git-workflows

Reusable git delivery workflows derived from local slash commands (commit, push, PR, release notes, and GitHub Actions failure triage with worktree-based fixes).

Jump to install

Repository: TencentCloudBase/CloudBase-MCP
Last source activity: June 23, 2026 at 06:29
Detected SKILL.md language: English
Stars: 1,064
Forks: 132

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/TencentCloudBase/CloudBase-MCP --skill git-workflows

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

3 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

ai-model-nodejs

Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express, Koa, NestJS, serverless APIs, scheduled jobs, LLM proxies. Only SDK supporting image generation (ai.createImageModel + generateImage). Text models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field of generateText/streamText. MUST run two-step preflight before code — see body. Keywords: backend, 云函数, 云托管, serverless, LLM proxy, agent orchestration, generateText, streamText, generateImage, createModel, hunyuan-image, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).

2026-07-21

ai-model-web

Use this skill when a browser/Web app (React, Vue, Angular, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI) needs AI models via @cloudbase/js-sdk. Default routing for page/页面/Web/前端/frontend/网页/H5 AI — call directly from browser, do NOT propose a Node.js proxy. Covers generateText and streamText. Models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field. MUST run two-step preflight before code — see body. Keywords: 页面, Web, 前端, React, Vue, Next, Nuxt, SPA, AI chat UI, generateText, streamText, createModel, hunyuan-exp, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).

2026-07-21

ai-model-wechat

Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, 企业微信小程序, wx.cloud apps). Features generateText and streamText with callbacks (onText, onEvent, onFinish). Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the data wrapper model field. API differs from JS/Node SDK — streamText needs data wrapper, generateText returns raw response. MUST run two-step preflight before code — see body. Keywords: Mini Program AI, wx.cloud.extend.AI, 小程序成长计划, ai_miniprogram_inspire_plan, Token Credits 资源包, generateText, streamText, createModel, hunyuan-exp, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web), Node.js backend (use ai-model-nodejs), or image generation (use ai-model-nodejs).

2026-07-21

View all from this repository

name	git-workflows
description	Reusable git delivery workflows derived from local slash commands (commit, push, PR, release notes, and GitHub Actions failure triage with worktree-based fixes).

Git Workflows (from local commands)

This skill turns the repo's former local command templates into reusable git delivery workflows.

When to use this skill

Use this skill when the user asks to:

run a commit workflow (conventional-changelog style)
push changes with safe branching and open a PR
generate release notes from git history / GitHub context
analyze the latest failed GitHub Actions workflow, attempt a fix in an isolated worktree, and submit a PR
check IDE icon configuration consistency across document components and source files

Source of truth

All detailed steps and constraints live in:

references/source-commands.md

This skill describes how to apply them consistently across agents/editors without duplicating implementation details.

Execution rules

Read the requested command template from references/source-commands.md.
Follow it as workflow steps, not as a loose summary.
Keep actions safe by default:
- avoid destructive git operations unless explicitly requested
- avoid committing secrets
- keep changes minimal and localized
If a workflow implies external side effects (push/PR/release), request explicit confirmation right before performing the side effect.

Command mapping

See references/command-catalog.md.

git-workflows

Source facts

Install options

Review the source files

More from this repository

More from this repository

Git Workflows (from local commands)

When to use this skill

Source of truth

Execution rules

Command mapping

Git Workflows (from local commands)

When to use this skill

Source of truth

Execution rules

Command mapping