Use when starting any conversation - establishes how arkhe skills bootstrap on Claude Code, Antigravity CLI (agy) / Gemini CLI, and Codex CLI, and maps Claude-only tools (AskUserQuestion, TaskCreate, EnterPlanMode, the Skill tool, the Agent tool) to their cross-platform equivalents
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치 방법 보기설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
arkhe plugins ship the same SKILL.md files across CLI harnesses. This bootstrap establishes how to access skills and how to translate platform tool names into equivalent operations on Claude Code, Antigravity CLI (agy), Gemini CLI, and Codex CLI.
Skill tool. When invoked, the skill content is loaded and presented to follow directly.agy): Skill metadata (name + description) is auto-loaded into the system prompt at session start. When triggers fire, use view_file to load skills/<skill-name>/SKILL.md from the plugin directory, then follow its instructions.read_file to load skills/<skill-name>/SKILL.md.AGENTS.md at install time. Follow the skill body directly when a trigger phrase fires.arkhe SKILL.md files reference core agent primitives. On each platform, substitute the equivalent operation from this table.
| Primitive / Claude tool | Antigravity CLI (agy) equivalent | Gemini CLI (Legacy) equivalent | Codex CLI equivalent |
|---|---|---|---|
AskUserQuestion | ask_question (native interactive modal with chip UI options) | Ask a plain-text question with numbered choices and await reply. | Plain-text question with numbered choices. |
TaskCreate / TaskUpdate | manage_task or inline TODO list rendered on each turn | Inline TODO list rendered on each turn | Inline TODO list rendered on each turn |
EnterPlanMode / ExitPlanMode | Native --mode plan / accept-edits mode | Announce plan mode and gate writes on approval | Announce plan mode and gate writes on approval |
Skill tool (Skill) | view_file on skills/<name>/SKILL.md | read_file on skills/<name>/SKILL.md | Skill content inlined in AGENTS.md |
Agent tool (subagent_type) | invoke_subagent / define_subagent (native background/concurrent subagent execution) | Inline agent prompt into current session | Inline agent prompt into current session |
Commands ship from the same plugins/<plugin>/commands/<name>.md source on every platform, but the slash-command syntax differs:
| Platform | Form | Example |
|---|---|---|
| Claude Code | /<plugin>:<command> (plugin-namespaced) | /core:think |
Antigravity CLI (agy) / Gemini CLI | /<command> (or agy plugin commands) | /think |
| Codex CLI | Trigger phrase in chat (no slash) | "think through whether to use Postgres or Redis" |
When this skill or other arkhe docs refer to core:think, core:debug, etc., resolve them through this table — same command, platform-specific invocation.
Six arkhe commands dispatch subagents on Claude Code and Antigravity CLI (agy). On legacy Gemini and Codex CLI, they run inline with the agent's prompt collapsed into the command body.
The affected commands:
core:debug (with --deep)core:thinkcore:researchcore:double-check (with --deep)spring-boot:spring-reviewspring-boot:verify-upgradeIf CLAUDE.md, GEMINI.md, or AGENTS.md says "do not use TDD" and a skill says "always use TDD," follow the user's instructions. The user is in control.
plugins/<plugin>/skills/<skill>/SKILL.md.claude-plugin/marketplace.jsonplugins/<plugin>/plugin.json or .gemini-extensions/<plugin>/plugin.json (skills directory is a symlink to the canonical source).codex-marketplace/<plugin>/AGENTS.md (skill index synthesized at build time; full content via symlinked skills/)Skill bodies are not duplicated across platforms. One file, cross-platform support.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Create, review, and manage Architecture Decision Records (ADRs) with auto-numbering, template detection, quality review, and index maintenance. Use when user mentions "ADR", "architecture decision", "document this decision", "create ADR", "review ADR", editing ADR files (docs/adr/, doc/adr/, .adr/), or discussing architectural choices and tradeoffs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Analyze system architecture, module structure, API contracts, data models, and code patterns. Use when designing systems, reviewing module boundaries, evaluating API designs, analyzing data models, checking pattern conformance, tracing decisions, or reviewing frontend architecture. Triggers: "architecture", "module design", "API design", "data model", "boundaries", "patterns", "decisions", "frontend architecture".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. Use when user says "create a Stitch prompt", "optimize this for Stitch", "convert this spec to a Stitch prompt", "write a UI prompt", or mentions Google Stitch prompt authoring. Follows Stitch best practices with short, directive prompts focused on screens, structure, and visual hierarchy.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wraps HTML fragments in a frame template, broadcasts live-reload over WebSocket, and captures browser-side click events to a JSONL file. Use when an agent needs to show HTML to the user in a browser and react to clicks — mockups, design exploration, gallery browsing, multi-select choices, prototype iteration. Triggered by "live preview", "browser companion", "preview server", "browser mockup", "show in browser", "arkhe-preview", or any skill that wants to write HTML fragments and have the user see them reload in real time.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Deletes merged git branches (local and remote) and flags stale unmerged branches for manual review. Use when user mentions "cleanup branches", "delete merged branches", "prune old branches", "remove stale branches", "branch cleanup", or runs /cleanup-branches command.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Interactive Claude Code environment setup wizard. Detects existing configuration, guides through best-practice setup for Global CLAUDE.md, project scaffolding, MCP servers, hooks, custom agents, keybindings, and settings. Use when user runs /devtools:code-env-setup, mentions "setup claude code", "configure claude", "claude code setup", "environment setup", or "initialize claude code".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.