Claude Code Slash Commands · page 4

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate

Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>

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

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

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

Say hello

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

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.

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

Stage all files and create a commit.

Stage, commit and push all code in the current branch

Create a pull request

Create a new agent skill

Utilize tools of Model Context Protocol (MCP) servers

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

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.

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

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。

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

Apply labels to GitHub issues

AI DevKit · Compare implementation with design and requirements docs to ensure alignment.

AI DevKit · Pre-push code review against design docs.

AI DevKit · Execute a feature plan task by task.

AI DevKit · Scaffold feature documentation from requirements through planning.

AI DevKit · Store reusable guidance in the knowledge memory service.

AI DevKit · Review feature design for completeness.

AI DevKit · Review feature requirements for completeness.

AI DevKit · Update planning docs to reflect implementation progress.

AI DevKit · Add tests for a new feature.

Add tests for recently changed files or specified code

System design and architecture planning mode. Focuses on high-level design, trade-offs, and technical decisions before implementation.

Explore the repository with 10 parallel subagents to create comprehensive documentation. Creates CODEBASE.md with full architecture analysis.

Simplifies code after implementation. Reviews recent changes and suggests/applies simplifications while preserving behavior.

Commit staged changes, push to remote, and create a pull request

Create a conventional commit with auto-generated message

Safe, one-at-a-time dependency upgrades with verification after each. Detects package manager automatically.

Runs linting and code quality checks. Catches style issues, potential bugs, and enforces project standards.

Auto-fix all linting and formatting issues

Educational mode that explains concepts, teaches patterns, and guides learning. Ideal when learning a new codebase, technology, or programming concept.

View agent performance metrics and session history. Shows usage patterns, files changed, and session summaries.

Multi-perspective analysis using parallel subagents. Analyzes code from architecture, security, performance, and testing viewpoints simultaneously.

Run parallel code review across multiple directories or files. Uses N subagents simultaneously for faster analysis.

Create and maintain a structured PLAN.md for persistent task tracking. Supports phases, dependencies, and progress tracking.

Quickly fix lint errors, type errors, or simple bugs

Fast-paced development mode for quick iterations. Minimal ceremony, maximum speed. Best for prototypes, MVPs, and time-sensitive tasks.

Systematic, safety-first refactoring with verification at each step. Never refactors and adds features simultaneously.

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。

Code review the current proposed code change

Code review for pull request $1