Claude Code Slash Commands · page 4

Understand the current state of the git repository

Creates a concise engineering implementation plan based on user requirements and saves it to specs directory

Creates a concise engineering implementation plan based on user requirements and saves it to specs directory

Load context for a new agent session by analyzing codebase structure, documentation and README

Load context for a new agent session by analyzing codebase structure and README

Answer questions about the project structure and documentation without coding

Manage, organize and ships your codebase.

Apply the Five Whys root cause analysis technique to investigate an issue

Create a branch, split changes into logical commits, and open a pull request

Run a multi-perspective PR review (product, dev, QA, security, DevOps, UX) and post it to GitHub

Development practices and TDD workflow to follow before starting a feature

LLM unit testing best practices checklist for testing internal logic, not API endpoints

Manage project todos in todos.md file

User Experience Designer & UI Specialist persona for design-focused tasks

Build a feature using Research > Plan > Implement phases

Diagnose pro-workflow setup and Claude Code configuration

Train a skill's SKILL.md by running a SkillOpt-flavored offline loop over accumulated learn-rule corrections

Commit all changes, push branch, create/update PR, and run local validation

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.

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.

Perform competitive analysis on companies or products

Fact-check claims or verify information

Research current market trends in a specific industry or domain

Start a focused research session on any topic

Summarize all current research findings

Say hello

Check running Claude Code or Codex sessions, find zombies, offer to clean up safely

Quick 10-second context health check with quality score and top issues

Create a detailed implementation plan using Codex 5.2 with high reasoning

Draft a professional email using the What-Why-How framework. Use when you need to compose emails to colleagues, stakeholders, or leadership.

Build a mental model of changes by splitting them into smaller logical chunks

Sync feature branch with the latest main branch.

Sync root README.md with current skills inventory from skills/ directory

Transform a raw tweet idea into an optimized viral post for X

Initialize the current project with Scientific Writer - a deep research and writing tool that combines AI-driven research with well-formatted written outputs.

Guided Apify Actor development with best practices and systematic workflow

Renamed → /portaljs-add-chart. This alias will be removed next minor release.

Renamed → /portaljs-add-dataset. This alias will be removed next minor release.

Renamed → /portaljs-add-map. This alias will be removed next minor release.

Renamed → /portaljs-add-resource. This alias will be removed next minor release.

Renamed → /portaljs-architect. This alias will be removed next minor release.

Renamed → /portaljs-check-data-quality. This alias will be removed next minor release.

Renamed → /portaljs-connect-ckan. This alias will be removed next minor release.

Renamed → /portaljs-define-schema. This alias will be removed next minor release.

Renamed → /portaljs-deploy. This alias will be removed next minor release.

Renamed → /portaljs-migrate. This alias will be removed next minor release.

Renamed → /portaljs-new-portal. This alias will be removed next minor release.

List pentest-ai agents relevant to a domain or tag (web, ad, cloud, mobile, recon, etc.).

Recommend the right pentest-ai agent and concrete next steps for a freeform task description.

Stage all files and create a commit.

Stage, commit and push all code in the current branch

Create a new agent skill

Create a pull request

Utilize tools of Model Context Protocol (MCP) servers

Postmortem analysis of cluster failures → OPTIMIZE PROMPTS to work for EVERY use case

启动 NanoClaw 智能体 (Agent) REPL — 一个由 claude CLI 驱动的持久化、会话感知 (session-aware) 的 AI 助手。

使用 Playwright 生成并运行端到端测试。创建测试旅程、运行测试、捕获截图/视频/追踪，并上传产物。

分析直觉（Instincts）并建议或生成进化的结构

增量修复 Go 构建错误、go vet 警告和 linter 问题。调用 go-build-resolver 智能体（Agent）进行最小化、外科手术式的修复。

针对地道模式、并发安全、错误处理和安全性的全面 Go 代码审查。调用 go-reviewer 智能体 (Agent)。

为 Go 强制执行测试驱动开发（TDD）工作流。先编写表格驱动测试（Table-Driven Tests），然后进行实现。使用 go test -cover 验证 80% 以上的覆盖率。

Export instincts from project/global scope to a file

从文件或 URL 导入直觉（Instincts）到项目/全局作用域

显示已学习的直觉（项目 + 全局）及其置信度

从会话中提取可复用的模式（Patterns），在保存前进行质量自评，并确定合适的保存位置（全局 vs 项目）。

重述需求、评估风险并制定分步实施计划。在修改任何代码之前，必须等待用户确认（CONFIRM）。

列出已知项目及其直觉（instinct）统计数据

将项目级直觉（Instincts）提升至全局作用域

针对 PEP 8 合规性、类型提示、安全性和 Pythonic 风格的全面 Python 代码审查。调用 python-reviewer 智能体（Agent）。

配置你偏好的包管理器 (npm/pnpm/yarn/bun)

分析本地 Git 历史以提取编码模式并生成 SKILL.md 文件。Skill Creator GitHub App 的本地版本。

强制执行测试驱动开发工作流。先搭建接口脚手架，首先生成测试，然后编写最少代码以通过测试。确保 80% 以上的覆盖率。

Add todo item to TO-DOS.md with context from conversation

Gather requirements through adaptive questioning before executing any task

Audit slash command file for YAML, arguments, dynamic context, tool restrictions, and content quality

Audit subagent configuration for role definition, prompt quality, tool selection, XML structure compliance, and effectiveness

List outstanding todos and select one to work on

Invoke create-hooks skill for expert guidance on Claude Code hook development

Create optimized prompts for Claude-to-Claude pipelines (research -> plan -> implement)

Create hierarchical project plans for solo agentic development (briefs, roadmaps, phase plans)

Create a new prompt that another Claude can execute

Create a new slash command following best practices and patterns

Create specialized Claude Code subagents with expert guidance

Apply expert debugging methodology to investigate a specific issue

Execute a PLAN.md file directly without loading planning skill context

Delegate one or more prompts to fresh sub-task contexts with parallel or sequential execution

Analyze the current conversation and create a handoff document for continuing this work in a fresh context

Prepare and execute an Android release (patch/minor/major)

Gather details and draft an actionable bug report for developers.

Create a git commit with concise, bullet-point commit message

Create a new plan document for tracking work.

Run E2E tests in a dev container (isolated environment)

Execute a plan document while keeping progress synchronized.

Investigate a problem and align on the right next step before implementing.

Investigate a Nimbalyst performance problem (freeze, lag, idle CPU, slow op, memory growth) with measured evidence before proposing a fix.

Prepare and execute an iOS release (patch/minor/major)

Create a visual UX mockup for a requested feature or screen.

Summarize my recent git commits in standup format