build-chatgpt-app
Use when the user explicitly wants a ChatGPT App, Apps SDK project, MCP server plus widget UI, ChatGPT-compatible tool UI, or submission/deployment work for that surface. Build, scaffold, refactor, or troubleshoot those projects from Claude Code, consult openai-docs before generating code, and use openai-platform-api-key before any app path that requires live OpenAI API credentials.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-03
- Stars
- ★ 43
- Forks
- 16
01 前言 Front Matter
- description
- Use when the user explicitly wants a ChatGPT App, Apps SDK project, MCP server plus widget UI, ChatGPT-compatible tool UI, or submission/deployment work for that surface. Build, scaffold, refactor, or troubleshoot those projects from Claude Code, consult openai-docs before generating code, and use openai-platform-api-key before any app path that requires live OpenAI API credentials.
03 SKILL.md 正文
Build ChatGPT App
Use this skill for Apps SDK projects that combine an MCP server with a ChatGPT-facing tool or widget experience.
Before You Build
- Use
openai-docsfirst for current Apps SDK guidance. - If the requested app or verification flow calls the OpenAI API, use
openai-platform-api-keybefore API-backed implementation, execution, or smoke tests. - Inspect the target repo before choosing architecture.
Workflow
- Classify the app:
- tool-only
- widget-backed
- submission-ready
- Plan the tool surface before code:
- tool names
- input schemas
- read/write behavior
- annotations and expected outputs
- Choose the smallest repo shape that fits the request.
- Register the MCP server surface and widget resources deliberately.
- Keep structured data, UI metadata, and side effects clear and reviewable.
- Add local run instructions and basic verification steps when implementation is requested.
Rules
- Prefer current OpenAI Apps SDK docs over stale examples.
- Keep tool annotations and widget metadata aligned with actual behavior.
- Treat CSP, domains, and submission-readiness as explicit design inputs when the app is meant for review or launch.
- Use
chatgpt-app-submissionwhen the user needs submission-specific review preparation.
04 同仓库更多 Skills
openai-platform-api-key
Use when Claude Code is asked to build, run, test, debug, or configure an OpenAI-backed or provider-unspecified AI app, UI, script, CLI, generator, or tool, especially requests phrased only as "using AI" or generators driven by forms/user input; also use for OPENAI_API_KEY or sk-proj setup. Do not gate model or prompt migrations that can proceed with source edits and offline validation. Otherwise treat this as the credential gate: inspect safely, ask reuse-vs-new before API work, guide manual local setup when needed, verify presence, and never expose plaintext.
openai-docs
Use whenever the user asks anything about OpenAI products, APIs, models, or SDKs — including factual lookups, coding requests, latest/current/default model selection, prompting guidance, model upgrades, and citation requests. Invoke before calling any openaiDeveloperDocs MCP tool.
openai-api-troubleshooting
Use when an OpenAI API request fails or the user asks what an error means, including blocked access to api.openai.com, 401 invalid_api_key, missing OPENAI_API_KEY, 429 insufficient_quota, 429 rate_limit_exceeded, or 403 model_not_found. Classify the failure, name the next step, route credential setup to openai-platform-api-key, and current guidance to openai-docs.
chatgpt-app-submission
Use when a developer needs a ChatGPT Apps submission import file from an MCP server. Inspect the implementation, generate chatgpt-app-submission.json with app info, tool-hint justifications, positive and negative test cases, then report review findings and outputSchema warnings.
agents-sdk
Use when the user wants to build, adapt, run, or evaluate an OpenAI Agents SDK app from Claude Code. Prefer a docs-first workflow and route API credential decisions through openai-platform-api-key before API-backed work.