Token导航 LogoToken导航TokenDH.com
开发敏感数据github未标认证来源可访问许可证需确认审计通过

stitch-sdk-pipelinestitch SDK pipeline 命令行

Agent Skill

stitch-sdk-pipeline 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,154

周安装

88

GitHub Stars

1,576

下载量

697
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:stitch-sdk-pipeline(stitch SDK pipeline 命令行)
来源仓库:https://github.com/google-labs-code/stitch-sdk
仓库路径:skills/stitch-sdk-pipeline
安装命令:
npx skills add https://github.com/google-labs-code/stitch-sdk --skill stitch-sdk-pipeline
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/google-labs-code/stitch-sdk --skill stitch-sdk-pipeline

简介

用于处理 GitHub 仓库和代码协作信息。

  • 适合围绕仓库状态、代码变更进行整理。
  • 可结合来源仓库和原始 README 核验具体用法。
  • 安装前建议确认权限范围和维护状态。stitch-sdk-pipeline 属于开发类 Skill,可作为该场景下的辅助能力补充。
  • 需避免触发联网、命令执行或文件读写。

SKILL.md

Stitch SDK Pipeline

This skill orchestrates the full SDK generation pipeline — from capturing MCP tool schemas to publishing a tested, validated package. Use this when:

  • The Stitch MCP server adds or changes tools
  • You need to regenerate the SDK from scratch
  • You want to verify the pipeline is healthy
[!IMPORTANT] Stage 2 is the only step requiring agent intelligence. All other stages are deterministic scripts. For Stage 2, use the stitch-sdk-domain-design skill.

Prerequisites

  • STITCH_API_KEY environment variable set
  • bun installed
  • Working directory: project root (stitch-sdk/)

Pipeline Stages

Stage 1: Capture Tool Schemas 🤖

// turbo
npm run capture

Connects to the Stitch MCP server, calls tools/list, and writes the raw schemas to packages/sdk/generated/tools-manifest.json. Updates the manifest section of stitch-sdk.lock.

Output: packages/sdk/generated/tools-manifest.json (includes inputSchema + outputSchema for every tool)

When to skip: If tools-manifest.json is already up to date and no server-side changes occurred.


Stage 2: Domain Design 🧠 (Agent)

Use the stitch-sdk-domain-design skill for this stage.

Read tools-manifest.json and edit packages/sdk/generated/domain-map.json to map tools → classes → methods.

Key decisions at this stage:

  • Which class owns each tool?
  • What are the arg routing rules (self, param, computed, selfArray)?
  • What is the response projection path?
  • Should the method cache data from the construction response?

Input: tools-manifest.json + scripts/ir-schema.ts (the canonical IR contract) Output: packages/sdk/generated/domain-map.json

When to skip: If domain-map.json already has the correct bindings and you only changed ir-schema.ts or generate-sdk.ts.


Stage 3: Generate TypeScript 🤖

// turbo
npm run generate

Validates the IR (Zod schema) and every projection (against outputSchema), then emits TypeScript files via ts-morph into packages/sdk/generated/src/.

Output: packages/sdk/generated/src/*.ts + updated stitch-sdk.lock

If this fails with a projection error, go back to Stage 2 and fix domain-map.json.


Stage 4: Build 🤖

// turbo
npm run build

TypeScript compilation: packages/sdk/packages/sdk/dist/.


Stage 5: Unit Tests 🤖

// turbo
npm run test

Runs core unit tests (vitest) — mocked callTool, verifying generated method signatures, caching, and error handling.


Stage 6: Script Tests 🤖

// turbo
npm run test:scripts

Runs contract tests (IR schema acceptance/rejection) and logic tests (expression builders) using bun:test.


Stage 7: E2E Tests 🤖

npm run test:e2e

Live API tests against the built package. Requires STITCH_API_KEY (and GEMINI_API_KEY for AI SDK tests). Two test suites:

  • live.test.ts — Direct SDK calls: create projects, generate screens, verify responses.
  • ai-sdk-e2e.test.ts — AI SDK integration via stitchTools(): Gemini autonomously calls Stitch tools, generates designs, extracts HTML + Tailwind config, produces modular React components, validates via SWC, and scaffolds a Vite preview app at .stitch/preview/.

Stage 8: Lock Validation 🤖

// turbo
npm run validate:generated

Verifies that stitch-sdk.lock hashes match the actual generated files. Catches drift (someone edited generated files manually or forgot to regenerate).

[!IMPORTANT] Always run after Stage 3 (Generate). If you run Capture (Stage 1) then Validate without re-generating, the hashes will mismatch because the manifest hash changed.

Stage 9: Skill Audit 🧠 (Agent)

After the pipeline passes, audit agent skills for freshness. Read the current source of truth and update any skills that reference stale methods, args, or examples.

Inputs:

  • packages/sdk/src/index.ts (public surface)
  • Generated class files in packages/sdk/generated/src/
  • packages/sdk/src/spec/errors.ts (error codes)
  • packages/sdk/src/spec/client.ts (config schema)

Skills to audit (in priority order):

  1. stitch-sdk-usage — highest churn, references specific methods and constructor signatures
  2. stitch-sdk-readme — must document stitchTools(), toolDefinitions, and AI SDK integration examples
  3. stitch-sdk-development — check cache examples match current domain-map patterns
  4. stitch-sdk-domain-design — check code examples in the cache section

Skills to skip: stitch-sdk-pipeline (self-referential), red-green-yellow (generic methodology).

What to check:

  • Every method name in a code example exists on its class
  • Every import in an example matches an export in index.ts
  • Constructor signatures match the actual constructors
  • Config fields match StitchConfigSchema
  • Error codes match StitchErrorCode

When to skip: If only infrastructure code changed (packages/sdk/src/client.ts, packages/sdk/src/proxy/) and no public API surface changed.


Quick Reference

Full pipeline (script stages only)

npm run pipeline

Runs Stage 1 → 3 → 4 → 5 in sequence. Does not include Stage 2 (agent), Stage 7 (e2e), or Stage 9 (skill audit).

Starting from a specific stage

ScenarioStart from
New tool added to MCP serverStage 1
Need to change how a tool maps to a methodStage 2
Changed ir-schema.ts or generate-sdk.tsStage 3
Changed code in packages/sdk/src/ (client, errors)Stage 4
Just want to verify everything worksStage 5
Changed AI SDK tools adapter or tool definitionsStage 5
Public API surface changedStage 9

Key files

FileLocationRole
tools-manifest.jsonpackages/sdk/generated/Raw MCP tool schemas (Stage 1 output)
domain-map.jsonpackages/sdk/generated/IR: tool → class → method mappings (Stage 2 output)
tool-definitions.tspackages/sdk/generated/src/Generated JSON Schema tool definitions for AI SDK
tools-adapter.tspackages/sdk/src/stitchTools() — AI SDK v6 adapter (imported via @google/stitch-sdk/ai)
ir-schema.tsscripts/Zod schema defining valid IR structure
tool-schema.tsscripts/TypeScript types for JSON Schema
generate-sdk.tsscripts/ts-morph codegen (Stage 3)
stitch-sdk.lockpackages/sdk/generated/Integrity hashes for drift detection
stitch-html.tspackages/sdk/test/helpers/Stitch HTML parser (Tailwind config + font extraction)
component-validator.tspackages/sdk/test/helpers/SWC AST validator for generated React components

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.79%
按下载量换算236

Claude

29.75%
按下载量换算207

Cursor

19.16%
按下载量换算134

Gemini CLI

10.73%
按下载量换算75

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills