names (统一归因模型 vs 测款节奏). Adds namingHints to cross-border-e

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

0.15.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 0.15.0release · observed Apr 30, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17e36cy6y9drqxrb49xdqh05d83hqde:kai-business-blueprint

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-kaisersong-kai-business-blueprint/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: kai-business-blueprint
description: Use when turning presales requirements, meeting notes, or solution materials into editable business capability blueprints, swimlane flows, and application architecture diagrams. Use when generating blueprint JSON, static HTML viewers, or exporting to SVG, draw.io, Excalidraw, or Mermaid formats. When no standard export template applies, default to free-flow output.
---

# Business Blueprint Skill

Use the Python scripts in this repository as the execution surface.

## Output Directory

All generated files (blueprint JSON, viewers, exports) go into `projects/workspace/` — not the repository root.

```bash
python scripts/business_blueprint/cli.py --plan projects/workspace/solution.blueprint.json --from "..."
python scripts/business_blueprint/cli.py --project projects/workspace/solution.blueprint.json
python scripts/business_blueprint/cli.py --export projects/workspace/solution.blueprint.json
```

## Industry Selection

Choose `--industry` from exactly one of: `"common"`, `"finance"`, `"manufacturing"`, `"retail"`. Select the closest match based on the user's domain and materials; do not invent other values.

| Industry | Hints content |
|----------|-------------|
| `common` | No hints — generic domains |
| `finance` | Risk control, credit, compliance, customer profile, etc. |
| `manufacturing` | Production planning, quality, warehouse, supply chain, etc. |
| `retail` | Store operations, membership, POS, order fulfillment, etc. |

## How to Generate a Blueprint

The AI agent is responsible for entity extraction. The Python tool handles JSON writing, visualization, and export.

### Step 1: Read industry hints

Read the seed template at `business_blueprint/templates/{industry}/seed.json` and get the `industryHints.checklist`.

### Step 2: Extract entities from source text

Using the user's source material AND the industry hints checklist, extract:
- **capabilities**: business capability areas (name, description)
- **actors**: roles/people involved (name)
- **flowSteps**: business process steps (name, actorId, capabilityIds, stepType)
- **systems**: IT systems that support capabilities
  - See `references/entities-schema.md` for all entity field definitions
  - See `references/systems-schema.md` for systems category/layer rules
  - See `scripts/business_blueprint/templates/common/seed.json` for field examples

**Domain-knowledge mode** (when seed has `meta.blueprintType: "domain-knowledge"`,
e.g. `cross-border-ecommerce`): entities go into `library.knowledge.*`
(painPoints / strategies / rules / metrics / practices / pitfalls), not the
architecture buckets above. The seed's `industryHints.knowledgeHints.namingHints`
section, when present, dictates content granularity:
- `strategy.name` must be a 4-10 字 product-grade noun phrase
  (e.g. "统一归因模型", "AIGC 素材工厂"), not an action ("优化素材") or a
  dimension ("测款节奏"). Reference the seed's `strategy_named_examples`.
- `painPoint.audience` and `strategy.audience` are f

evals/README.md

# Export Evals

This directory holds machine-readable export quality inputs, thresholds, and taxonomy data for `kai-business-blueprint`.

## Files

- `export-integrity-thresholds.json` — numeric thresholds for geometry-sensitive integrity checks
- `defect-taxonomy.json` — canonical defect categories used by tests and eval fixtures
- `export-scoring-schema.json` — minimal scoring/output schema for export eval runs

## Fixtures

- `fixtures/route-freeflow.json` — generic graph that should stay on `freeflow`
- `fixtures/route-architecture.json` — categorized architecture graph that should resolve to `architecture-template`
- `fixtures/route-evolution.json` — dated staged flow that should resolve to `evolution`

## Usage

- Route tests read these fixtures to keep export-family decisions stable.
- Integrity tests should reference taxonomy ids instead of inventing one-off failure labels.
- Human-readable failure maps, if needed later, should be generated from these files and test references rather than hand-maintained as the source of truth.

README.md

# kai-business-blueprint

> 售前需求、会议纪要、RFP 材料 → 可编辑的业务能力蓝图、泳道流程图、应用架构图。一份 canonical JSON IR，多个下游导出格式（SVG / draw.io / Excalidraw / Mermaid）。

A [Claude Code](https://claude.ai/claude-code) skill that turns raw presales inputs into canonical business capability blueprints, with a static HTML viewer and multi-format diagram exports.

