What are allowed-tools in Claude Code?

Allowed-tools are specific tools or bash commands authorized within a skill's frontmatter to execute without manual user permission prompts, speeding up automated workflows.

How do I troubleshoot a skill that isn't loading?

Run Claude with the --debug flag to see if the skill is discovered and if there are YAML syntax errors. You can also use /clear to force a refresh of the skill cache.

Can I use custom arguments with my Claude skills?

Yes, by defining an 'argument-hint', you can pass user input directly into your skill using the $ARGUMENTS variable, enabling flexible slash commands like /skill-name [path].

How does the 'fork' context work in a Claude Skill?

The fork context launches the skill in an isolated subagent environment. This is useful for parallel processing or preventing the main conversation context from becoming cluttered with technical logs.

What is dynamic context injection?

It is a feature that allows you to embed backtick-enclosed bash commands within your skill file. Claude executes these commands at runtime to fetch the latest environment data, such as 'git status'.

Claude Code Skill Architect

Name: Claude Code Skill Architect
Author: outfitter-dev

byoutfitter-dev

•

개발자 도구

Streamlines the creation of advanced Claude Code skills with domain-specific configurations, tool permissions, and context management.

소개

The Claude Code Skill Architect is a meta-skill designed to help developers build, configure, and optimize specialized capabilities for Claude Code. It provides a standardized framework for implementing advanced features like allowed-tools for permissionless execution, context forking for isolated subagent tasks, and dynamic context injection via bash commands. This skill is essential for developers looking to create highly efficient, agentic workflows that reduce manual overhead and leverage domain-specific best practices within the Claude environment.

주요 기능

Dynamic context injection using real-time bash command output
18 GitHub stars
Custom slash command creation with interactive argument hints
Support for Master-Clone architectures to orchestrate complex background tasks
Advanced frontmatter configuration for tool permission management (allowed-tools)
Context mode switching between 'inherit' for shared history and 'fork' for isolated execution

사용 사례

Developing specialized security auditing skills that run in isolated subagent contexts
Creating custom project utilities that automate git operations without repeated permission prompts
Building documentation helpers that inject live environment data into Claude's context

소개

주요 기능

Dynamic context injection using real-time bash command output
18 GitHub stars
Custom slash command creation with interactive argument hints
Support for Master-Clone architectures to orchestrate complex background tasks
Advanced frontmatter configuration for tool permission management (allowed-tools)
Context mode switching between 'inherit' for shared history and 'fork' for isolated execution

사용 사례

Developing specialized security auditing skills that run in isolated subagent contexts
Creating custom project utilities that automate git operations without repeated permission prompts
Building documentation helpers that inject live environment data into Claude's context