一键导入
setup
Bootstrap agent working system for a new project. Triggers on "setup agent system", "initialize claude", "bootstrap project".
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Bootstrap agent working system for a new project. Triggers on "setup agent system", "initialize claude", "bootstrap project".
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Create and manage AI agent sessions with multiple backends (SDK, Claude CLI, Codex, Cursor). Also supports multi-agent workflows with shared context, @mention coordination, and collaborative voting. Use for "start agent session", "create worker", "run agent", "multi-agent workflow", "agent collaboration", "test with tools", or when orchestrating AI conversations programmatically.
Discover, record, and execute E2E test cases using browser exploration. Use when exploring test scenarios, recording user flows, organizing test structure, or executing YAML-based tests.
Guide for authoring effective Agent Skills using principle-based approach (Progressive Disclosure, Respect Intelligence, Enable Discovery). Covers creating, improving, refactoring, and reviewing skills. Use for skill authoring, design questions, best practices, anti-patterns, or structure decisions.
Dives deep into project questions using layered investigation (docs → code → analysis) to provide evidence-based answers with file:line citations. Use when asking "how does X work", "what is Y", "where is Z", or investigating features, APIs, configuration, codebase structure, or technical decisions.
Guides technical decisions, architecture, and implementation. Use for tech choices, system design, API design, refactoring, or "how should I build this" questions.
Initialize frontend projects with opinionated modern toolchain - Bun (package manager), Oxfmt (formatter), Oxlint (linter), tsdown (npm bundler), tsgo (type checker). Use when creating new frontend/TypeScript projects, setting up project tooling, or mentions "init project", "new frontend", "setup tooling".
基于 SOC 职业分类
| name | setup |
| description | Bootstrap agent working system for a new project. Triggers on "setup agent system", "initialize claude", "bootstrap project". |
Bootstrap the agent working system for a new project.
Without this system, every agent starts from zero. Mistakes you make, successors will repeat. What you learn, successors must relearn.
With this system:
This isn't optional "best practice"—it's the infrastructure that enables agent teams to evolve.
Base it on lidessen/moniro/CLAUDE.md.
Keep these sections as-is (core working method):
FIRST/ALWAYS/LAST)Who You Are (entire section)Methodology (entire section)Remember (closing section)Replace these sections (project-specific):
Vision → describe this project's purposeStructure → describe this project's directory layoutRemove or adapt these sections (optional):
Skill Collaboration → keep if using skills, remove if notSkill Core Methods → keep if using skills, remove if notContributing → adapt to this project's contribution guidelinesmkdir -p .memory/{notes,decisions,todos}
| Directory | Purpose |
|---|---|
| notes/ | Learnings, reflections, discoveries |
| decisions/ | Important decisions and their rationale |
| todos/ | Tasks that span sessions |
Create .memory/notes/to-those-who-come-after.md.
Reference lidessen/moniro/.memory/notes/2026-01-31-to-those-who-come-after.md for structure, but write your own content:
The above is the required framework. On top of this, adapt based on project needs:
Add these to the appropriate sections in CLAUDE.md.
After setup, verify:
Who You Are, Methodology, and Remember sectionsFIRST/ALWAYS/LAST remindersSource: lidessen/moniro
For the origin and evolution of this system, see that repository's .memory/notes/ directory.