Test Prompt Skill
技能 已验证 活跃Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing
To apply TDD principles to prompt engineering, ensuring prompts are robust, reliable, and produce desired agent behavior through systematic testing and refinement.
功能
- Applies RED-GREEN-REFACTOR cycle to prompt engineering
- Uses isolated subagents for baseline testing
- Provides structured guidance for prompt optimization
- Supports testing of various prompt types (commands, hooks, skills)
使用场景
- Testing new prompts before deploying them to production
- Verifying prompt changes do not introduce regressions
- Comparing different prompt variations for optimal performance
- Ensuring prompt clarity and consistency for agent instructions
非目标
- Writing the initial prompt from scratch without prior testing
- Testing prompts within an existing conversation history
- Directly modifying agent behavior outside of prompt updates
工作流
- Design test scenarios for the prompt type.
- Launch subagent WITHOUT the prompt to observe baseline behavior (RED Phase).
- Document agent failures verbatim.
- Write a minimal prompt addressing specific baseline failures (GREEN Phase).
- Test with the prompt using subagent and verify improvement.
- Optimize the prompt while keeping tests passing (REFACTOR Phase).
- Re-verify with fresh subagents after refactoring.
实践
- Prompt Engineering
- Test-Driven Development
- Agent Workflow Design
先决条件
- Understanding of TDD: RED-GREEN-REFACTOR cycle
- Familiarity with prompt-engineering skill
Trust
- info:Issues AttentionThere are 6 open issues and 8 closed issues in the last 90 days, indicating active but potentially slower-than-ideal maintainer engagement.
安装
请先添加 Marketplace
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install customaize-agent@context-engineering-kit质量评分
已验证类似扩展
Using Superpowers
99在开始任何对话时使用 — 确定如何查找和使用技能，要求在任何响应（包括澄清问题）之前调用 Skill Tool
Cli Creator
100Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.
Context Mode Ops
100使用并行子代理军队管理 context-mode GitHub 问题、PR、发布和营销。为每个任务编排 10-20 个动态代理。在分类问题、审查 PR、发布版本、撰写 LinkedIn 帖子、宣布发布、修复错误、合并贡献、验证 ENV 变量、测试适配器或同步分支时使用。
Fixflow
100使用严格的交付工作流执行编码任务：构建完整计划、分步实现、持续运行测试，并默认在每一步 (`per_step`) 后提交。当用户要求行为驱动交付或需求不明确时，支持显式提交策略覆盖 (`final_only`, `milestone`) 和可选的 BDD（给定/当/则）。
Kotlin Mcp Server Generator
100Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official io.modelcontextprotocol:kotlin-sdk library.
Spec to Repo
100Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I have requirements and need a codebase', or provides a natural-language project specification and expects a complete, runnable repository. Stack-agnostic: Next.js, FastAPI, Rails, Go, Rust, Flutter, and more.