faf-go

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

FAF Go — Guided Path to 100% ✪

FAF Go — 通往100% ✪的引导路径

"Just type /faf-go, answer questions till you're done. 100% target."

.faf

is an IANA-registered context format (

application/vnd.faf+yaml

) — a typed, portable file you own, readable by any AI. faf-cli scores on 21 slots; your

app_type

selects which are active, and 100% ✪ = every active slot filled. This skill is the guided interview that gets you there: the AI fills what it can detect, then asks you — via Claude Code's AskUserQuestion — only for the gaps it can't source.

"只需输入/faf-go，回答问题直至完成。目标：100%。"

.faf

是一种IANA注册的上下文格式（

application/vnd.faf+yaml

）——一种由你拥有的类型化可移植文件，可被任何AI读取。faf-cli会对21个维度进行评分；你的

app_type

会选择哪些维度处于「激活」状态，而100% ✪意味着所有激活维度均已填写完整。本技能就是帮你达成这一目标的引导式访谈：AI会自动填充它能检测到的内容，然后通过Claude Code的AskUserQuestion工具，仅向你询问它无法获取的缺失信息。

When to Use This Skill

何时使用本技能

Activate when:

User wants to improve their .faf score
User mentions "Gold Code" or "100%"
User has incomplete project context
After
```
faf init
```
to fill in missing fields
User says "help me with my .faf"

在以下场景激活：

用户想要提升其.faf文件的评分
用户提及「黄金代码」或「100%」
用户的项目上下文信息不完整
执行
```
faf init
```
后需要填充缺失字段
用户表示「帮我处理我的.faf文件」

Integration with Claude Code

与Claude Code的集成

FAF Go is built FOR Claude Code:

AskUserQuestion - Native Claude Code UI for questions
multiSelect: true - Allow multiple answers (e.g., "pytest + WJTTC")
TodoWrite - Track progress through the interview
Structured output - JSON that Claude Code understands
Bi-sync - Answers flow to .faf AND CLAUDE.md

FAF Go专为Claude Code打造：

AskUserQuestion - 原生Claude Code提问UI
multiSelect: true - 支持多选答案（例如："pytest + WJTTC"）
TodoWrite - 跟踪访谈进度
结构化输出 - Claude Code可识别的JSON格式
双向同步 - 答案会同步至.faf文件和CLAUDE.md

multiSelect Support

多选支持

Some questions allow multiple selections:

```
stack.testing
```
→ "pytest + WJTTC"
```
stack.cicd
```
→ "GitHub Actions + Cloud Build"
```
stack.frontend
```
→ "React + Tailwind"
```
human_context.who
```
→ "Developers + AI agents"

When

multiSelect: true

, user can pick 2+ options. Results are joined with " + ".

部分问题允许多选：

```
stack.testing
```
→ "pytest + WJTTC"
```
stack.cicd
```
→ "GitHub Actions + Cloud Build"
```
stack.frontend
```
→ "React + Tailwind"
```
human_context.who
```
→ "Developers + AI agents"

当

multiSelect: true

时，用户可选择2个及以上选项，结果将用" + "连接。

Workflow

工作流程

Step 1: Check Current State

步骤1：检查当前状态

Run faf score to understand current position:

bash

faf score --verbose

Or get it as structured data for programmatic use:

bash

faf score --json

--json

returns the score + per-slot breakdown — the empty slots are what you interview on (the priority order is in Step 2).

运行faf score命令了解当前评分：

bash

faf score --verbose

或获取结构化数据用于程序化调用：

bash

faf score --json

--json

参数会返回评分及各维度的详细情况——空维度就是需要访谈补充的内容（优先级顺序见步骤2）。

Step 2: Ask Questions Using AskUserQuestion

步骤2：使用AskUserQuestion提问

For each missing field, use Claude Code's AskUserQuestion tool:

Priority Order (most impactful first):

```
project.goal
```
- What does this project do?
```
human_context.why
```
- Why does this exist?
```
human_context.who
```
- Who uses this?
```
human_context.what
```
- What problem does it solve?
```
project.main_language
```
- Primary language
```
stack.database
```
- Database choice
```
stack.hosting
```
- Where is it deployed?
```
stack.frontend
```
- Frontend framework
```
stack.backend
```
- Backend framework
```
human_context.where
```
- Environment
```
human_context.when
```
- Timeline/phase
```
human_context.how
```
- How the project is built (sourced from the stack)

