tangram-define — for Claude Code tangram-define, multi-restaurant-sample-app, community, for Claude Code, ide skills, tangram:constitution, adaptation, tangram:define, corresponding, Tangram

v1.0.0

Über diesen Skill

Geeigneter Einsatz: Ideal for AI agents that need codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml. Lokalisierte Zusammenfassung: Codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Funktionen

Codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml.
You are the Tangram Build AI executing the define command.
Input: Triggered by /tangram:define. Optionally, the user may include an idea or an update request.
Check State & Analyze
First, check if tangram/overview.md already exists and read its contents.

# Kernthemen

JeroTan JeroTan
[0]
[0]
Aktualisiert: 5/5/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Geeigneter Einsatz: Ideal for AI agents that need codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml. Lokalisierte Zusammenfassung: Codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Warum diese Fähigkeit verwenden

Empfehlung: tangram-define helps agents codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml. Codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml.

Am besten geeignet für

Geeigneter Einsatz: Ideal for AI agents that need codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml.

Handlungsfähige Anwendungsfälle for tangram-define

Anwendungsfall: Codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml
Anwendungsfall: You are the Tangram Build AI executing the define command
Anwendungsfall: Input: Triggered by /tangram:define. Optionally, the user may include an idea or an update request

! Sicherheit & Einschränkungen

  • Einschraenkung: Do not write the file yet. Just show the suggested content.
  • Einschraenkung: Do not write the file yet
  • Einschraenkung: Requires repository-specific context from the skill documentation

About The Source

The section below is adapted from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Labs-Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ und Installationsschritte

These questions and steps mirror the structured data on this page for better search understanding.

? Häufige Fragen

Was ist tangram-define?

Geeigneter Einsatz: Ideal for AI agents that need codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml. Lokalisierte Zusammenfassung: Codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Wie installiere ich tangram-define?

Führen Sie den Befehl aus: npx killer-skills add JeroTan/multi-restaurant-sample-app/tangram-define. Er funktioniert mit Cursor, Windsurf, VS Code, Claude Code und mehr als 19 weiteren IDEs.

Wofür kann ich tangram-define verwenden?

Wichtige Einsatzbereiche sind: Anwendungsfall: Codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml, Anwendungsfall: You are the Tangram Build AI executing the define command, Anwendungsfall: Input: Triggered by /tangram:define. Optionally, the user may include an idea or an update request.

Welche IDEs sind mit tangram-define kompatibel?

Dieser Skill ist mit Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer kompatibel. Nutzen Sie die Killer-Skills CLI für eine einheitliche Installation.

Gibt es Einschränkungen bei tangram-define?

Einschraenkung: Do not write the file yet. Just show the suggested content.. Einschraenkung: Do not write the file yet. Einschraenkung: Requires repository-specific context from the skill documentation.

So installieren Sie den Skill

  1. 1. Terminal öffnen

    Öffnen Sie Ihr Terminal oder die Kommandozeile im Projektverzeichnis.

  2. 2. Installationsbefehl ausführen

    Führen Sie aus: npx killer-skills add JeroTan/multi-restaurant-sample-app/tangram-define. Die CLI erkennt Ihre IDE oder Ihren Agenten automatisch und richtet den Skill ein.

  3. 3. Skill verwenden

    Der Skill ist jetzt aktiv. Ihr KI-Agent kann tangram-define sofort im aktuellen Projekt verwenden.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below is adapted from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

tangram-define

Codex adaptation of.codex/workflows/tangram/commands/tangram/preconstruct/define.toml. This AI agent skill supports Claude Code, Cursor, and Windsurf

SKILL.md
Readonly
Upstream Repository Material
The section below is adapted from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

Codex adaptation of .codex/workflows/tangram/commands/tangram/preconstruct/define.toml.

Use this skill when the user asks for /tangram:define, $tangram-define, or the corresponding Tangram workflow in natural language. Codex does not load source workflow .toml command files directly; this SKILL.md carries the converted prompt.

You are the Tangram Build AI executing the define command. Your goal is to guide the user in generating or updating tangram/overview.md, which serves as the general, high-level summary of the application.

Input: Triggered by /tangram:define. Optionally, the user may include an idea or an update request.

Steps

  1. Check State & Analyze First, check if tangram/overview.md already exists and read its contents.

    • If it DOES NOT exist (Creation Mode): Review the user's input. If the name or the idea is omitted/vague, you MUST ask: "What is the name of the app/project and the general idea of what you want to build?"
    • If it DOES exist (Update Mode): Compare the user's new input against the current overview.md. Act as a strategic partner. Acknowledge the shift and ask for their reasoning to ensure the app's vision stays coherent. Example: "I see you want to add/remove [Feature]. Our original overview focused on [Original Focus]. What is driving this change? Should we adjust the Target Audience or Vision to reflect this pivot?" Wait for their response before drafting.
  2. Suggest the Draft Once you have the necessary context, generate a draft for tangram/overview.md using the template below and present it to the user. Do not write the file yet. Just show the suggested content.

  3. Wait for Approval Ask: "Does this capture the core idea, or would you like to make further adjustments before we finalize it?" Pause and wait for the user's response.

  4. Summarize and Write Once the user approves (or after applying their requested adjustments), write the final content to tangram/overview.md. Announce that the file has been successfully created or updated.

Output On Success

Project Definition Complete

File Created: tangram/overview.md Vision: [App Name] core concept established.

Next Action: Run /tangram:constitution to establish the non-negotiable laws and principles of your project.

Draft Template for tangram/overview.md

[App Name / Working Title]

Core Concept

[1-2 paragraphs explaining what the app is and its primary value proposition. Keep it simple and visionary.]

Target Audience

[A brief description of who this application is built for.]

High-Level Vision

[A short summary of what the app will feel like from a user's perspective, focusing on the main problem it solves.]

Guardrails

  • Identity First: Never proceed with the draft until a name or working title is established.
  • Strict Loop: Suggest -> Approve -> Summarize -> Write.
  • Consultative Tone: Ensure any updates to the vision make logical sense before overwriting the file.

Verwandte Fähigkeiten

Looking for an alternative to tangram-define or another community skill for your workflow? Explore these related open-source skills.

Alle anzeigen

openclaw-release-maintainer

Logo of openclaw
openclaw

Lokalisierte Zusammenfassung: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

333.8k
0
Künstliche Intelligenz

widget-generator

Logo of f
f

Lokalisierte Zusammenfassung: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat. It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code

149.6k
0
Künstliche Intelligenz

flags

Logo of vercel
vercel

Lokalisierte Zusammenfassung: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
Browser

pr-review

Logo of pytorch
pytorch

Lokalisierte Zusammenfassung: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review. It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
Entwickler