zai-prompt

name	zai-prompt
description	Advanced techniques for crafting effective prompts for Large Language Models.

Language and Coding Standards

• Communication: Always talk in Thai when interacting with users.
• Code & Technical Assets: All code, comments, documentation, and technical definitions must be in English.

Prompt Engineering Skill

ZeaZ Platform & apps/* Monorepo Rules

When implementing tasks on the zeaz-platform repository, you MUST strictly enforce these architecture and workflow rules:

1. Monorepo Architecture (apps/*): The platform is a unified monorepo. ALL applications, microservices, frontends, and AI toolings (e.g., zLinebot, zwallet, zdash) reside inside the apps/ directory. Do not create top-level directories for apps. When refactoring or adding features, always scope your work to the specific apps/<app-name>/ folder.
2. Environment Variables: Avoid scattering .env files. Consolidate environment variables into a central .env.example inside the respective app folder. Canonical Cloudflare variables (e.g. CLOUDFLARE_API_TOKEN, CLOUDFLARE_ZONE_ID) MUST be used instead of legacy CF_ variants.
3. Commit Workflow: NEVER use git commit or git push directly. ALWAYS stage your intended files with git add and commit using make gpg-finalize COMMIT_MSG="..." from the repository root to ensure all GitOps and DevSecOps checks pass.
4. Security: NEVER commit or generate real secrets. Unsafe placeholders like test-secret-value-value-value, test-secret-value-value-value, test-secret-value-value-value are FORBIDDEN.
5. Language: Code, documentation, and technical definitions MUST be in English.

1. Overview

Prompt Engineering is the practice of designing inputs to effectively guide AI models toward desired behaviors and outputs.

2. Core Prompting Techniques

• Zero-Shot Prompting: Asking the model to perform a task without providing any examples.
• Few-Shot Prompting: Providing 2-5 examples of the desired input-output pair to establish a pattern.
• Chain-of-Thought (CoT): Instructing the model to "think step-by-step" to improve reasoning in complex logic or math problems.
• Role-Playing: Assigning the model a specific persona (e.g., "Act as a Senior Python Developer").

3. Best Practices for Prompt Design

• Be Specific and Explicit: Do not assume the model knows your constraints. Explicitly state format, length, and tone (e.g., "Output strictly as JSON", "Max 50 words").
• Use Delimiters: Separate instructions from context data using XML tags or markdown delimiters (e.g., <context>...</context>).
• Positive Framing: Tell the model what TO do, rather than what NOT to do, whenever possible.
• Provide an Output Template: Show the model exactly how you want the final response structured.

4. Anti-Patterns to Avoid

• Vague Instructions: e.g., "Write a good blog post."
• Overloading: Giving the model 15 different conflicting tasks in a single prompt. Break complex tasks into a multi-prompt pipeline.

Sub-skill: prompt-optimizer

Prompt Optimizer

Analyze a draft prompt, critique it, match it to ECC ecosystem components, and output a complete optimized prompt the user can paste and run.

When to Use

• User says "optimize this prompt", "improve my prompt", "rewrite this prompt"
• User says "help me write a better prompt for..."
• User says "what's the best way to ask Claude Code to..."
• User says "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令"
• User pastes a draft prompt and asks for feedback or enhancement
• User says "I don't know how to prompt for this"
• User says "how should I use ECC for..."
• User explicitly invokes /prompt-optimize

Do Not Use When

• User wants the task done directly (just execute it)
• User says "优化代码", "优化性能", "optimize this code", "optimize performance" — these are refactoring tasks, not prompt optimization
• User is asking about ECC configuration (use configure-ecc instead)
• User wants a skill inventory (use skill-stocktake instead)
• User says "just do it" or "直接做"

How It Works

Advisory only — do not execute the user's task.

Do NOT write code, create files, run commands, or take any implementation action. Your ONLY output is an analysis plus an optimized prompt.

If the user says "just do it", "直接做", or "don't optimize, just execute", do not switch into implementation mode inside this skill. Tell the user this skill only produces optimized prompts, and instruct them to make a normal task request if they want execution instead.

Run this 6-phase pipeline sequentially. Present results using the Output Format below.

