AI Agent Hub
Back to skills
Prompt Master CLI icon

Prompt Master CLI

AI Agent Updated 2026.08.30

Paste the following prompt into your AI chat to install this skill:

Follow https://skillhub.cn/install/skillhub.md to install @user_5d00e27d/majia-system-prompt-cli.

About this skill

Problem

Engineers often know the desired output but struggle to express it as an executable LLM instruction: prompts are vague, missing constraints, or misclassified by task type. majia-system-prompt-cli is a local CLI workflow that turns fuzzy intent into structured prompt tasks rather than replacing the model.

How It Works

It first applies safety and intent checks, then routes work by task shape:
- M1 Research: ask for goals, targets, and constraints on first-time or ambiguous domains
- M2/M3: apply templates or expand creative tasks
- M4: analyze provided materials or data
- M5: decompose multi-step or cross-domain workflows

During execution it loads rules from rules/ for safety, research, output quality, and preference evolution, then runs a confidence self-check before output. Lightweight caching stores stable preferences to reduce repetitive clarification.

Boundaries

It is useful for prompt structuring, task decomposition, and output constraints, but it is not a compliance authority. Legal, medical, safety, and copyright cases still require human review, and output quality depends on the configured provider and model in config.yaml.

Use Cases

  • Expand “write a marketing plan” in a terminal into a prompt with goals, audience, channels, and deliverables.
  • Switch between DeepSeek and Claude via `config.yaml` to compare outputs for the same local analysis task.
  • Use M4 analysis to cluster user feedback, then produce actionable improvement recommendations.
  • Trigger M1 research on a new domain to confirm goals, constraints, and acceptance criteria before generation.

Best For

  • AI application developers who need to turn vague requirements into executable prompts with fewer rewrites.
  • Prompt engineers debugging multi-model CLI outputs who compare model differences and constraint adherence.
  • Independent researchers who want to persist personal preferences and reduce repeated goal formatting.
  • Automation engineers building CLI workflows who need generation, analysis, and planning routed into steps.