English | [简体中文](README.zh-CN.md)

---

## Demo

Retail industry blueprint, exported as SVG:

![retail-blueprint](demos/screenshots/retail-arch.svg)

The SVG is generated by `business-blueprint --export demos/retail.blueprint.json` — the source JSON is in `demos/retail.blueprint.json`, the viewer is `demos/solution.viewer.html`.

---

## Design Philosophy: IR-First Pipeline

### 1. JSON as Canonical Intermediate Representation

Every workflow converges on `solution.blueprint.json` — the single source of truth. All other artifacts (viewer, SVG, draw.io) are deterministic projections from it.

```
Raw Text ──(--plan)──→ JSON ──(--generate)──→ Viewer HTML
                          │
                          ├──(--export)──→ SVG / draw.io / Excalidraw / Mermaid
                          │
                          └──(--edit)────→ JSON (patch logged) + Viewer refresh
```

The IR is:
- **Version-controllable** — standard JSON, diffs are meaningful
- **AI-readable** — downstream skills parse `entities`, `relations`, `flowSteps` without HTML parsing
- **Human-editable** — light fields (labels, names) can be edited without breaking structure

### 2. Progressive Disclosure

The skill file (`SKILL.md`) is a routing layer — it tells Claude *which* file to read for *which* command. Heavy assets (industry packs, viewer HTML template, export engine) stay on disk until needed.

```
--plan        → only model + generation rules; no CSS, no export engine
--generate    → one viewer.html template + one industry pack
--export      → only the requested export engine; other formats stay on disk
--validate    → schema + rules; no rendering code
```

### 3. Silicon-Carbon Collaboration

**Input:** Humans write natural language (requirements, meeting notes, RFPs). AI parses into structured entities (Application Systems, Business Capabilities, Process Flows, Actors) and relations.

**Output:** The viewer is a static HTML page — no build step, no JS framework, works offline. Every node is editable in-place, and edits are logged as a JSON patch trail (`solution.patch.jsonl`) for full traceability.

---

## Install

### Claude Code

```bash
git clone https://github.com/kaisersong/kai-business-blueprint ~/.claude/skills/kai-business-blueprint
```

Then: `cd kai-business-blueprint && pip install -e .`

### OpenClaw

```bash
git clone https://github.com/kaisersong/kai-business-blueprint ~/.openclaw/skills/kai-business-blueprint
cd kai-business-blueprint && pip install -e .
```

---

## Usage

### CLI Commands

| Flag | Purpose |
|------|---------|
| `--plan "text"` | Parse raw text into canonical blueprint JSON |
| `--project <blueprint.json>` | Deriv

_meta.json

{
  "ownerId": "kn7bjv9d2ccsjqk1m4edthgtgx82fem8",
  "slug": "kai-business-blueprint",
  "version": "0.15.0",
  "publishedAt": 1777558652981
}

references/architecture-design-system.md

# Architecture Diagram Design System

本文件定义 Agent 生成架构图时使用的完整设计系统。所有颜色、字体、间距、布局规则必须严格遵循。

## 1. 主题

### 暗黑模式（默认）

| Token | 值 | 用途 |
|-------|-----|------|
| `bg` | `#020617` | 页面背景（Slate-950） |
| `canvas` | `#0F172A` | 卡片表面（Slate-900） |
| `text_main` | `#E2E8F0` | 主文字 |
| `text_sub` | `#94A3B8` | 副文字 |
| `border` | `#1E293B` | 边框 |
| `grid` | `#1E293B` | 网格线（40px pattern） |

暗黑模式是默认输出。除非用户明确要求亮色模式，否则不得切换到亮色主题。

### 亮色模式

| Token | 值 | 用途 |
|-------|-----|------|
| `bg` | `#F8FAFC` | 页面背景 |
| `canvas` | `#FFFFFF` | 卡片表面 |
| `text_main` | `#0F172A` | 主文字 |
| `text_sub` | `#64748B` | 副文字 |
| `border` | `#CBD5E1` | 边框 |

