Claude Code Slash Commands · page 11

Interactive wizard to configure user preferences for command defaults and behavior

Generate 8 project design documents (overview, architecture, tech-stack, data, API, capacity, deployment, workflow) via interactive questionnaire or config file

Generate OKLCH design tokens with WCAG validation, shadcn/ui integration, and Tailwind v4 theming via 8 customization questions

Discovery-first prototyping - explore app ideas with zero-risk iteration before committing to roadmap/features

Manage product roadmap via GitHub Issues (brainstorm, prioritize, track). Auto-validates features against project vision (from overview.md) before adding to roadmap.

Diagnose and fix CI/deployment blockers for pull requests to enable safe deployment

Run quality gates (CI checks or security scanning)

Run on-demand code review during development (voting-enabled)

Check and set up everything needed for /crew (agent teams, Go binaries)

Load a synced session summary for context

List synced sessions from GitHub

Configure which sections appear in the Claude Code statusline

Disable session sync to GitHub

Enable session sync to GitHub for cross-device continuation

Manually sync current session to GitHub now

Launch a code-mode agent team

Scaffold a custom workflow — generates a mode skill and shortcut command

Launch a general-mode agent team

Interactively launch an agent team with guided setup

Walk through swarm's core concepts and launch your first team

Run recursive refinement on the current branch and PR

Launch a triage-mode agent team — diagnose an issue without changing it

Regenerate an existing custom workflow's shortcut command wiring from the current swarm template

Update the swarm plugin to the latest version

Launch a custom workflow using a user-defined mode skill

Launch a writing-mode agent team

Launch an evidence-mode agent team (code mode + a durable evidence record)

Perform a comprehensive PR review with code analysis, best practices check, and suggestions

Perform a comprehensive PR review with code analysis, best practices

Quick SEO + AEO check on the current file or a specified page

Generate SEO + AEO + GEO-optimized content for a topic or keyword

Research and generate a complete topic plan with keyword mapping, audience, angle, and competitive positioning

tag and push a release after the release PR is merged

create a release PR (auto-detects previous tag)

Invoke the shared Gemini bridge for long-context code exploration, analysis, and documentation generation

Opens a link to join the Pinecone Discord, allowing users to learn from each other, contact the Pinecone team, and get help in our dedicated help channel.

Diagnose a flaky test by running it N times. Delegates to flaky-test-isolator subagent — N runs, signature-grouped failures, stability report. Does NOT fix the test.

代码库分析，从 Git 历史和代码结构提取编码模式

构建项目并检查错误（修复错误见 /cc-best:fix）

快速恢复上下文，了解项目当前状态

CC-Best Ralph Loop 集成，长时间自主循环

检查点管理，保存和恢复进度

需求澄清智能体，解决 REQ 文档中的待澄清项

死代码清理和代码整理

代码架构文档生成，自动扫描项目结构生成 token 优化的架构图

Git 提交命令，生成规范的 commit message（另见 /cc-best:git-guide 操作指南）

上下文压缩，减少 token 消耗

置信度检查，评估当前阶段的决策质量和完成度

上下文管理，加载项目信息（会话级，另见 /cc-best:memory 管理持久记忆）

UI 设计师智能体，负责界面设计审查和用户体验优化

研发工程师智能体，负责功能编码实现

文档同步，更新项目文档

知识演化，将学习内容聚类生成 Skills/Agents/Commands

GitHub Issue 端到端修复闭环（分析→修复→测试→提交→关闭）

快速修复构建/类型/编译错误，最小化 diff（构建检查见 /cc-best:build）

Git 提交规范和操作指南（参考文档，提交请用 /cc-best:commit）

紧急修复快速通道，跳过 PM/Lead 直接 Dev→Verify→Commit

模型推理和测试

自主迭代循环，自动完成任务序列

研发经理智能体，负责技术方案设计和任务分解

会话学习，从会话中提取可复用模式

项目记忆管理，维护 memory-bank（持久化，另见 /cc-best:context 管理会话上下文）

切换工作模式以适应不同场景（dev/research/review/planning）

结对编程模式，与用户协作开发

产品经理智能体，负责需求分析和产品规划

创建 Pull Request

测试工程师智能体，负责质量保证和问题验证

版本发布管理（版本号同步、CHANGELOG 更新、Git Tag）

启动开发服务或应用（快捷启动，完整管理见 /cc-best:service）

配置安全扫描，审计插件自身配置的安全性

自我检查，验证输出质量

开发服务管理（自动检测运行时、启动/停止/重启服务）

配置项目首选包管理器 (npm/pnpm/yarn/bun)

项目初始化，配置 Claude Code 项目和 Hooks

项目状态与诊断信息

组件库审计，评估 skills/rules/commands 的健康度

任务粒度管理，分解和追踪任务

运行项目测试套件

训练机器学习/深度学习模型

综合验证命令，执行构建、类型、Lint、测试、安全检查

Analyze staged changes and organize them into intuitive atomic commits following conventional commits.

Address code review feedback — corroborate, validate, and implement changes from a review's final.md.

Create a new custom reviewer from a natural language description.

Check OCR installation and verify all dependencies are available.

List past OCR review sessions.

Generate a Code Review Map to help navigate large, complex changesets.

Post the current OCR review to a GitHub PR.

Run an AI-powered multi-agent code review on your changes.

List all available reviewer personas for code review.

Display a past OCR review session.

Sync reviewer metadata from markdown files to reviewers-meta.json for the dashboard.

Translate a multi-reviewer code review into a single human-voice GitHub PR comment.

Review a given code review markdown document, GitHub PR review, or inline feedback — corroborate each point against actual code, then implement valid changes.

Set Tokenless style to chat: shortest readable output

Set Tokenless style to coding: dense structured output

Disable Tokenless style and compression hooks

Show Tokenless status, savings, latest artifact, and style controls