Pace Test logo

Pace Test

Community
arch-team
pace-test

Use when user says "跑测试", "测试覆盖", "验证一下", "验收", "回归", "影响分析", "test", "verify", "accept", "coverage", "测试策略", /pace-test, or when test results, coverage gaps, or acceptance readiness are discussed. NOT for code implementation (use /pace-dev). NOT for code review or approval (use /pace-review).

Overview

Publisherarch-team
Repositorydevpace
Skill namepace-test
Stars
73
Forks
6
Bundled files
11
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.

  • 11 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 Test 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-test
  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-test .claude/skills/pace-test
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pace Test 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 Test 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 Test 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-test — BizDevOps 感知的测试策略与验证

基于业务上下文(BR→PF→CR 价值链),智能管理和执行测试验证——不只是"跑测试",而是"基于需求验收标准,评估验证覆盖度和执行 AI 驱动的验收验证"。

与现有机制的关系

  • checks.md:定义 Gate 1/2 要执行的命令列表(what to run)
  • /pace-test:管理测试策略(what to test, why, how comprehensive)
  • /pace-dev Gate 1/2:消费 checks.md 中的测试命令
  • /pace-review Gate 2:可消费 /pace-test accept 的验收映射报告作为审查证据

accept 的定位

Gate 2 仅二元判定整体一致性。accept 提供精细能力:逐条验收标准附证据、三级判定(✅/⚠️/❌)、测试预言审查断言实质性、弱覆盖自动降级策略。不做 accept 也能过 Gate 2,但做了的 CR 在 Gate 3 有更充分的证据支撑(详见 skills/pace-test/test-procedures-verify.md)。

输入

$ARGUMENTS:

日常使用(大多数场景只需这些):

  • (空)→ 对当前 CR 运行所有已配置的测试,输出结构化报告
  • accept [CR编号] → AI 驱动的验收验证:逐条比对 PF 验收标准与实际行为
  • strategy → 基于 PF 验收标准生成测试策略建议
  • coverage → 分析当前测试对 PF 验收标准的覆盖度(需求覆盖率 + 代码覆盖率辅助信号)
  • impact [CR编号] [--run] → 变更影响分析:基于变更范围推荐需要重跑的测试(--run 自动执行必跑测试)
  • report [CR编号|REL-xxx] → 生成面向人类的测试摘要报告(支持 CR 级和 Release 级)

深度功能(按需使用):

  • generate [PF标题] [--full] → 基于 PF 验收标准生成测试用例(默认骨架,--full 生成完整实现)
  • flaky → 分析历史测试结果,识别不稳定测试并建议修复/隔离
  • dryrun [1|2|4] → 模拟执行指定 Gate 的完整检查流程(dry-run)
  • baseline → 建立/更新测试基准线(供 /pace-retro 度量使用)

向后兼容:旧名称 verify/regress/gen/gate 仍可使用,自动映射到新名称。

推荐使用流程

  • 首次:strategy → generate → coverage → 无参数运行 → accept → report
  • 日常:accept + 无参数运行。迭代中 impact --run 快速执行受影响测试
  • 深度:flaky · dryrun · baseline 按需使用。发布:report REL-xxx

流程

Step 1:上下文加载

  1. 检查 .devpace/ 是否存在:
    • 存在 → 读取 state.md 确定当前 CR,读取 project.md 获取 PF 列表
    • 不存在 → 降级模式:基于代码库直接分析(无 PF→测试映射能力,仅 Layer 1 可用)
  2. 如果指定了 CR 编号 → 定位对应 CR 文件
  3. 如果未指定 → 读取 state.md 当前活跃 CR
  4. 读取 .devpace/rules/checks.md(如存在)

Step 2:路由到子命令

根据 $ARGUMENTS 第一个参数路由(仅读取匹配子命令的规程文件,不加载全部规程)。非自包含子命令执行前加载 skills/pace-test/test-procedures-common.md(分层输出约定 + 技术栈检测 SSOT)。

参数流程详细规程
(空)Layer 1 基础执行skills/pace-test/test-procedures-core.md §1
accept(旧名 verify)Layer 3 AI 验收验证skills/pace-test/test-procedures-verify.md
generate(旧名 gen)测试用例生成skills/pace-test/test-procedures-generate.md(自包含)
strategy测试策略生成skills/pace-test/test-procedures-strategy-gen.md
coverage需求覆盖分析skills/pace-test/test-procedures-coverage.md
impact(旧名 regress)变更影响分析skills/pace-test/test-procedures-impact.md
report测试摘要报告(CR 级/Release 级)skills/pace-test/test-procedures-report.md
flaky不稳定测试分析skills/pace-test/test-procedures-flaky.md(自包含)
dryrun(旧名 gate)模拟门禁执行skills/pace-test/test-procedures-dryrun.md(自包含)
baseline测试基准线skills/pace-test/test-procedures-baseline.md(自包含)

Step 3:执行并报告

  1. 按子命令流程执行
  2. 将关键结果写入 CR 文件"验证证据"section(如 verify 产出)
  3. 更新 state.md(如有状态变化)
  4. 智能推荐(仅空参数运行时):根据 CR 状态推荐下一步(规则见 skills/pace-test/test-procedures-common.md)

输出

分阶段输出:子命令执行结果 + 下一步建议。支持 --brief / --detail 三级输出详细度(规则见 skills/pace-test/test-procedures-common.md)。

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 Test AI skill do?

Use when user says "跑测试", "测试覆盖", "验证一下", "验收", "回归", "影响分析", "test", "verify", "accept", "coverage", "测试策略", /pace-test, or when test results, coverage gaps, or acceptance readiness are discussed. NOT for code implementation (use /pace-dev). NOT for code review or approval (use /pace-review).

Why use Pace Test on TypingMind?

Because you install it once and use it with any model. Pace Test 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 Test in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/arch-team/devpace/tree/main/skills/pace-test. 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 Test?

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 Test?

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

Is the Pace Test 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 👇