byhesreallyhim· 10 skills
Techniques for writing comprehensive, self-contained prompts when spawning sub-agents or teammates via the Task tool. Use when delegating work to agents, designing multi-agent workflows, or when spawned agents are returning poor results due to insufficient context. Covers frontloading, file path enumeration, deliverable specification, constraint injection, and pattern reuse across spawn calls.
$npx -y skills add hesreallyhim/really-claude-code --skill agent-prompt-engineeringInstalls into the current project.
Run `npx skills use "https://github.com/hesreallyhim/really-claude-code" --skill "hesreallyhim/really-claude-code/agent-prompt-engineering"` 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/hesreallyhim/really-claude-code" that are relevant to the current task. Run `npx skills add "https://github.com/hesreallyhim/really-claude-code"` and select the relevant skills, then follow their instructions.