start-gsd-2

GitHub

指导用户通过 /start-gsd-2 命令启动 GSD 项目初始化流程,包括运行新命令、回答访谈问题及等待规划生成。

gsd-framework/.claude/skills/start-gsd-2/SKILL.md carlvellotti/free-ai-courses

Trigger Scenarios

用户输入 /start-gsd-2 需要初始化新项目或学习 GSD 第一课

Install

npx skills add carlvellotti/free-ai-courses --skill start-gsd-2 -g -y
More Options

Non-standard path

npx skills add https://github.com/carlvellotti/free-ai-courses/tree/main/gsd-framework/.claude/skills/start-gsd-2 -g -y

Use without installing

npx skills use carlvellotti/free-ai-courses@start-gsd-2

指定 Agent (Claude Code)

npx skills add carlvellotti/free-ai-courses --skill start-gsd-2 -a claude-code -g -y

安装 repo 全部 skill

npx skills add carlvellotti/free-ai-courses --all -g -y

预览 repo 内 skill

npx skills add carlvellotti/free-ai-courses --list

SKILL.md

Frontmatter
{
    "name": "start-gsd-2",
    "description": "Learn GSD lesson 2 through its file-backed planning and build workflow. Use when the student types \/start-gsd-2.",
    "allowed-tools": [
        "Read",
        "Write",
        "Bash",
        "AskUserQuestion",
        "Skill"
    ],
    "disable-model-invocation": true
}

3.2 Start a Project

Setup

ACTION: Read and follow .claude/rules/teaching-rules.md before teaching. Then run this idempotent staging action. It never replaces existing work. Echo and summarize the clickable staged path.

mkdir -p "expense-splitter"
printf '[expense-splitter](expense-splitter/)\\n'

In this lesson, you'll run /gsd:new-project for the first time.

Here's what GSD is going to do:

  1. Interview you about what you want to build (~3-5 mins of your input)
  2. Spawn research agents to investigate best practices, architecture, pitfalls (~5-10 mins)
  3. Create requirements organized into v1/v2/out-of-scope
  4. Generate a roadmap with phases and success criteria
  5. Save everything to expense-splitter/.planning/

All from one command. You just answer questions when prompted.

STOP: Ready?

USER: Yes


Before You Run It

A few important things:

This will take 10-15 minutes. Most of that is GSD researching and planning while you wait. That's normal - it's doing real work.

You'll be asked questions first. Use your PROJECT_BRIEF.md as reference when describing the Expense Splitter. You can customize features however you want - whatever you choose WILL get built.

You'll see optional agent toggles. GSD will ask if you want:

  • Research agents - investigate best practices (recommended ON)
  • Plan checker - verifies plans achieve goals (recommended ON)
  • Verifier - confirms work after execution (recommended ON)

These add quality but also add time. I recommend enabling all of them for the full experience.

When it finishes, you'll see "PROJECT INITIALIZED" and be back at the normal composer. I will narrate progress and summarize the result in prose.

STOP: What will you type when GSD finishes and you're back at the normal prompt?

USER: Done

Exactly - you'll type "done" so we can continue the lesson together.


Run It

Type /gsd:new-project and hit enter.

GSD will take over and start asking you questions. Answer using PROJECT_BRIEF.md as a guide and describe the Expense Splitter features.

Remember: this takes 10-15 minutes. Grab a coffee if you want. When you see "PROJECT INITIALIZED" and you're back at the normal prompt, type "done".

STOP: Run /gsd:new-project now. Type "done" when you're back at the normal prompt.

USER: Done


Let's See What GSD Created

Nice work! GSD just did a lot behind the scenes.

It interviewed you to understand your vision. It spawned research agents in parallel to investigate stack options, feature patterns, architecture approaches, and common pitfalls. Then it synthesized everything into a structured spec.

And your main context stayed clean while all those agents did the heavy lifting.

Let's tour what it created.

ACTION: List expense-splitter/.planning/, echo the file names in prose, and include clickable links.


You should see several files. Let me walk you through each one.

ACTION: Read PROJECT.md and summarize its contents.

PROJECT.md is your project vision and constraints - the high-level "what and why." It captures what you described in the interview.

STOP: Does it match what you described?

USER: Yes


ACTION: Read REQUIREMENTS.md and summarize its contents.

REQUIREMENTS.md has your features organized into v1, v2, and out-of-scope.

Notice the REQ-IDs - things like PEOPLE-01, SPLIT-02. These trace through the whole system. Every requirement maps to exactly one phase. When GSD builds and verifies, it references these IDs.

STOP: See how it organized the features?

USER: Yes


ACTION: Read ROADMAP.md and summarize its contents.

ROADMAP.md shows the phases and what each one delivers.

Each phase has success criteria - these are observable behaviors, not just tasks.

"User can add people to the bill" is a success criterion. "Create People component" is just a task. GSD thinks in outcomes.

STOP: Make sense how the roadmap is structured?

USER: Yes


ACTION: Read STATE.md and summarize its contents.

