Slash Commands de Claude Code · página 6

Strict code review mode with high standards. Thoroughly examines code for bugs, security issues, performance problems, and best practice violations.

Runs project tests intelligently. Identifies affected tests from changes and runs them first, then full suite.

Document session learnings to CLAUDE.md and AGENTS.md. Use after completing significant tasks, debugging sessions, or discovering project patterns.

Security-focused code scan. Checks for hardcoded secrets, vulnerable dependencies, and common security issues.

Summarize recent changes for standup, PR, or documentation

Sync current branch with main/master (fetch, rebase or merge)

Interactive tutorial for learning the plugin. Walks through agents, skills, hooks, and commands with hands-on examples.

Validates project build process. Run after changes to ensure the project compiles/transpiles correctly.

Comprehensive verification after code changes. Uses Boris Cherny's multi-subagent adversarial approach.

Manually activate NoPUA clarity mode when stuck — identify the failure pattern and work through stop → observe → transform → act → transcend, driven by wisdom rather than fear.

行き詰まったとき NoPUA 清明モードを手動起動——失敗パターンを識別し、恐怖ではなく知恵で止→観→転→行→悟へ導く。

Deprecated - use the aegis:brainstorming skill instead

Deprecated - use the aegis:executing-plans skill instead

Deprecated - use the aegis:writing-plans skill instead

Code review the current proposed code change

Resolve a merge conflict

Code review for pull request $1

Check work for adherance with architecture and run checks

Claude Code upstream change tracker -> moai-adk update plan + docs sync workflow (dev-only). Tracks new CC release notes, classifies changes by impact tier, cross-references official docs, generates update plan at .moai/research/ or .moai/specs/, and synchronizes docs-site 4-locale + README. NOT distributed to user projects.

GitHub Workflow - Manage issues and review PRs with Agent Teams (dev-only). NOT distributed to user projects.

MoAI-ADK production release via Enhanced GitHub Flow (CLAUDE.local.md §18). Creates release/vX.Y.Z branch, version bump, CHANGELOG (bilingual), PR to main, merge commit (NOT squash), then scripts/release.sh for tag + GoReleaser. Hotfix support via --hotfix flag. All git operations delegated to manager-git. Quality failures escalate to expert-debug. NOT distributed to user projects (dev-only).

Run the 7-phase /moai brain ideation workflow to convert ideas into validated proposals

Identify and safely remove dead code with test verification

Scan codebase and generate architecture documentation in codemaps/

Analyze test coverage, identify gaps, and generate missing tests

Hybrid design workflow — Claude Design import (path A) or code-based brand design (path B)

(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.

Create and run E2E tests across web, mobile, and desktop with auto-detection and CLI-first toolchains

Collect feedback and create GitHub issue (bug report, feature request)

Auto-detect and fix LSP errors, linting issues, and type errors

Run lint+format+type-check+test in parallel (pre-commit quality gate)

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

Register a completion condition and arm the autonomous continuation loop

Manage harness learning subsystem (status/apply/rollback/disable) OR create a harness via natural-language analysis (Context-First Discovery + name derivation + approval gate)

Iteratively fix issues until all resolved or max iterations reached

Scan codebase and add @MX code-level annotations for AI context

(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).

Create SPEC document with EARS format requirements and acceptance criteria

Generate project documentation (product.md, structure.md, tech.md, codemaps/)

(dev-only) release maintainer harness — MoAI-ADK production release (Enhanced GitHub Flow, scripts/release.sh + GoReleaser). 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.

Code review with security and @MX tag compliance check

Implement SPEC requirements using DDD/TDD methodology

Synchronize documentation, codemaps, and create pull request

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

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

Deep analysis of code against project standards

Quick git commit with auto-generated or specified message

Explain code in simple, beginner-friendly terms

Show recent git history with summary

Create a pull request with auto-detected context

Review code for quality, bugs, and improvements

Deploy with safety checks and automatic testing

Show git status with helpful context

Add a TODO comment to code

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

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 an accessibility audit on the current project for WCAG compliance.

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

Reverse-engineer a Product Requirements Document from existing code.

Build a competitive analysis matrix comparing products or tools.

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

Assess financial health of a SaaS business using key metrics.

Apply a focused, minimal-change bugfix with minimal blast radius.

Create or review OKRs (Objectives and Key Results).

Activate a cross-domain persona for the current session.

Design or review a CI/CD pipeline for the current project.

Audit installed plugins, extensions, and dependencies for security and health.

Create a pull request from the current branch.

Create a Product Requirements Document from scratch.

Assess overall project health across code quality, tests, docs, and activity.

Run a sprint retrospective with data-driven insights from git history.

Run the local review gate before pushing.