## 2. 字体

- 主字体：`'JetBrains Mono', 'Fira Code', monospace`（Google Fonts CDN 引入）
- 回退字体：`system-ui, -apple-system, sans-serif`

| 层级 | 字号 | 字重 | 用途 |
|------|------|------|------|
| 标题 | 20px | 700 | SVG 主标题 |
| 副标题 | 13px | 400 | 副标题/注解 |
| 组件名 | 14px | 600 | 节点名称 |
| 副标签 | 11px | 400 | 节点描述 |
| 注解 | 9-10px | 400 | 标签、Legend |
| Region 标签 | 12px | 600 | Region 名称 |

## 3. 语义色

7 种系统类别，每种定义 fill + stroke（暗黑模式值）：

| 类别 | 填充色 | 描边色 | 用途 |
|------|--------|--------|------|
| `frontend` | `rgba(8,51,68,0.4)` | `#22d3ee` | Web、移动端、UI |
| `backend` | `rgba(6,78,59,0.4)` | `#34d399` | Lambda、API、服务 |
| `database` | `rgba(76,29,149,0.4)` | `#a78bfa` | DynamoDB、RDS |
| `cloud` | `rgba(120,53,15,0.3)` | `#fbbf24` | Region 框、CloudFront |
| `security` | `rgba(136,19,55,0.4)` | `#fb7185` | Security Group、WAF |
| `message_bus` | `rgba(251,146,60,0.3)` | `#fb923c` | SQS、SNS、EventBridge |
| `external` | `rgba(30,41,59,0.5)` | `#94a3b8` | 第三方 API、SaaS |

无类别时回退到：fill `#1E293B`，stroke `#94A3B8`。

## 4. 布局规则

### 4.1 L→R 数据流

```
Clients(左) → Frontend → Backend → Database(右)
```

- Clients 通常放在 Region 框外左侧
- 其他组件按 `flowSteps[].seqIndex` 排序，从左到右排列
- 水平间距 40-60px，垂直居中对齐

### 4.2 组件尺寸

根据 capabilities 数量决定：

| 能力数 | 宽度 | 高度 | 用途 |
|--------|------|------|------|
| 0-1 | 140px | 44px | 简单组件（SQS 等） |
| 2-4 | 150px | 80px | 中等组件（Lambda、S3） |
| 5+ | 160px | 80px | 大组件（API Gateway、DynamoDB） |

所有组件：`rx="8"` 圆角，`stroke-width="2"` 描边。

如果文本、特征列表或标签超出上述尺寸，不得硬压缩成“牙膏图”。优先顺序是：
1. 增大卡片宽度或高度
2. 将同层节点换到多行
3. 扩大画布
4. 必要时回退到 `freeflow`

禁止通过把整层强行塞成一行、把图例改成浮层、或让底部内容被裁切来维持模板外观。

### 4.3 Region 边界

- 矩形框：`rx="16"`, `stroke-dasharray="8,4"`, 琥珀色 `#F59E0B`, `opacity="0.4"`
- Region 标签放在框外上方（x=Region左边界+20, y=Region上边界-10）
- 填充：`none`（仅描边）

### 4.4 Summary Cards

放在架构图底部，3 组卡片，响应式网格布局：

| 卡片 | 颜色 | 内容 |
|------|------|------|
| Infrastructure | 琥珀色 `#F59E0B` | 基础设施列表 |
| Compute | 翠绿色 `#34D399` | 计算资源描述 |
| Data | 紫色 `#A78BFA` | 数据存储描述 |

每张卡片：`rx="10"`, fill `#0F172A`, stroke `#1E293B`, 宽 340-370px, 高 130px。

### 4.5 分层布局约束

- 分层图中的“层”是语义分组，不是强制单行容器。
- 每层 `1-3` 个节点时可单行展示。
- 每层 `4-6` 个节点时默认拆成两行，保持卡片尺寸可读。
- 每层 `7+` 个节点时应扩大画布或直接回退到 `freeflow`，不要继续压缩。
- Actor / User 角色默认渲染为边栏标签、badge 或 lane header，不应伪装成普通系统卡片。

### 4.6 Legend 位置

- Legend 默认放在左下或底部保留区。
- Legend 必须参与整体高度计算，不能作为右上角悬浮遮罩。
- 禁止将 legend 放在 top-right 覆盖标题区或内容区。

### 4.7 画布尺寸与裁切

- `viewBox` 和最终 `height` 必须覆盖：最底部节点、legen

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.