ai-architect-lite
Lightweight playbook distilled from AI Architecture to keep dual-engine memory (.ai_context) and manifest dispatcher with minimal overhead; use when bootstrapping or porting the pattern into Claude Skills format.
Best use case
ai-architect-lite is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Lightweight playbook distilled from AI Architecture to keep dual-engine memory (.ai_context) and manifest dispatcher with minimal overhead; use when bootstrapping or porting the pattern into Claude Skills format.
Teams using ai-architect-lite should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ai-architect-lite/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ai-architect-lite Compares
| Feature / Agent | ai-architect-lite | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Lightweight playbook distilled from AI Architecture to keep dual-engine memory (.ai_context) and manifest dispatcher with minimal overhead; use when bootstrapping or porting the pattern into Claude Skills format.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# AI Architect Lite > 精简版「AI Architecture」:保留 `.ai_context` 记忆协议与 manifest 驱动调度,服务轻量项目或快速移植场景。 ## 适用场景 - 新建/迁移仓库,希望用最小开销引入 `.ai_context` + slash-first 调度。 - 需要统一开发日志格式,但不启用完整 Pro 协议。 - 想把 AI Architect 的初衷以 Claude Skill 形式交付,供其他会话直接加载。 ## 快速上手 1. 解析路径:`PROJECT_ROOT` = 当前仓库;`TOOLKIT_PATH` = 本技能所在目录(用于引用资源)。 2. 检查 `PROJECT_ROOT/.ai_context/03_ACTIVE_TASK.md`;缺失则按 `references/lite-protocol.md` 模板创建或运行 `python skills/project-init/entrypoint.py`。 3. 阅读 `03_ACTIVE_TASK.md` 获取 Current Mission;若存在 `01/02` 则作为补充规则加载,不强制解析全部细节。 4. 查看 `.ai-manifest.json`:优先使用 `commands` 中的 slash 触发;若无 `cognitive_skills` 配置,则保持纯命令模式。 - 新手护栏:若拿不准流程,先快速浏览 `references/superpowers-lite.md`,按其“迷你 TDD”“快速执行模板”走一遍。 - 仅本技能加载时的默认动作:先输出友好欢迎语,告诉用户你已启用 AI Architect Lite,并给出 3 个可选下一步(如:① 生成迷你计划 `python scripts/plan_helper.py ...`;② 填写/创建 `.ai_context/03_ACTIVE_TASK.md`;③ 用 `scripts/append_log.py` 记录第一次动作)。 ## 工作流程(Loop) - **Dispatcher 次序**:Slash > Intent(可选)> 普通对话;未命中技能时按当前任务回答。 - **迷你流程(面向新手)**:用 3 步走完——① 写目标/约束/<=5 步计划(可直接在回答里列出,或运行 `python scripts/plan_helper.py --goal \"...\" --steps \"...\" --validation \"...\" --out -` 获取模板);② 先写“会失败”的验证点(命令或检查点),再动手;③ 完成后按验证点复跑并记录结果。 - **日志写入**:优先运行 `python scripts/append_log.py --note "..." --action "..." --changes "..." --outcome "..." --next "..."`(随技能提供的最小脚本,默认在项目根执行并自动创建 `.ai_context/03_ACTIVE_TASK.md`)。若项目已有通用 `skills/memory-sync/entrypoint.py`,可直接复用;两者都不可用时在 `03_ACTIVE_TASK.md` 手动追加四段式记录。 - **范围与安全**:仅操作 `PROJECT_ROOT`;执行前用中文说明修改/命令目的与影响,避免写入密钥。 - **上下文收敛**:长文档/规范放入 `references/`,按需加载;核心指令保持在本文件。 ### 默认问候模板(仅单独加载本技能时使用) ``` 嗨,我是 AI Architect Lite(目前只加载了我)。为了让你轻松上手,我们可以从这三步选一: 1) 想清楚要做什么:用“迷你计划”列出目标、3 步以内的行动、以及如何确认完成(好处:先定方向,少走弯路)。 2) 准备一本“任务笔记”:如果没有 .ai_context/03_ACTIVE_TASK.md,就按 references/lite-protocol.md 的格式建一个,记录当前任务和进展(好处:状态清晰,随时可查)。 3) 留下一条“开工日志”:用 scripts/append_log.py 记下你做的第一步和结果(好处:有迹可循,方便回顾或求助)。 告诉我你的目标,或者直接挑一条开始,我会陪你一步步完成。 ``` ## 资源使用 - `references/lite-protocol.md`:`.ai_context` 最小规范、开发日志模板、slash-first 调度要点。 - `references/superpowers-lite.md`:超能力精简卡,涵盖迷你 TDD、系统化调试和透明协作的最小做法。 - `scripts/append_log.py`:为新手准备的最小日志脚本,自动建文件并按模板追加;可作为示例扩展。 - `scripts/plan_helper.py`:生成目标/约束/步骤/验证的极简计划模板,默认输出到终端,避免额外文件。 - `assets/`:保留占位,用于未来模板/示例;当前无需加载到上下文。 ## 示例日志片段 ```markdown ### [2025-11-21 10:00] Action: 初始化 lite 协议 - Changes: 创建 .ai_context/03_ACTIVE_TASK.md;检查 .ai-manifest.json - Outcome: 完成;未运行测试 - Next: 按当前任务执行并在每步后同步日志 ```
Related Skills
analyze-project-architecture
LLM-based architectural analysis that transforms raw project data into meaningful structure
analyze-architecture
Comprehensive brownfield architecture analysis for existing codebases. Discovers structure, identifies patterns, assesses quality, calculates production readiness, and provides actionable recommendations. Use when analyzing existing codebases to understand architecture, assess quality, or prepare for modernization.
aidb-architecture
Comprehensive architectural reference for AIDB core and MCP integration. Covers 6-layer architecture (MCP, Service, Session, Adapter, DAP Client, Protocol), component organization, data flow patterns, and design decisions. Use when explaining overall system design or understanding how layers interact.
ai-ad-doc-architect
No description provided.
agentic_architecture
Enforces high-level architectural thinking, separation of concerns, and scalability checks before coding.
agentic-jumpstart-architecture
Architecture guidelines for Jarvy CLI - codebase structure, tool implementation patterns, registry system, platform-specific code organization, and module conventions.
agent-java-architect
Senior Java architect specializing in enterprise-grade applications, Spring ecosystem, and cloud-native development. Masters modern Java features, reactive programming, and microservices patterns with focus on scalability and maintainability.
agent-architect
Claude Code architecture advisor. Classifies knowledge and delegates to appropriate skills. Use when deciding where to put new knowledge or restructuring components.
agent-angular-architect
Expert Angular architect mastering Angular 15+ with enterprise patterns. Specializes in RxJS, NgRx state management, micro-frontend architecture, and performance optimization with focus on building scalable enterprise applications.
aegis-architect
Enhanced architecture guidance for voice-first Brazilian fintech applications. Use when designing voice interfaces, implementing PIX/Boletos, optimizing financial systems, or making technology stack decisions for Brazilian market applications. Integrates with docs/ content, MCP tools for Brazilian market research, enhanced validation scripts, and comprehensive Brazilian compliance patterns.
Advanced Clean Hexagonal Architecture
Apply Clean Architecture and Hexagonal (Ports & Adapters) patterns for domain isolation and testability. Use when designing system boundaries, creating ports/adapters, or structuring domain-driven applications.
adr-graph-easy-architect
ASCII architecture diagrams for ADRs via graph-easy. TRIGGERS - ADR diagram, architecture diagram, ASCII diagram.