@riba2534: #claudecode Claude Code comes built-in with a ton of useful features—I thought everyone knew about them, but apparently…

X AI KOLs Timeline Tools
claude-code ai-coding developer-tools slash-commands automation code-review

Summary

推文整理了 Claude Code 内置的大量实用斜杠命令与功能，按代码审查、验证运行、批量任务、配置维护等场景分类，并分享了一套自动化组合工作流与使用技巧。

#claudecode Claude Code comes built-in with a ton of useful features—I thought everyone knew about them, but apparently a lot of folks don't. I've put together a complete list organized by scenario 👇 🔍 Code Review - /code-review: Specifically hunts down correctness bugs, alias /review. Optional intensity from low to max, --fix directly patches, --comment posts to PR, ultra runs cloud-based deep review - /simplify: Four agents in parallel check for reuse, simplification, efficiency, and abstraction levels, directly edits code, but doesn't hunt bugs - /security-review: Scans changes in the current branch relative to main for injection, auth, data leaks, and other vulnerabilities - /ultrareview: Cloud-based multi-agent deep review, equivalent to /code-review ultra, Pro/Max gets 3 free runs ✅ Verify Changes Actually Run - /verify: Compiles and runs the app to confirm changes really take effect, no fooling around with tests or type checks - /run: Starts up and interacts with your app, see the effects with your own eyes - /run-skill-generator: Run once per project to record installation and startup steps as a recipe, then /run and /verify follow it 🚀 Big Jobs, Long Jobs - /batch <command>: Breaks big changes into 5 to 30 independent units, each in its own workspace running in parallel, like a full JS to TS migration - /goal <condition>: Keeps going until the condition is met - /loop [interval] [prompt]: Repeatedly executes on a timer, like checking deployment every 5 minutes - /plan: Jumps straight into planning mode, think it through before diving in - /workflows: View, pause, resume running workflows 🛠 Config and Maintenance - /doctor: Health check on install, settings, plugins, and CLAUDE.md, and helps fix issues; /doctor prompt-audit specifically checks for outdated or conflicting instructions - /fewer-permission-prompts: Pulls common read-only commands from history into a whitelist to cut down on confirmation popups - /update-config: One-liner to tweak settings.json, like adding hooks or setting env vars - /init: Generates CLAUDE.md for the project - /insights: Analyzes your recent usage habits, generates an HTML report - /debug: Turns on debug logs to troubleshoot Claude Code itself 🎨 Other Scenarios - /claude-api: For writing Claude API projects, with subcommands like migrate, cost-optimize, build-eval - /dataviz: Guidance on charts and dashboards - /design: Sketches UI mocks, flowcharts, posters - /slides: One-liner to generate PPT - /claude-in-chrome: Lets it operate your browser, test pages, fill forms, check console 💡 My Fully Automated Combo Punch /simplify → /code-review max --fix → Open PR → /goal watches the PR and handles all comments 📌 Two Little Tips - Custom skills you write can also be used as slash commands, same name overrides built-ins - Don't want bundled skills? Add "disableBundledSkills": true in settings Official full list:
Original Article
View Cached Full Text

Cached at: 10/11/26, 03:16 PM

#claudecode Claude Code comes built-in with a ton of useful features—I thought everyone knew about them, but apparently a lot of folks don’t. I’ve put together a complete list organized by scenario 👇 🔍 Code Review

