用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/ktg-one/goodai-mate --skill source-command-init命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Good'ai brutalist/direct-mail frontend: brand tokens, stamp UI, voice hero, asset registry, and ESLint gates. Use when building or reviewing UI in goodai-mate, fixing design fidelity, prepping demos (ABS), running lint, or when the user says /goodai-frontend, goodai frontend, brutalist mail board, stamp design, or frontend-design for this project.
API Route Handler, Server Action, and data mutation patterns for Next.js 16. Zod validation, error handling, auth patterns, cache revalidation.
React 19 + Server Component patterns from official Vercel/React docs. Component templates, hooks patterns, RSC boundaries, performance optimization.
正在显示 SKILL.md
基于 SOC 职业分类
| name | source-command-init |
| description | init |
Use this skill when the user asks to run the migrated source command init.
flowchart TD
start-node-default([Start])
end_node_default([End])
prompt-1775005816205[1. /init]
skill-1775007042958[[Skill: skill-lookup]]
mcp-1775007205350[[MCP: resolve-library-id]]
skill-1775007625044[[Skill: gsd-new-project]]
start-node-default --> prompt-1775005816205
prompt-1775005816205 --> mcp-1775007205350
mcp-1775007205350 --> skill-1775007625044
skill-1775007625044 --> skill-1775007042958
skill-1775007042958 --> end_node_default
Follow the Mermaid flowchart above to execute the workflow. Each node type has specific execution methods as described below.
Description: Resolves a package/product name to a Context7-compatible library ID and returns matching libraries.
You MUST call this function before 'Query Documentation' tool to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.
Each result includes:
For best results, select libraries based on name match, source reputation, snippet coverage, benchmark score, and relevance to your use case.
Selection Process:
Response Format:
For ambiguous queries, request clarification before proceeding with a best-guess match.
IMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best result you have.
MCP Server: context7
Tool Name: resolve-library-id
Validation Status: valid
User Intent (Natural Language Parameter Description):
make a knowledge base of this projects codebase
Parameter Schema (for AI interpretation):
query (string) (required): The question or task you need help with. This is used to rank library results by relevance to what the user is trying to accomplish. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query.libraryName (string) (required): Library name to search for and retrieve a Context7-compatible library ID.Execution Method:
Codex should interpret the natural language description above and set appropriate parameter values based on the parameter schema. Use your best judgment to map the user intent to concrete parameter values that satisfy the constraints.
1. /init
2. git clone "https://github.com/ktg-one/mcp-webdev"
3. npx in-memoria server
4. Read ONBOARD.md
5. sign contract