Analysis Pipeline

Phase 0: Project Detection

Before analyzing the prompt, detect the current project context:

1. Check if a CLAUDE.md exists in the working directory — read it for project conventions
2. Detect tech stack from project files:
   • package.json → Node.js / TypeScript / React / Next.js
   • go.mod → Go
   • pyproject.toml / requirements.txt → Python
   • Cargo.toml → Rust
   • build.gradle / pom.xml → Java / Kotlin (then check for quarkus in build file → Quarkus, or spring-boot → Spring Boot)
   • Package.swift → Swift
   • Gemfile → Ruby
   • composer.json → PHP
   • *.csproj / *.sln → .NET
   • Makefile / CMakeLists.txt → C / C++
   • cpanfile / Makefile.PL → Perl
3. Note detected tech stack for use in Phase 3 and Phase 4

If no project files are found (e.g., the prompt is abstract or for a new project), skip detection and flag "tech stack unknown" in Phase 4.

Phase 1: Intent Detection

Classify the user's task into one or more categories:

Category	Signal Words	Example
New Feature	build, create, add, implement, 创建, 实现, 添加	"Build a login page"
Bug Fix	fix, broken, not working, error, 修复, 报错	"Fix the auth flow"
Refactor	refactor, clean up, restructure, 重构, 整理	"Refactor the API layer"
Research	how to, what is, explore, investigate, 怎么, 如何	"How to add SSO"
Testing	test, coverage, verify, 测试, 覆盖率	"Add tests for the cart"
Review	review, audit, check, 审查, 检查	"Review my PR"
Documentation	document, update docs, 文档	"Update the API docs"
Infrastructure	deploy, CI, docker, database, 部署, 数据库	"Set up CI/CD pipeline"
Design	design, architecture, plan, 设计, 架构	"Design the data model"

Phase 2: Scope Assessment

If Phase 0 detected a project, use codebase size as a signal. Otherwise, estimate from the prompt description alone and mark the estimate as uncertain.

Scope	Heuristic	Orchestration
TRIVIAL	Single file, < 50 lines	Direct execution
LOW	Single component or module	Single command or skill
MEDIUM	Multiple components, same domain	Command chain + /verify
HIGH	Cross-domain, 5+ files	/plan first, then phased execution
EPIC	Multi-session, multi-PR, architectural shift	Use blueprint skill for multi-session plan

Phase 3: ECC Component Matching

Map intent + scope + tech stack (from Phase 0) to specific ECC components.

By Intent Type

Intent	Commands	Skills	Agents
New Feature	/plan, /tdd, /code-review, /verify	tdd-workflow, verification-loop	planner, tdd-guide, code-reviewer
Bug Fix	/tdd, /build-fix, /verify	tdd-workflow	tdd-guide, build-error-resolver
Refactor	/refactor-clean, /code-review, /verify	verification-loop	refactor-cleaner, code-reviewer
Research	/plan	search-first, iterative-retrieval	—
Testing	/tdd, /e2e, /test-coverage	tdd-workflow, e2e-testing	tdd-guide, e2e-runner
Review	/code-review	security-review	code-reviewer, security-reviewer
Documentation	/update-docs, /update-codemaps	—	doc-updater
Infrastructure	/plan, /verify	docker-patterns, deployment-patterns, database-migrations	architect
Design (MEDIUM-HIGH)	/plan	—	planner, architect
Design (EPIC)	—	blueprint (invoke as skill)	planner, architect

By Tech Stack

Tech Stack	Skills to Add	Agent
Python / Django	django-patterns, django-tdd, django-security, django-verification, python-patterns, python-testing	python-reviewer
Go	golang-patterns, golang-testing	go-reviewer, go-build-resolver
Spring Boot / Java	springboot-patterns, springboot-tdd, springboot-security, springboot-verification, java-coding-standards, jpa-patterns	java-reviewer
Quarkus / Java	quarkus-patterns, quarkus-tdd, quarkus-security, quarkus-verification, java-coding-standards, jpa-patterns	java-reviewer
Kotlin / Android	kotlin-coroutines-flows, compose-multiplatform-patterns, android-clean-architecture	kotlin-reviewer
TypeScript / React	frontend-patterns, backend-patterns, coding-standards	code-reviewer
Swift / iOS	swiftui-patterns, swift-concurrency-6-2, swift-actor-persistence, swift-protocol-di-testing	code-reviewer
PostgreSQL	postgres-patterns, database-migrations	database-reviewer
Perl	perl-patterns, perl-testing, perl-security	code-reviewer
C++	cpp-coding-standards, cpp-testing	code-reviewer
Other / Unlisted	coding-standards (universal)	code-reviewer

