Use when building an LLM agent that uses tools over multiple steps. Covers tool design, the agent loop, error recovery, termination, human checkpoints, and knowing when an agent is the wrong architecture.
$npx -y skills add nimadorostkar/claude-skills-collection --skill agent-designInstalls into the current project.
Run `npx skills use "https://github.com/nimadorostkar/claude-skills-collection" --skill "nimadorostkar/claude-skills-collection/agent-design"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/nimadorostkar/claude-skills-collection" that are relevant to the current task. Run `npx skills add "https://github.com/nimadorostkar/claude-skills-collection"` and select the relevant skills, then follow their instructions.