STATE.md is GSD's memory. It tracks where you are, what decisions were made, any blockers.

Here's the cool part: these files persist in the Desktop project tree. In a new session, use Cmd+N, invoke /start-gsd-2, link STATE.md, and GSD uses its recorded position to resume the workflow.

STOP: Pretty useful, right?

USER: Yes


Recap

You just went from project brief to complete spec with one command.

GSD interviewed you, researched best practices, and created traceable requirements. expense-splitter/.planning/ is now your source of truth.

Here's what you have:

  • PROJECT.md - Vision and constraints
  • REQUIREMENTS.md - Features with IDs that trace through the system
  • ROADMAP.md - Phases with success criteria (outcomes, not tasks)
  • STATE.md - Persistent memory across sessions

Next, we'll plan Phase 1. You'll see how GSD breaks it into small, atomic tasks - the secret to keeping quality high.

STOP: Ready to plan the build? Type /start-gsd-3 to continue.

USER: Ready


Important Notes for Claude

  • If .planning folder doesn't exist, the new-project command may have failed - have them run it again
  • The exact file contents will vary based on their interview answers
  • STATE.md might be minimal at this point - that's normal
  • After "done": Always walk through each file in expense-splitter/.planning/, read it, summarize it, and link it.
  • The file tour is critical for understanding what GSD created

Success Criteria

  • Student ran /gsd:new-project successfully
  • expense-splitter/.planning/ exists with PROJECT.md, REQUIREMENTS.md, ROADMAP.md, STATE.md
  • Student saw and understood what each file contains (Claude read and summarized each)
  • Student understands STATE.md enables session persistence
  • Student knows requirements have IDs that trace through the system
  • Student understands roadmap has success criteria (outcomes, not tasks)

Sendoff

ACTION: Before wrapping up, record this lesson as complete by running this WITHOUT NARRATING the raw output:

fspm progress complete gsd-2

If it fails because the fspm CLI isn't installed, follow the teaching rules' missing-CLI guidance: tell the learner progress tracking needs the FSPM CLI, offer to install it, and continue the wrap-up either way.

Then close out with the student's options, in natural language (never as a command list):

  • Mention they can leave feedback on this lesson anytime — if they have some, collect it conversationally and submit it with the CLI (see teaching rules).
  • Remind them, briefly and only if it fits the moment, that they can always ask for a recap, a quiz on what they just did, a saved note, or where they stand in the course.
  • End with the next step: when you're ready for the next lesson, use /clear first, then:

/start-gsd-3

Version History

  • 8a6f91b Current 2026-07-31 07:49

    更新课程结尾的标准交互模式,整合教学规则CLI契约及始终可询问的能力。

  • 058c617 2026-07-23 00:56

Same Skill Collection

claude-code-everyone-course/course-materials/.claude/skills/start-1-1/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-1-2/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-1-3/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-1-4/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-1-5/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-1-6/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-1-7/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-1-8/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-2-1/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-2-2/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-2-3/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-2-4/SKILL.md
claude-code-everyone-course/course-materials/.claude/skills/start-2-5/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/auq/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/convert-doc/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/draft-and-humanize/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/draft-followups/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/humanizer/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/marketing-psychology/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/news/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/process-meetings-plus/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/standup/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/start-skills-1/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/start-skills-2/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/start-skills-3/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/start-skills-4/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/start-skills-5/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/write-proposal/SKILL.md
codex-for-pms-skills-bonus/.agents/skills/writing-voice/SKILL.md
codex-pm-course/.agents/skills/start-1-1/SKILL.md
codex-pm-course/.agents/skills/start-1-2/SKILL.md
codex-pm-course/.agents/skills/start-1-3/SKILL.md
codex-pm-course/.agents/skills/start-1-4/SKILL.md
codex-pm-course/.agents/skills/start-1-5/SKILL.md
codex-pm-course/.agents/skills/start-1-6/SKILL.md
codex-pm-course/.agents/skills/start-2-1/SKILL.md
codex-pm-course/.agents/skills/start-2-2/SKILL.md
codex-pm-course/.agents/skills/start-2-3/SKILL.md
codex-pm-course/.agents/skills/start-3-1/SKILL.md
codex-pm-course/.agents/skills/start-3-2/SKILL.md
codex-pm-course/.agents/skills/start-3-3/SKILL.md
codex-pm-course/.agents/skills/start-3-4/SKILL.md
codex-pm-course/.agents/skills/start-3-5/SKILL.md
course-materials/.claude/skills/pptx/SKILL.md
course-materials/.claude/skills/start-1-1/SKILL.md
course-materials/.claude/skills/start-1-2/SKILL.md
course-materials/.claude/skills/start-1-3/SKILL.md
course-materials/.claude/skills/start-1-4/SKILL.md
course-materials/.claude/skills/start-1-5/SKILL.md
course-materials/.claude/skills/start-1-6/SKILL.md

Metadata

Files
0
Version
8a6f91b
Hash
65cb9f51
Indexed
2026-07-23 00:56

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-06 00:45
浙ICP备14020137号-1 $방문자$