bob

Create and maintain agent prompts using YAML frontmatter and SKILL.md templates.

1|Updated Jan 10, 2026
One-click install
npx skills add https://github.com/drusifer/via --skill bob
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bob
Source: https://github.com/drusifer/via/tree/main/agents/bob.docs
Command: npx skills add https://github.com/drusifer/via --skill bob

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Bob skill standardizes the creation and maintenance of agent prompts, ensuring a cohesive set of capabilities across all personas.

Core Features & Use Cases

  • Create new agents with a consistent SKILL.md frontmatter using the *new workflow.
  • Update and reprompt existing agents to reflect evolving requirements with a single source of truth.
  • Broadcast team learnings and enforce shared prompting conventions across the agent network.

Quick Start

Create a new agent with *new <DESC> to generate a fully populated SKILL.md in agents/<name>.docs/ and begin managing prompts according to policy.

Frequently Asked Questions about bob

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I standardize agent prompt creation across multiple AI personas?

You can standardize agent prompt creation by using YAML frontmatter and SKILL.md templates to enforce a single source of truth, ensuring consistent state management and guardrails across all personas.

What is the best way to maintain and update prompts for existing agents?

The best way to maintain prompts is by reprompting existing agents through a standardized protocol, which updates evolving requirements while preserving cross-agent collaboration and shared learning conventions.

How does YAML frontmatter work for agent state management?

YAML frontmatter works for agent state management by embedding standardized metadata directly in SKILL.md files, providing a consistent structure that governs agent capabilities and maintains prompt integrity.

Can I broadcast team learnings and enforce prompting conventions across an agent network?

Yes, you can broadcast team learnings and enforce shared prompting conventions across the agent network, ensuring all personas operate under cohesive policies and standardized guardrails.

Do I need a specific framework to start generating standardized agent prompts?

No specific framework is required. You can generate a fully populated SKILL.md file in a designated agents directory using a simple initialization command to begin managing prompts according to policy.

When should I not use a standardized SKILL.md template for prompt engineering?

You should avoid using a standardized SKILL.md template when your project requires highly customized, non-uniform prompt structures that cannot conform to the cross-agent collaboration and state management guardrails enforced by the protocol.