coding-agent-standards
Defines practical standards for implementation-focused coding agents. Use when creating or editing code, especially when…
Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.
$ npx -y skills add repowise-dev/claude-code-prompts --skill prompt-architect --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/prompt-architectContext preview
The summary Claude sees to decide when to auto-load this skill.
Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.
name: prompt-architect description: Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.
Use this skill to turn vague intent into reliable prompt instructions.
1. Define objective, audience, and success criteria. 2. Capture hard constraints (format, tools, safety, style). 3. Specify required reasoning boundaries and output structure. 4. Add verification instructions and failure handling. 5. Iterate using concrete examples and observed errors.
Use [reference.md](reference.md) for compact templates, anti-patterns, and refinement loops.
Independently written prompt templates for building AI coding agents, inspired by patterns observed in Claude Code codebase. System prompts, tool prompts, agent prompts, memory management, and multi-agent coordination.
Defines practical standards for implementation-focused coding agents. Use when creating or editing code, especially when…
Provides a structured verification workflow for code and prompt outputs. Use when asked to validate correctness, catch…