Bootstrap Template Evaluation

Bootstrap Template Evaluation

Use this skill when a pre-built template likely covers the target use case.

Interactive Q&A protocol (mandatory)

BEFORE the first scoping question, search for a structured question tool (e.g., AskUserQuestion or similar interactive widget) and load it. Use that tool for EVERY scoping question. Fall back to plain-text lettered options ONLY if no such tool exists in the environment.

If template choice is ambiguous, ask one question at a time using the structured question tool (loaded per the HARD-GATE above).

Example question structure:

Which template family best matches your goal?
A) AI writing detection
B) Code quality
C) Unsure, list all templates first

Rules:

• Ask one question per message.
• Use the structured question tool for every question. Structure each with a short header, 2-4 options with labels and descriptions, and place the recommended option first. Do not add "(Recommended)" or similar annotations to option labels.
• Ask one follow-up only when needed.

Workflow

1. Discover templates:

• Call list_templates.

1. Select template:

• Match use case to template slug.

1. Provision private dataset:

• Call provision_template(slug).

1. Deploy live evaluation:

• Call create_and_deploy_evaluation(dataset_id).
• Capture api_key immediately because it is returned only once.

1. Verify:

• Run run_eval with representative inputs.

1. Return deployment artifacts:

• dataset_id
• live_evaluation_id
• verification result

Guardrails

• If no template fits, hand off to create-evaluation.
• Do not skip verification after deployment.

Scopes reference

• list_templates requires datasets:read
• provision_template requires datasets:write
• create_and_deploy_evaluation requires evaluations:write, live-evaluations:write
• run_eval requires live-evaluations:execute

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: Goodeye-Labs
• Source: Goodeye-Labs/truesight-mcp-skills
• License: MIT
• Homepage: https://truesight.goodeyelabs.com/docs/mcp-integration

Install and usage instructions live in the source repository linked above.