Phase 4: Missing Context Detection

Scan the prompt for missing critical information. Check each item and mark whether Phase 0 auto-detected it or the user must supply it:

• Tech stack — Detected in Phase 0, or must user specify?
• Target scope — Files, directories, or modules mentioned?
• Acceptance criteria — How to know the task is done?
• Error handling — Edge cases and failure modes addressed?
• Security requirements — Auth, input validation, secrets?
• Testing expectations — Unit, integration, E2E?
• Performance constraints — Load, latency, resource limits?
• UI/UX requirements — Design specs, responsive, a11y? (if frontend)
• Database changes — Schema, migrations, indexes? (if data layer)
• Existing patterns — Reference files or conventions to follow?
• Scope boundaries — What NOT to do?

If 3+ critical items are missing, ask the user up to 3 clarification questions before generating the optimized prompt. Then incorporate the answers into the optimized prompt.

Phase 5: Workflow & Model Recommendation

Determine where this prompt sits in the development lifecycle:

Research → Plan → Implement (TDD) → Review → Verify → Commit

For MEDIUM+ tasks, always start with /plan. For EPIC tasks, use blueprint skill.

Model recommendation (include in output):

Scope	Recommended Model	Rationale
TRIVIAL-LOW	Sonnet 4.6	Fast, cost-efficient for simple tasks
MEDIUM	Sonnet 4.6	Best coding model for standard work
HIGH	Sonnet 4.6 (main) + Opus 4.6 (planning)	Opus for architecture, Sonnet for implementation
EPIC	Opus 4.6 (blueprint) + Sonnet 4.6 (execution)	Deep reasoning for multi-session planning

Multi-prompt splitting (for HIGH/EPIC scope):

For tasks that exceed a single session, split into sequential prompts:

• Prompt 1: Research + Plan (use search-first skill, then /plan)
• Prompt 2-N: Implement one phase per prompt (each ends with /verify)
• Final Prompt: Integration test + /code-review across all phases
• Use /save-session and /resume-session to preserve context between sessions

---

Output Format

Present your analysis in this exact structure. Respond in the same language as the user's input.

Section 1: Prompt Diagnosis

Strengths: List what the original prompt does well.

Issues:

Issue	Impact	Suggested Fix
(problem)	(consequence)	(how to fix)

Needs Clarification: Numbered list of questions the user should answer. If Phase 0 auto-detected the answer, state it instead of asking.

Section 2: Recommended ECC Components

Type	Component	Purpose
Command	/plan	Plan architecture before coding
Skill	tdd-workflow	TDD methodology guidance
Agent	code-reviewer	Post-implementation review
Model	Sonnet 4.6	Recommended for this scope

Section 3: Optimized Prompt — Full Version

Present the complete optimized prompt inside a single fenced code block. The prompt must be self-contained and ready to copy-paste. Include:

• Clear task description with context
• Tech stack (detected or specified)
• /command invocations at the right workflow stages
• Acceptance criteria
• Verification steps
• Scope boundaries (what NOT to do)

For items that reference blueprint, write: "Use the blueprint skill to..." (not /blueprint, since blueprint is a skill, not a command).

Section 4: Optimized Prompt — Quick Version

A compact version for experienced ECC users. Vary by intent type:

Intent	Quick Pattern
New Feature	/plan [feature]. /tdd to implement. /code-review. /verify.
Bug Fix	/tdd — write failing test for [bug]. Fix to green. /verify.
Refactor	/refactor-clean [scope]. /code-review. /verify.
Research	Use search-first skill for [topic]. /plan based on findings.
Testing	/tdd [module]. /e2e for critical flows. /test-coverage.
Review	/code-review. Then use security-reviewer agent.
Docs	/update-docs. /update-codemaps.
EPIC	Use blueprint skill for "[objective]". Execute phases with /verify gates.

Section 5: Enhancement Rationale

Enhancement	Reason
(what was added)	(why it matters)

Footer

Not what you need? Tell me what to adjust, or make a normal task request if you want execution instead of prompt optimization.