针对每个缺失字段，使用Claude Code的AskUserQuestion工具：

优先级顺序（影响从高到低）：

```
project.goal
```
- 该项目的功能是什么？
```
human_context.why
```
- 该项目存在的原因是什么？
```
human_context.who
```
- 谁会使用这个项目？
```
human_context.what
```
- 它解决了什么问题？
```
project.main_language
```
- 主要开发语言
```
stack.database
```
- 数据库选择
```
stack.hosting
```
- 部署位置
```
stack.frontend
```
- 前端框架
```
stack.backend
```
- 后端框架
```
human_context.where
```
- 运行环境
```
human_context.when
```
- 时间线/阶段
```
human_context.how
```
- 项目构建方式（从技术栈中获取）

Step 3: Apply Answers

步骤3：应用答案

After collecting answers, update the .faf file:

bash

undefined

收集答案后，更新.faf文件：

bash

undefined

Read current .faf

读取当前.faf文件

cat project.faf

Update fields (use Edit tool)

更新字段（使用编辑工具）

Then verify:

然后验证：

faf score

undefined

faf score

undefined

Step 4: Celebrate or Continue

步骤4：庆祝或继续

If score >= 100: Celebrate Gold Code achievement If score < 100: Continue with remaining questions

如果评分≥100：庆祝达成黄金代码成就如果评分<100：继续完成剩余问题

Question Templates for AskUserQuestion

AskUserQuestion的问题模板

Single-Select Questions (pick one)

单选问题（选一个）

project.goal

json

{
  "question": "What does this project do? (one clear sentence)",
  "header": "Goal",
  "multiSelect": false,
  "options": [
    {"label": "Let me type it", "description": "I'll describe it myself"},
    {"label": "Help me write it", "description": "Guide me through it"}
  ]
}

json

{
  "question": "该项目的功能是什么？（用一句话清晰描述）",
  "header": "目标",
  "multiSelect": false,
  "options": [
    {"label": "我自己输入", "description": "我来描述功能"},
    {"label": "帮我撰写", "description": "引导我完成描述"}
  ]
}

human_context.why

json

{
  "question": "Why does this project exist?",
  "header": "Why",
  "multiSelect": false,
  "options": [
    {"label": "Business need", "description": "Solving a business problem"},
    {"label": "Personal project", "description": "Learning or hobby"},
    {"label": "Open source", "description": "Community contribution"},
    {"label": "Let me explain", "description": "Custom reason"}
  ]
}

json

{
  "question": "该项目存在的原因是什么？",
  "header": "原因",
  "multiSelect": false,
  "options": [
    {"label": "业务需求", "description": "解决业务问题"},
    {"label": "个人项目", "description": "学习或爱好"},
    {"label": "开源项目", "description": "社区贡献"},
    {"label": "我来解释", "description": "自定义原因"}
  ]
}

stack.database

json

{
  "question": "What database do you use?",
  "header": "Database",
  "multiSelect": false,
  "options": [
    {"label": "PostgreSQL", "description": "Relational database"},
    {"label": "MongoDB", "description": "Document database"},
    {"label": "SQLite", "description": "File-based database"},
    {"label": "None", "description": "No database"}
  ]
}

json

{
  "question": "你使用什么数据库？",
  "header": "数据库",
  "multiSelect": false,
  "options": [
    {"label": "PostgreSQL", "description": "关系型数据库"},
    {"label": "MongoDB", "description": "文档型数据库"},
    {"label": "SQLite", "description": "文件型数据库"},
    {"label": "无", "description": "不使用数据库"}
  ]
}

stack.hosting

json

{
  "question": "Where is this deployed?",
  "header": "Hosting",
  "multiSelect": false,
  "options": [
    {"label": "Vercel", "description": "Frontend/serverless"},
    {"label": "AWS", "description": "Amazon Web Services"},
    {"label": "Local only", "description": "Not deployed"},
    {"label": "Other", "description": "Different platform"}
  ]
}

json

{
  "question": "项目部署在哪里？",
  "header": "部署位置",
  "multiSelect": false,
  "options": [
    {"label": "Vercel", "description": "前端/无服务器"},
    {"label": "AWS", "description": "亚马逊云服务"},
    {"label": "仅本地", "description": "未部署"},
    {"label": "其他", "description": "其他平台"}
  ]
}

Multi-Select Questions (pick multiple, joined with " + ")

多选问题（选多个，用" + "连接）

stack.testing

json

{
  "question": "What testing tools/methodologies do you use?",
  "header": "Testing",
  "multiSelect": true,
  "options": [
    {"label": "pytest", "description": "Python testing framework"},
    {"label": "Jest", "description": "JavaScript testing"},
    {"label": "Vitest", "description": "Vite-native testing"},
    {"label": "WJTTC", "description": "Championship methodology (Layer 2)"}
  ]
}

Result format:

pytest + WJTTC

(industry first, WJTTC follows)

