Claude Code Slash Commands · page 6

Implement SPEC requirements using DDD/TDD methodology

Synchronize documentation, codemaps, and create pull request

(dev-only) devkit dev-maintainer harness — consolidates the three numeric maintainer commands (CC upstream tracker / GitHub issue-PR workflow / production release) into one /harness:devkit entry. NOT distributed to user projects.

(dev-only) github maintainer harness — GitHub issue-fix and PR-review via gh CLI. NOT distributed to user projects.

(dev-only) release-update maintainer harness — Claude Code upstream change tracker (release-notes version-delta sweep + docs sync). NOT distributed to user projects.

(dev-only) release maintainer harness — MoAI-ADK production release (Enhanced GitHub Flow, scripts/release.sh + GoReleaser). NOT distributed to user projects.

(user-owned) oss-docs harness — README 4-locale + docs-site publishing for the moai-adk-go OSS project (adk.mo.ai.kr, Vercel auto-deploy).

Register a completion condition and arm the autonomous continuation loop

Backlog queue for Kanban Mode — add, list, or pick the next card

Deprecated - use the aegis:brainstorming skill instead

Deprecated - use the aegis:executing-plans skill instead

Deprecated - use the aegis:writing-plans skill instead

Implement tasks from an OpenSpec change (Experimental)

Archive a completed change in the experimental workflow

Enter explore mode - think through ideas, investigate problems, clarify requirements

Propose a new change - create it and generate all artifacts in one step

Start a Bernstein orchestration run with a goal

Show current Bernstein orchestration status

Gracefully stop a running Bernstein orchestration

Use the Agentlas browser hardpoint for browser-required work.

Prepare explicitly named Agentlas Hub or Cloud agents.

Connect Agentlas agents or teams to Telegram.

Staff a task only from public Agentlas Hub agents.

Staff a task only from Agentlas agents registered on this machine.

Turn the persistent Agentlas One personal agent on or off, or rename it.

Search Agentlas Cloud and Hub agent candidates without invoking.

Agentlas commands — one entry point for network, build, storm, call, and the rest.

Sign this machine into Agentlas (opens the browser sign-in window).

Set or show which model runs the orchestrator and which runs the workers.

Update the installed Agentlas runtime and every host adapter on this machine.

Use the Agentlas browser hardpoint for browser-required work.

Build, repair, or package Agentlas agents and teams with Hephaestus.

Prepare explicitly named Agentlas Hub or Cloud agents.

Staff a task only from the signed-in owner's Agent Cloud agents.

Connect Agentlas agents or teams to Telegram.

Build an Agentlas automation by describing it, list saved ones, or request a run.

Staff a task only from public Agentlas Hub agents.

Staff a task only from Agentlas agents registered on this machine.

Sign this machine into Agentlas (opens the browser sign-in window).

Staff a task from registered Local, owner Cloud, and public Hub agents.

Set or show which model runs the orchestrator and which runs the workers.

Search Agentlas Cloud and Hub agent candidates without invoking.

Run a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion.

Update the installed Agentlas runtime and every host adapter on this machine.

Publish an Agentlas package to Agent Cloud or the public Hub.

Quick git commit with auto-generated or specified message

Explain code in simple, beginner-friendly terms

Show recent git history with summary

Show git status with helpful context

Review code for quality, bugs, and improvements

Add a TODO comment to code

Deep analysis of code against project standards

Create a pull request with auto-detected context

Deploy with safety checks and automatic testing

Interrogate a spec with Loki's Devil's-Advocate grill before building, and summarize the hardest questions it surfaces.

Check whether the spec has drifted from its lock using Loki's living-spec drift detection, and summarize the report.

Run Loki's deterministic PR verification on the current change and summarize the evidence verdict.

检查 ToolSearch（WebSearch）是否可用

问题修复（fix 快速修复 / debug 系统化调试）

新功能全流程（需求审问 → 设计 → 实现）

系统优化扫描（full/ux/perf/code 四种模式）

为新项目初始化 Claude Code 配置

扫描项目生成配置（CLAUDE.md/restart.sh/ignore/Docker）

需求分析（doc 文档框架 / interrogate 极刑审问）

代码审查（full/quick/security 三种模式），支持指定提交

一键安装 cc-use-exp 配置体系

卸载 cc-use-exp 配置体系（仅 Plugin Marketplace 安装）

更新 cc-use-exp 配置体系到最新版本

显示当前加载的配置状态

从代码或设计图提取样式变量

Executa UMA sessão do gov-loop do DeskcommCRM (uma feature de governança, depois morre)

Tria um PR de contribuidor de ponta a ponta — acolhe, mede, reproduz, corrige, responde. Para no merge, que é do mantenedor.

Walk the user through installing the optional composio skill and turning on screen memory

List all /openloomi:* commands

Install, uninstall, or inspect OpenLoomi's Claude Code hooks

Show OpenLoomi Loop dashboard state (pending decisions, connectors, last tick) and force-refresh connector health — thin doorway into the openloomi-loop sub-skill

Search OpenLoomi memory (files + knowledge base + insights) — thin doorway into the openloomi-memory sub-skill

Set the OpenLoomi Pet to a specific state (theme-agnostic; fox sprite set active by default)

Run OpenLoomi one-time setup — auto-chains install → launch → guest login → ready in one call

Print stable JSON status for the OpenLoomi ↔ Claude Code integration

Walk a brand-new OpenLoomi user through the entire pipeline in one guided session — thin doorway into the openloomi-tour sub-skill

Show today's LLM usage summary as recorded by OpenLoomi

Run every objective gate this project can prove and report the real N/N. Use before claiming any screen or component is done.

Scaffold a new design-product project that matches the recommended Claude Code layout (the reference structure). Use when starting a fresh product/app that will be built with this design system.

Pre-release gate — run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.

Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.

Configure claude-delegator with Codex (GPT) or Gemini MCP servers

Uninstall claude-delegator (remove MCP config and rules)

Run when user calls /commit or asks to generate a commit message. Analyzes staged changes and writes a structured commit message.

Run when user calls /review. Analyzes local changes and runs a comprehensive code review using the agent-reviewer prompt.

Run when user calls /test-tdd. Scans modified files, locates their corresponding unit/integration test suites, and runs them.

Set up fablize always-on (inject the operating block into CLAUDE.md).

Route, create, improve, or inspect reusable AI skills with SkillForge

Trigger the Commit & Branch Guard workflow on demand.

Stage working tree changes and create a Conventional Commit (no push).

Stage, commit, and push the current branch following git governance rules.

Create a pull request from the current branch.

Run the local review gate before pushing.

Run the security scan gate before pushing.

Run the full review gate locally and trigger CI visibility.