Pace Biz logo

Pace Biz

Community
arch-team
pace-biz

Use when user says "业务机会/OPP", "专题/Epic", "分解需求/decompose", "精炼/refine", "战略对齐/align", "业务全景/view", "需求发现/brainstorm/discover", "导入/import", "技术债务/infer", "pace-biz", or wants to plan requirements. NOT for /pace-dev, -change, -plan, -init.

Overview

Publisherarch-team
Repositorydevpace
Skill namepace-biz
Stars
73
Forks
6
Bundled files
10
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 10 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by arch-team on GitHub. Read the source before you install it.

Installation

Install the Pace Biz AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/arch-team/devpace/tree/main/skills/pace-biz
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/arch-team/devpace.git /tmp/devpace
mkdir -p .claude/skills
cp -r /tmp/devpace/skills/pace-biz .claude/skills/pace-biz
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pace Biz in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pace Biz on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pace Biz is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/pace-biz — 业务规划域统一入口

管理从业务机会到专题(Epic)到业务需求(BR)的上游价值链。覆盖 Opportunity 捕获、Epic 创建与管理、需求分解、战略对齐检查和业务全景展示。

与现有机制的关系

  • /pace-biz:业务规划域(Opportunity→Epic→BR 的创建和分解)
  • /pace-change:需求变更域(已有 BR/PF/Epic 的变更——add/pause/resume/modify)
  • /pace-plan:迭代规划域(PF/CR 的排期)
  • /pace-init:项目初始化(首次 Vision/Strategy/OBJ 引导)
  • /pace-init full:项目不存在时,从 0 到 1 建立 .devpace/ + OBJ + 功能树 + 迭代计划(一站式初始化)
  • /pace-biz discover:项目已存在时,从模糊想法探索新的 OPP→Epic→BR→PF(增量扩展)
  • /pace-status:开发状态(CR/PF 开发进度视图)

推荐使用流程

完整业务路径:  opportunity → epic → decompose → /pace-dev
探索式发现:    discover → decompose → /pace-plan next
多源导入:      import <文档> → align → /pace-plan next
代码库推断:    infer → align → /pace-dev
战略对齐检查:  align(只读分析)
业务全景:      view(只读展示)
直接创建 Epic: epic(跳过 Opportunity)
日常需求注入:  /pace-change add(跳过 Opportunity/Epic,走快速路径)

输入

$ARGUMENTS:

子命令

创建型(产出新实体):

  • opportunity <描述> → 捕获业务机会到 opportunities.md
  • epic [OPP-xxx] <描述> → 从 Opportunity 转化或直接创建 Epic
  • decompose <EPIC-xxx|BR-xxx> → 分解 Epic→BR 或 BR→PF

精炼型(深化已有实体):

  • refine <BR-xxx|PF-xxx> → 交互式补充验收标准、边界条件、用户故事

发现型(探索和导入需求):

  • discover <描述> → 交互式需求发现,从模糊想法产出 OPP→Epic→BR→PF 候选树
  • import <路径>... [--threshold N] → 从文档批量提取需求实体,合并到功能树(阈值默认 0.8)
  • infer → 从代码库推断未追踪功能和技术债务

分析型(查看和检查):

  • align → 检查 OBJ→Epic→BR 战略对齐度,发现孤立实体
  • view → 业务全景视图(OPP→EPIC→BR 流)

空参数

  • (空)→ 智能引导——扫描项目上下文,按下方"空参数引导"章节给出个性化推荐

执行路由表

子命令读取写入procedures 文件
opportunityproject.md, opportunities.mdopportunities.mdskills/pace-biz/biz-procedures-opportunity.md
epicopportunities.md, project.mdepics/EPIC-xxx.md, project.md, opportunities.mdskills/pace-biz/biz-procedures-epic.md
decompose EPIC-xxxepics/EPIC-xxx.md, project.mdproject.md, epics/skills/pace-biz/biz-procedures-decompose-epic.md
decompose BR-xxxrequirements/BR-xxx.md, project.mdproject.md, requirements/skills/pace-biz/biz-procedures-decompose-br.md
refineproject.md, requirements/BR-xxx.mdproject.md, requirements/skills/pace-biz/biz-procedures-refine.md
alignproject.md, epics/, requirements/, opportunities.md, metrics/insights.mdmetrics/insights.md(趋势数据)skills/pace-biz/biz-procedures-align.md
viewproject.md, epics/, requirements/, opportunities.md(只读)skills/pace-biz/biz-procedures-view.md
discoverstate.md, project.md, opportunities.mdopportunities.md, epics/, project.md, scope-discovery.mdskills/pace-biz/biz-procedures-discover.md
importproject.md, insights.mdproject.md, epics/, requirements/skills/pace-biz/biz-procedures-import.md
inferproject.md, src/project.mdskills/pace-biz/biz-procedures-infer.md
(空参)state.md, project.md, opportunities.md(只读)(内联于下方"空参数引导"章节)