Ordering: When both selected, industry tests come first:

```
pytest + WJTTC
```
(not
```
WJTTC + pytest
```
)
WJTTC can also run standalone

json

{
  "question": "你使用什么测试工具/方法论？",
  "header": "测试",
  "multiSelect": true,
  "options": [
    {"label": "pytest", "description": "Python测试框架"},
    {"label": "Jest", "description": "JavaScript测试"},
    {"label": "Vitest", "description": "Vite原生测试"},
    {"label": "WJTTC", "description": "冠军级方法论（第二层）"}
  ]
}

结果格式：

pytest + WJTTC

（行业首创，WJTTC后置）

排序规则： 当同时选中时，行业通用测试工具在前：

```
pytest + WJTTC
```
（而非
```
WJTTC + pytest
```
）
WJTTC也可单独使用

stack.cicd

json

{
  "question": "What CI/CD tools do you use?",
  "header": "CI/CD",
  "multiSelect": true,
  "options": [
    {"label": "GitHub Actions", "description": "GitHub-native CI/CD"},
    {"label": "Cloud Build", "description": "Google Cloud CI/CD"},
    {"label": "CircleCI", "description": "CircleCI pipelines"},
    {"label": "None", "description": "No CI/CD yet"}
  ]
}

Result format:

GitHub Actions + Cloud Build

json

{
  "question": "你使用什么CI/CD工具？",
  "header": "CI/CD",
  "multiSelect": true,
  "options": [
    {"label": "GitHub Actions", "description": "GitHub原生CI/CD"},
    {"label": "Cloud Build", "description": "谷歌云CI/CD"},
    {"label": "CircleCI", "description": "CircleCI流水线"},
    {"label": "无", "description": "尚未使用CI/CD"}
  ]
}

结果格式：

GitHub Actions + Cloud Build

stack.frontend

json

{
  "question": "What frontend technologies do you use?",
  "header": "Frontend",
  "multiSelect": true,
  "options": [
    {"label": "React", "description": "React framework"},
    {"label": "Next.js", "description": "React meta-framework"},
    {"label": "Svelte", "description": "Svelte framework"},
    {"label": "None/API-only", "description": "No frontend"}
  ]
}

json

{
  "question": "你使用什么前端技术？",
  "header": "前端",
  "multiSelect": true,
  "options": [
    {"label": "React", "description": "React框架"},
    {"label": "Next.js", "description": "React元框架"},
    {"label": "Svelte", "description": "Svelte框架"},
    {"label": "无/仅API", "description": "无前端"}
  ]
}

human_context.who

json

{
  "question": "Who uses this project?",
  "header": "Users",
  "multiSelect": true,
  "options": [
    {"label": "Developers", "description": "Software developers"},
    {"label": "End users", "description": "Non-technical users"},
    {"label": "AI agents", "description": "Claude, Gemini, etc."},
    {"label": "Internal team", "description": "Your team only"}
  ]
}

Result format:

Developers + AI agents

json

{
  "question": "谁会使用这个项目？",
  "header": "用户",
  "multiSelect": true,
  "options": [
    {"label": "开发者", "description": "软件开发者"},
    {"label": "终端用户", "description": "非技术用户"},
    {"label": "AI agents", "description": "Claude、Gemini等"},
    {"label": "内部团队", "description": "仅你的团队使用"}
  ]
}

结果格式：

Developers + AI agents

Processing Multi-Select Answers

处理多选答案

When user selects multiple options, join them with " + ":

python

undefined

当用户选择多个选项时，用" + "连接：

python

undefined

Example: User selects ["pytest", "WJTTC"]

示例：用户选择["pytest", "WJTTC"]

selected = ["pytest", "WJTTC"] value = " + ".join(selected) # "pytest + WJTTC"


This creates readable, scannable values in the .faf file:
```yaml
stack:
  testing: pytest + WJTTC
  cicd: GitHub Actions + Cloud Build

selected = ["pytest", "WJTTC"] value = " + ".join(selected) # "pytest + WJTTC"


这会在.faf文件中生成易读、易扫描的值：
```yaml
stack:
  testing: pytest + WJTTC
  cicd: GitHub Actions + Cloud Build

Example Session

会话示例

User: /faf-go

Claude: Let me check your current .faf status.

[Runs: faf score --verbose]

Your score is 45%. Let's get you to Gold Code!

[Uses AskUserQuestion for project.goal]

User: [Selects option or types custom]

Claude: Great! Now let's capture why this project exists.

[Uses AskUserQuestion for human_context.why]

... continues until 100% ...

Claude: ✪ GOLD CODE ACHIEVED!
Your AI now has complete context for championship performance.