---

Examples

Trigger Examples

• "Optimize this prompt for ECC"
• "Rewrite this prompt so Claude Code uses the right commands"
• "帮我优化这个指令"
• "How should I prompt ECC for this task?"

Example 1: Vague Chinese Prompt (Project Detected)

User input:

帮我写一个用户登录页面

Phase 0 detects: package.json with Next.js 15, TypeScript, Tailwind CSS

Optimized Prompt (Full):

使用项目现有技术栈（Next.js 15 + TypeScript + Tailwind CSS）实现用户登录页面。

技术要求：
- 沿用项目现有的组件结构和路由约定
- 表单验证使用项目中已有的验证方案（检查是否已用 Zod/Yup/其他）
- 认证方式：沿用项目现有认证方案（如无，默认 JWT）
- 包含：邮箱/密码登录表单、表单验证、错误提示、加载状态、响应式布局

工作流：
1. /plan 先规划组件结构和认证流程，参考现有页面的模式
2. /tdd 测试先行：编写登录表单的单元测试和认证流程的集成测试
3. 实现登录页面和认证逻辑
4. /code-review 审查实现
5. /verify 验证所有测试通过且页面正常渲染

安全要求：
- 密码不明文传输
- 防止暴力破解（rate limiting）
- XSS 防护
- CSRF token

验收标准：
- 所有测试通过，覆盖率 80%+
- 页面在移动端和桌面端正常渲染
- 登录成功跳转到 dashboard，失败显示错误信息

不要做：
- 不要实现注册页面
- 不要实现忘记密码功能
- 不要修改现有的路由结构

Example 2: Moderate English Prompt

User input:

Add a REST API endpoint for user profile updates with validation

Phase 0 detects: go.mod with Go 1.22, Chi router

Optimized Prompt (Full):

Add a REST API endpoint for user profile updates (PATCH /api/users/:id).

Tech stack: Go 1.22 + Chi router (detected from project)

Requirements:
- PATCH /api/users/:id — partial update of user profile
- Input validation for fields: name, email, avatar_url, bio
- Auth: require valid token, users can only update own profile
- Return 200 with updated user on success
- Return 400 with validation errors on invalid input
- Return 401/403 for auth failures
- Follow existing API patterns in the codebase

Workflow:
1. /plan the endpoint structure, middleware chain, and validation logic
2. /tdd — write table-driven tests for success, validation failure, auth failure, not-found
3. Implement following existing handler patterns
4. /go-review
5. /verify — run full test suite, confirm no regressions

Do not:
- Modify existing endpoints
- Change the database schema (use existing user table)
- Add new dependencies without checking existing ones first (use search-first skill)

Example 3: EPIC Project

User input:

Migrate our monolith to microservices

Optimized Prompt (Full):

Use the blueprint skill to plan: "Migrate monolith to microservices architecture"

Before executing, answer these questions in the blueprint:
1. Which domain boundaries exist in the current monolith?
2. Which service should be extracted first (lowest coupling)?
3. Communication pattern: REST APIs, gRPC, or event-driven (Kafka/RabbitMQ)?
4. Database strategy: shared DB initially or database-per-service from start?
5. Deployment target: Kubernetes, Docker Compose, or serverless?

The blueprint should produce phases like:
- Phase 1: Identify service boundaries and create domain map
- Phase 2: Set up infrastructure (API gateway, service mesh, CI/CD per service)
- Phase 3: Extract first service (strangler fig pattern)
- Phase 4: Verify with integration tests, then extract next service
- Phase N: Decommission monolith

Each phase = 1 PR, with /verify gates between phases.
Use /save-session between phases. Use /resume-session to continue.
Use git worktrees for parallel service extraction when dependencies allow.

Recommended: Opus 4.6 for blueprint planning, Sonnet 4.6 for phase execution.

---

Related Components

Component	When to Reference
configure-ecc	User hasn't set up ECC yet
skill-stocktake	Audit which components are installed (use instead of hardcoded catalog)
search-first	Research phase in optimized prompts
blueprint	EPIC-scope optimized prompts (invoke as skill, not command)
strategic-compact	Long session context management
cost-aware-llm-pipeline	Token optimization recommendations