Launch a sub-agent judge to evaluate conversation results with evidence-based scoring.
npx skills add https://github.com/dalawwa/labor-methods --skill sadd-judge
Please help me install this Agent Skill. Skill: sadd:judge Source: https://github.com/dalawwa/labor-methods/tree/main/.cek/plugins/sadd/skills/judge Command: npx skills add https://github.com/dalawwa/labor-methods --skill sadd-judge
This Skill enables rapid, isolated evaluation of work produced during a conversation by deploying a sub-agent judge that provides structured, evidence-based feedback and scoring.
Launch the judge sub-agent to evaluate the latest work produced in the conversation.
High-intent search queries and answers about installing and using this skill.
Launch a sub-agent judge to evaluate results produced in the current conversation. It runs in a fresh, isolated context to prevent prior session biases from influencing the structured assessment.
Evidence-based scoring requires every score to include citations from the work, such as file locations and line references. This ensures all evaluation feedback is grounded in specific, verifiable evidence rather than subjective judgment.
Launch the judge sub-agent to evaluate your latest analysis. It applies a multi-dimensional rubric with weighted criteria and clear level descriptions, performing self-verification before delivering a report-only outcome.
Yes, this skill is applicable to evaluating code, analysis, or documentation across isolated contexts. It deploys a sub-agent judge that provides structured, evidence-based feedback for these varied work types.
No, the judge sub-agent provides a report-only outcome. It delivers findings and structured feedback without making any automatic changes to the evaluated code, analysis, or documentation.
Use a sub-agent judge that enforces context isolation, evidence-based scoring, and self-verification. This approach includes dynamic verification questions and documented adjustments to ensure accurate, verifiable feedback.
Ikram-AlamEvaluate agent outputs against rubrics and ground truth with multi-dimensional scoring.
luicabref97Generate YAML rubrics and score conversational artifacts with cited evidence.
ductrung-nguyenIsolate sub-agent contexts to enforce unbiased artifact validation.
flutterOrchestrate automated evaluation of agent skills using isolated subagents and rubrics.