用户: /faf-go

Claude: 让我检查你当前的.faf文件状态。

[执行: faf score --verbose]

你的当前评分是45%。让我们一起达成黄金代码！

[使用AskUserQuestion询问project.goal]

用户: [选择选项或输入自定义内容]

Claude: 很棒！现在让我们记录这个项目存在的原因。

[使用AskUserQuestion询问human_context.why]

... 持续提问直至评分达100% ...

Claude: ✪ 达成黄金代码！
你的AI现在拥有完整的项目上下文，可实现冠军级性能。

TodoWrite Integration

TodoWrite集成

Track progress with todos:

javascript

[
  {"content": "Answer project.goal question", "status": "completed"},
  {"content": "Answer human_context.why question", "status": "in_progress"},
  {"content": "Answer stack.database question", "status": "pending"},
  {"content": "Verify Gold Code achieved", "status": "pending"}
]

通过待办事项跟踪进度：

javascript

[
  {"content": "回答project.goal问题", "status": "completed"},
  {"content": "回答human_context.why问题", "status": "in_progress"},
  {"content": "回答stack.database问题", "status": "pending"},
  {"content": "验证是否达成黄金代码", "status": "pending"}
]

CLI Fallback

CLI备选方案

Outside Claude Code, the same destination is reached with the CLI's own interactive interview:

bash

faf go            # interactive terminal interview (--resume continues a session)

This skill is the Claude-native version of that interview — AskUserQuestion instead of terminal prompts. For structured, programmatic data, use

faf score --json

在Claude Code之外，你也可以通过CLI自带的交互式访谈达成目标：

bash

faf go            # 交互式终端访谈（--resume可继续未完成的会话）

本技能是该访谈的Claude原生版本——用AskUserQuestion替代终端提示。如需结构化的程序化数据，可使用

faf score --json

。

Success Metrics

成功指标

User reaches 100% score
All required fields filled with meaningful content
No placeholder values (TBD, Unknown, None where inappropriate)
User understands what each field is for

用户评分达到100%
所有必填字段均填写有意义的内容
无占位符值（如TBD、Unknown、不恰当的None）
用户理解每个字段的用途

On Completion

完成后

When 100% ✪ is achieved:

✪ 100% — Gold Code

project.faf: complete
CLAUDE.md:   synced from .faf

Optionally run

faf sync

to emit CLAUDE.md / AGENTS.md from the .faf. Your AI now starts every session with complete project context.

当达成100% ✪时：

✪ 100% — 黄金代码

project.faf: 已完成
CLAUDE.md:   已从.faf同步

可选择执行

faf sync

从.faf文件生成CLAUDE.md / AGENTS.md。此后你的AI在每次会话开始时都会拥有完整的项目上下文。

Related Skills

Limitations

局限性

Use this skill only when the task clearly matches its upstream source and local project context.
Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.
Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.

仅当任务与上游源和本地项目上下文明确匹配时使用本技能。
在应用更改前，请验证命令、生成的代码、依赖项、凭据和外部服务行为。
请勿将示例替代为特定环境的测试、安全审查或用户对破坏性/高成本操作的批准。

faf-go

Original

Translation

FAF Go — Guided Path to 100% ✪

FAF Go — 通往100% ✪的引导路径

When to Use This Skill

何时使用本技能

Integration with Claude Code

与Claude Code的集成

multiSelect Support

多选支持

Workflow

工作流程

Step 1: Check Current State

步骤1：检查当前状态

Step 2: Ask Questions Using AskUserQuestion

步骤2：使用AskUserQuestion提问

Step 3: Apply Answers

步骤3：应用答案

Read current .faf

读取当前.faf文件

Update fields (use Edit tool)

更新字段（使用编辑工具）

Then verify:

然后验证：

Step 4: Celebrate or Continue

步骤4：庆祝或继续

Question Templates for AskUserQuestion

AskUserQuestion的问题模板

Single-Select Questions (pick one)

单选问题（选一个）

project.goal

project.goal

human_context.why

human_context.why

stack.database

stack.database

stack.hosting

stack.hosting

Multi-Select Questions (pick multiple, joined with " + ")

多选问题（选多个，用" + "连接）

stack.testing

stack.testing

stack.cicd

stack.cicd

stack.frontend

stack.frontend

human_context.who

human_context.who

Processing Multi-Select Answers

处理多选答案

Example: User selects ["pytest", "WJTTC"]

示例：用户选择["pytest", "WJTTC"]

Example Session

会话示例

TodoWrite Integration

TodoWrite集成

CLI Fallback

CLI备选方案

Success Metrics

成功指标

On Completion

完成后

Related Skills

相关技能

Limitations

局限性