From truesight
Fastest route to a deployed live evaluation using a pre-built Truesight template. Use when the user wants a quick start without building judgment configs from scratch.
How this skill is triggered — by the user, by Claude, or both
Slash command
/truesight:bootstrap-template-evaluationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when a pre-built template likely covers the target use case.
Use this skill when a pre-built template likely covers the target use case.
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:
list_templates.slug.provision_template(slug).create_and_deploy_evaluation(dataset_id).api_key immediately because it is returned only once.run_eval with representative inputs.dataset_idlive_evaluation_idcreate-evaluation.list_templates requires datasets:readprovision_template requires datasets:writecreate_and_deploy_evaluation requires evaluations:write, live-evaluations:writerun_eval requires live-evaluations:executenpx claudepluginhub goodeye-labs/truesight-mcp-skillsAttaches judges to LaunchDarkly config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.
Builds LangSmith evaluation pipelines: create LLM-as-Judge/custom evaluators, capture agent outputs/trajectories via run functions, run locally with evaluate() or CLI.
Designs, tests, compares, versions, and validates prompts or LLM behavior using measurable criteria and datasets. Useful when evaluating prompt quality, edge cases, and deployment readiness.