  • /code-review: Specifically hunts down correctness bugs, alias /review. Optional intensity from low to max, –fix directly patches, –comment posts to PR, ultra runs cloud-based deep review
  • /simplify: Four agents in parallel check for reuse, simplification, efficiency, and abstraction levels, directly edits code, but doesn’t hunt bugs
  • /security-review: Scans changes in the current branch relative to main for injection, auth, data leaks, and other vulnerabilities
  • /ultrareview: Cloud-based multi-agent deep review, equivalent to /code-review ultra, Pro/Max gets 3 free runs ✅ Verify Changes Actually Run
  • /verify: Compiles and runs the app to confirm changes really take effect, no fooling around with tests or type checks
  • /run: Starts up and interacts with your app, see the effects with your own eyes
  • /run-skill-generator: Run once per project to record installation and startup steps as a recipe, then /run and /verify follow it 🚀 Big Jobs, Long Jobs
  • /batch : Breaks big changes into 5 to 30 independent units, each in its own workspace running in parallel, like a full JS to TS migration
  • /goal : Keeps going until the condition is met
  • /loop [interval] [prompt]: Repeatedly executes on a timer, like checking deployment every 5 minutes
  • /plan: Jumps straight into planning mode, think it through before diving in
  • /workflows: View, pause, resume running workflows 🛠 Config and Maintenance
  • /doctor: Health check on install, settings, plugins, and CLAUDE.md, and helps fix issues; /doctor prompt-audit specifically checks for outdated or conflicting instructions
  • /fewer-permission-prompts: Pulls common read-only commands from history into a whitelist to cut down on confirmation popups
  • /update-config: One-liner to tweak settings.json, like adding hooks or setting env vars
  • /init: Generates CLAUDE.md for the project
  • /insights: Analyzes your recent usage habits, generates an HTML report
  • /debug: Turns on debug logs to troubleshoot Claude Code itself 🎨 Other Scenarios
  • /claude-api: For writing Claude API projects, with subcommands like migrate, cost-optimize, build-eval
  • /dataviz: Guidance on charts and dashboards
  • /design: Sketches UI mocks, flowcharts, posters
  • /slides: One-liner to generate PPT
  • /claude-in-chrome: Lets it operate your browser, test pages, fill forms, check console 💡 My Fully Automated Combo Punch /simplify → /code-review max –fix → Open PR → /goal watches the PR and handles all comments 📌 Two Little Tips
  • Custom skills you write can also be used as slash commands, same name overrides built-ins
  • Don’t want bundled skills? Add “disableBundledSkills”: true in settings Official full list:

Similar Articles

@vincemask: The advanced use of Claude lies in building an Agent system that can automatically decompose tasks, generate prompts, assign roles, and review results. An efficient Claude workflow typically includes: 1. Using files like CLAUDE.md to accumulate long-term project context 2. Letting multiple Agents each...

X AI KOLs Timeline

Introduces the advanced use of Claude, which involves building an Agent system that automatically decomposes tasks, generates prompts, assigns roles, and reviews results, including using files like CLAUDE.md to accumulate context and multi-Agent collaboration to build automated workflows.

@Xudong07452910: Open-source tutorial recommendation: 'Claude How-To' – The most complete advanced learning path for Claude Code, with diagrams, templates, and self-assessment. If you've been using Claude Code in a 'look up as you go' manner, this project is worth 11-13 hours to go through systematically. It uses Me...

X AI KOLs Timeline

Recommend an open-source tutorial called 'Claude How-To', which provides a complete advanced learning path for Claude Code, including visual flowcharts, production-grade templates, and self-assessment quizzes. Suitable for developers to go from zero to proficient in Claude Code.

@yaohui12138: I've finished reading it. Here are some key takeaways I've compiled for everyone: In this session, he primarily broke down a core mechanism overlooked by 90% of users: the CLAUDE.md context injection system. This system is divided into three levels: Enterprise-level: Organization-wide mandatory rules that cannot be overridden by individual settings. Project-level: Team-shared code standards and workflows. Loc...

X AI KOLs Timeline

The article shares key insights from a workshop by Boris on using CLAUDE.md for context injection in Claude, highlighting three usage levels, specific commands like /loop, and plan mode to improve developer workflows.

@sitinme: An open-source project that adds an "enhanced plugin pack" to Claude Code — oh-my-claudecode, upgrading the originally solo-operating Claude Code into more of an AI development team with division of labor, workflows, and automation capabilities. Many people use Claude Cod…

X AI KOLs Timeline

oh-my-claudecode is an open-source project that provides an enhanced plugin pack for Claude Code, upgrading it into an AI development team with task division, automated workflows, and team collaboration capabilities, suitable for heavy users and complex projects.