Token导航 LogoToken导航TokenDH.com
AI 工具只读github未标认证来源可访问clear审计通过

template-engineering模板工程

Agent Skill

template-engineering 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

392

周安装

16

GitHub Stars

61

下载量

125
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

3

许可证

MIT

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:template-engineering(模板工程)
来源仓库:https://github.com/melodic-software/claude-code-plugins
仓库路径:skills/template-engineering
安装命令:
npx skills add https://github.com/melodic-software/claude-code-plugins --skill template-engineering
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/melodic-software/claude-code-plugins --skill template-engineering

简介

template-engineering 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 中围绕仓库状态、代码变更或协作事项进行整理时使用。

  • 适用于项目管理、代码审查、团队协作和版本控制相关任务。
  • 可自动解析仓库结构、跟踪 Issue 进展、分析 PR 差异并生成协作摘要。
  • 安装命令:npx skills add https://github.com/melodic-software/claude-code-plugins --skill template-engineering。
  • 使用前需确认权限范围、维护状态及是否触发联网或命令执行操作。

SKILL.md

Template Engineering

Guide for creating meta-prompt templates - prompts that build prompts.

When to Use

  • Creating new slash commands that generate plans
  • Encoding team workflows into reusable templates
  • Designing meta-prompts for chores, bugs, features
  • Analyzing existing templates for improvement

Template Anatomy

Every effective template has five sections:

1. Purpose Section

Clear description at the top:

# [Work Type] Planning

Create a new plan in specs/*.md to resolve the [Work Type] using
the exact specified markdown Plan Format.

2. Instructions Section

Guidance for the agent:

## Instructions

- You are writing a plan, not implementing
- Use your reasoning model: THINK HARD about the plan
- Focus on files in the Relevant Files section
- Include validation commands that verify completion
- Fill in every section of the Plan Format

3. Relevant Files Section

Guide context loading:

## Relevant Files

Focus on the following files:
- README.md (project context)
- src/** (source code)
- tests/** (test patterns)
- docs/** (documentation)

4. Plan Format Section

Template with placeholders:

## Plan Format

# [WorkType]: <name>

## Description
<what needs to be done>

## Relevant Files
<files to modify>

## Step by Step Tasks
<numbered actionable tasks>

## Validation Commands
<commands proving completion>

## Notes
<edge cases and considerations>

5. Parameter Section

Accept user input:

## [WorkType]
$ARGUMENTS

Design Workflow

Step 1: Identify the Work Type

What class of problems does this template solve?

  • Chores: Maintenance, updates, cleanup
  • Bugs: Investigation and fixes
  • Features: New functionality
  • Refactors: Code improvement

Step 2: Define the Plan Structure

What sections does this work type need?

Work TypeEssential Sections
ChoreDescription, Files, Tasks, Validation
BugProblem, Solution, Reproduce, Root Cause, Tasks, Validation
FeatureUser Story, Implementation Plan, Testing, Acceptance
RefactorBefore/After, Migration, Rollback

Step 3: Write Instructions

Guide the agent's reasoning:

  • What should they focus on?
  • What reasoning depth is needed? ("think hard")
  • What common mistakes should they avoid?
  • What format requirements are strict?

Step 4: Specify Relevant Files

Limit scope to improve quality:

  • Core files for this work type
  • Test files to understand patterns
  • Config files if relevant
  • Avoid overly broad patterns

Step 5: Test with Examples

Validate your template:

  1. Run with simple input
  2. Check generated plan completeness
  3. Try edge cases
  4. Refine based on results

Quality Checklist

Before deploying a template:

  • Purpose clearly states what template does
  • Instructions include "THINK HARD" for reasoning
  • Relevant Files are specific, not too broad
  • Plan Format has all necessary sections
  • Validation Commands section is mandatory
  • Parameter uses $ARGUMENTS correctly
  • Output location specified (specs/*.md)

Common Patterns

Reasoning Activation

Use your reasoning model: THINK HARD about the plan
and the steps to accomplish this work.

File Output Pattern

Create a new plan in specs/*.md using the following naming:
specs/[worktype]-[descriptive-name].md

Validation Mandate

The Validation Commands section is REQUIRED. Every plan must
include commands that prove the work is complete.

Anti-Patterns to Avoid

Too Broad Relevant Files

Bad: **/* (everything) Good: src/auth/**, tests/auth/** (focused)

Missing Validation Section

Bad: No way to verify completion Good: Specific test and lint commands

Vague Instructions

Bad: "Make a good plan" Good: "Focus on error handling edge cases, include rollback steps"

No Output Location

Bad: Plan written somewhere undefined Good: specs/[worktype]-[name].md pattern

Related Memory Files

  • @template-engineering.md - Core concepts and examples
  • @meta-prompt-patterns.md - Prompt hierarchy
  • @plan-format-guide.md - Standard plan structures

Version History

  • v1.0.0 (2025-12-26): Initial release

Last Updated

Date: 2025-12-26 Model: claude-opus-4-5-20251101

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Antigravity

28.57%
按下载量换算36

trae

23.28%
按下载量换算29

windsurf

18.87%
按下载量换算24

Claude Code

14.24%
按下载量换算18

Codex

8.82%
按下载量换算11

Gemini CLI

4.06%
按下载量换算5

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。

来源信息

继续浏览同类 Skills