Claude Code supports up to five stacked slash-skill invocations
TL;DR
Claude Code now loads all leading skills in stacked slash-skill invocations like /skill-a /skill-b do XYZ, up to five instead of only the first.
What changed
Claude-code now loads up to five leading slash skills in stacked invocations such as /skill-a /skill-b do XYZ. The change replaces the prior behavior that stopped after the first skill. Vibe Builders, Basic Users and Developers can now issue these combined commands without truncation.
Why it matters
Developers gain the ability to chain up to five skills in one command for multi-step coding flows. Basic Users see fewer repeated calls when combining skills in daily tasks. Vibe Builders benefit in workflows that previously required separate invocations after the first skill.
What to watch for
Test the update against the prior single-skill limit in claude-code by running a three-skill stack and inspecting the loaded skill list in the session log. Compare results with Cursor to confirm consistent behavior across tools.
Who this matters for
- Vibe Builders: Chain up to five skills in one prompt to handle complex file edits without manual restarts.
Harsh’s take
This update fixes a major friction point in terminal-based AI agents. Forcing users to invoke skills one by one was a bottleneck that broke flow and increased latency. By allowing five stacked skills, Anthropic is moving Claude Code closer to a true autonomous agent that can plan and execute multi-stage operations in a single pass.
Operators should immediately update their CLI and test complex stacks like linting, testing, and documentation in one go. This isn't just a convenience: it is a structural improvement for high-velocity builders who need the model to understand the full context of a multi-tool task before it starts writing code.
by Harsh Desai
About Claude Code
View the full Claude Code page →All Claude Code updatesGo deeper
More AI news
- Daily RoundupGPT-5.6 Sol price drop, DeepSeek V4 Flash Vision, and image models on Replicate
OpenAI cut GPT-5.6 Sol rates on Vercel while DeepSeek added vision to its Flash model and Alibaba released new image generators on Replicate.
- Weekly DigestCursor iPad and Origin beta, Claude Code subagent forking, and Codex CLI 0.149 updates you can run today
Cursor added iPad support and Google Workspace plugins, Claude Code enabled default subagent forking with GitLab tools, and OpenAI Codex shipped new CLI versions plus cross-app sync features.
- Daily RoundupReplicate adds flux-video-upscale and p-video-avatar, Vercel CLI tools ship, and agent runtimes to test
Replicate released two video models while Vercel pushed CLI and observability updates; industry reports showed Grok issues alongside new routing and agent tools across platforms.