Craft clear, actionable prompts and instruction surfaces for Azoth agents.
npx skills add https://github.com/yiwei79/azoth --skill prompt-engineer-yiwei79
Please help me install this Agent Skill. Skill: prompt-engineer Source: https://github.com/yiwei79/azoth/tree/main/.opencode/skills/prompt-engineer Command: npx skills add https://github.com/yiwei79/azoth --skill prompt-engineer-yiwei79
Craft reliable prompts and agent instructions across Azoth's ecosystem to reduce ambiguity and improve consistency.
Apply the RCTF pattern to craft clear agent instructions and run an L2 refinement pass to improve prompts.
High-intent search queries and answers about installing and using this skill.
Clear system prompts for AI agents require structured instruction surfaces using patterns like RCTF to enforce consistency. Applying explicit prompt patterns standardizes agent behavior and reduces ambiguity across different tasks and toolchains.
L2 refinement in prompt engineering is an evidence-driven auto-refinement pass that iteratively improves agent instructions. It applies governance-oriented quality checks to evaluate and enhance prompt clarity, ensuring reliable and actionable outputs.
Standardize slash commands and agent definitions across toolchains by applying cross-surface prompt patterns like SKILL.md. This ensures instruction consistency, evaluability, and governance compliance regardless of the specific platform used.
Enforce anti-slop and governance checks in LLM prompts by embedding explicit quality checks and evidence-driven improvement workflows into the instruction design. Using structured prompt patterns ensures outputs meet governance standards and reduces low-quality generations.
Prompt engineering patterns apply across both slash commands and full agent definitions in Azoth's ecosystem. Cross-surface applicability ensures that instruction consistency, governance, and L2 refinement are maintained regardless of the interaction surface.
Agent instructions produce inconsistent results when lacking standardized prompt patterns and explicit quality checks. Applying structured governance frameworks like RCTF and running L2 refinement passes reduces ambiguity and ensures reliable, consistent task execution.
meta-pytorchParse GitHub issues into goals, acceptance criteria, and constraints.
akillnessDefine role-based workflows with auditable execution for multi-agent orchestration.
SOLEROMStandardize slash-command frontmatter and YAML fields across plugins.
starlink-awakenAutomates iterative Algorithm cycles with human review between each pass.
