agent-curator

Coordinate multi-phase curation sessions to refine agent definitions.

Updated Dec 23, 2025
One-click install
npx skills add https://github.com/Smith-Happens/xlightsfpptester --skill agent-curator-smith-happens
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-curator
Source: https://github.com/Smith-Happens/xlightsfpptester/tree/main/skills/agent-curator
Command: npx skills add https://github.com/Smith-Happens/xlightsfpptester --skill agent-curator-smith-happens

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables structured, scalable curation of AI agent definitions through a guided, multi-phase workflow. It coordinates knowledge research, persona refinement, tooling optimization, and instruction quality improvements to produce higher-performing agents with auditable curation records.

Core Features & Use Cases

  • Structured Curation Sessions: Guided, phase-driven interactions that systematically improve agent definitions.
  • Knowledge Research Coordination: Integrates sources and references to enrich agent knowledge and alignment.
  • Persona, Doctrine & Tooling Refinement: Sharpen identity, behavior, and server/tool configurations for consistent outcomes.
  • Operational Logging & Upstream Readiness: Generates curation session records and optional upstream contributions.

Quick Start

Activate a curation session for an agent using the orchestration workflow: [ACTIVATE:AGENT_CURATOR_V1] Parameters: agent: path/to/agent.md mode: broad | project project: {project-name} # Required if mode=project Then proceed through the phases to review knowledge sources, persona, tooling, local corpora, and instructions before saving updates.

Frequently Asked Questions about agent-curator

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

FAQPage Schema
How do I systematically refine and curate an AI agent definition?

To curate an AI agent definition, you use a structured, multi-phase guided workflow that coordinates knowledge research, persona refinement, tooling optimization, and instruction improvements to enhance agent effectiveness.

What is the best way to orchestrate agent persona and tooling refinement at scale?

The best way to orchestrate persona and tooling refinement at scale is through phase-based curation sessions that systematically review knowledge sources, behaviors, and server tool configurations for consistent outcomes.

How does a guided multi-phase workflow improve agent instruction quality?

A guided multi-phase workflow improves instruction quality by sequentially routing the agent definition through knowledge-researchers and tooling editors, systematically auditing and enhancing instructions before saving updates.

Can I generate operational logs and audit records during agent curation?

Yes, you can generate operational logs during agent curation, as the structured workflow produces curation session records and optional upstream contributions to maintain auditable improvement histories.

Do I need a specific project context to start an agent curation session?

You do not need a specific project context by default; you can activate a broad curation mode, but a project name is required if you choose to run the workflow in project mode.

When should I use broad mode versus project mode for agent curation?

Use broad mode for general agent definition enhancements without project constraints, and use project mode when you need to align the curation, knowledge sources, and tooling configurations with a specific project name.