流程

所有子命令的公共前置

  1. 读取 state.md 和 project.md 确认项目上下文
  2. 确认 .devpace/ 已初始化(未初始化时引导 /pace-init)
  3. 读取 project.md 配置 section 的 preferred-role 字段(缺省 = Dev)。角色影响:输出措辞、追问方向、展示维度排序。参见各 procedures 文件中的"角色适配"段落
  4. 按子命令路由到对应 procedures 文件(各 procedure 内部根据 role 调整行为)

空参数引导

当用户无参数调用 /pace-biz 时,执行以下智能引导:

以下检测逻辑与 knowledge/_signals/signal-priority.md S16-S19 部分重叠。此处为用户直接引导版本(面向空参数场景),信号版本面向 pace-next/pace-pulse 的自动推荐。两处条件修改时需同步审查。

  1. 读取 project.md 的 mode 字段判断模式
  2. 扫描 opportunities.md 中 评估中 的 Opportunity 数量
  3. 扫描 epics/ 中 进行中 和 规划中 的 Epic 数量
  4. 扫描 project.md 树视图中未关联 Epic 的"孤立" BR 数量
  5. 阶段判断(内部逻辑,用于选择推荐策略,不直接输出阶段名称给用户):
    • 无 OPP 且无 Epic/BR → Sense 阶段→ 侧重发现型推荐
    • 有 OPP 未转化 或 有活跃 discover 会话 → Ideate 阶段→ 侧重转化和探索
    • 有 Epic 未分解 或 有 BR 未分解出 PF → Structure 阶段→ 侧重 decompose
    • 有 BR/PF 平均就绪度 < 60% → Refine 阶段→ 侧重 refine
    • 距上次 align > 5 天 或 从未执行 → Validate 阶段→ 侧重 align
    • 大部分 BR/PF 就绪度 >= 80% → Ready 阶段→ 推荐移交 /pace-dev
    • 多阶段条件同时满足时,按上述顺序取最早未完成的阶段
  6. 推荐优先级(生命周期感知):
    1. 未评估 Opportunity → opportunity 或 epic
    2. 规划中 Epic 需分解 → decompose
    3. BR/PF 平均就绪度 < 60% → refine Top-3 最需精炼项
    4. 距上次 align 超过 5 天或从未执行 → align
    5. 以上均不满足 → 上下文发现型推荐(import/infer/discover)
  7. 附完整子命令列表

发现型推荐(上下文感知):

  • 检测到 .md/.txt 文档 → 推荐 import <文件>
  • 检测到 src//lib/ 等代码目录 → 推荐 infer
  • 有活跃 Epic 但 BR 为空 → 推荐 decompose <EPIC-xxx>
  • 其他 → 推荐 discover

输出

  • 渐进暴露:默认输出简洁摘要,--detail 展示完整信息
  • 操作确认:写入操作前展示变更预览,用户确认后执行
  • 追溯链:每次创建实体时展示其在价值链中的位置

各子命令输出格式索引

权威模板在各 procedures 文件中。

子命令输出摘要权威源
opportunity已捕获业务机会:OPP-xxx -- [描述],状态:评估中skills/pace-biz/biz-procedures-opportunity.md Step 4
epic已创建专题:EPIC-xxx -- [名称],关联 OBJ + MoSskills/pace-biz/biz-procedures-epic.md Step 8
decompose (Epic)已分解 EPIC-xxx:BR 列表 + 依赖关系 + 价值链skills/pace-biz/biz-procedures-decompose-epic.md Step 6
decompose (BR)已分解 BR-xxx:PF 列表 + 优先级 + 价值链skills/pace-biz/biz-procedures-decompose-br.md Step 6
refine已精炼 [BR/PF]:变更摘要 + 就绪度变化skills/pace-biz/biz-procedures-refine.md Step 4
align战略对齐度报告:覆盖率 + 孤立实体 + 就绪度 + 趋势skills/pace-biz/biz-procedures-align.md Step 3
view业务全景:OPP->EPIC->BR->PF->CR 树视图 + 统计skills/pace-biz/biz-procedures-view.md Step 2
discover已从发现会话创建:OPP + Epic + BR + PF 汇总skills/pace-biz/biz-procedures-discover.md Step 6
import导入完成:新增 + 丰富 + 跳过 汇总skills/pace-biz/biz-procedures-import.md Step 6
infer代码库推断完成:追踪 + 技术债务 + 未实现 汇总skills/pace-biz/biz-procedures-infer.md Step 6

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Pace Biz AI skill do?

Use when user says "业务机会/OPP", "专题/Epic", "分解需求/decompose", "精炼/refine", "战略对齐/align", "业务全景/view", "需求发现/brainstorm/discover", "导入/import", "技术债务/infer", "pace-biz", or wants to plan requirements. NOT for /pace-dev, -change, -plan, -init.

Why use Pace Biz on TypingMind?

Because you install it once and use it with any model. Pace Biz is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pace Biz in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/arch-team/devpace/tree/main/skills/pace-biz. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Pace Biz?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pace Biz?

As many as you like. As long as a model supports skills, you can use Pace Biz with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pace Biz AI skill free?

Yes. It is published on GitHub by arch-team under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