Evaluate user queries against subagents and output a JSON decision payload.
npx skills add https://github.com/arisng/github-copilot-fc --skill agent-evaluator
Please help me install this Agent Skill. Skill: agent-evaluator Source: https://github.com/arisng/github-copilot-fc/tree/main/skills/agent-evaluator Command: npx skills add https://github.com/arisng/github-copilot-fc --skill agent-evaluator
This Skill provides a deterministic evaluator to decide which subagents to activate for a given user query, ensuring reproducible and auditable agent activation and a JSON decision payload.
Run the evaluator on a user query to determine activation: python scripts/agent_evaluator.py 'create a flowchart'
High-intent search queries and answers about installing and using this skill.
To determine subagent activation, you can run an evaluator script against a user query to produce a deterministic JSON decision payload containing activated, required, and suggested agents.
Deterministic subagent selection evaluates user queries against available agents using keyword and intent matching, yielding a reproducible JSON payload with per-agent evaluations for auditing.
Yes, the evaluator supports optional file context alongside keyword signals and intent patterns to provide context-aware scoring that influences subagent activation decisions.
You can generate a JSON payload by executing the evaluation script with a user query, which outputs structured results including activated_agents, required_agents, and suggested_agents.
A deterministic evaluator ensures reproducible and auditable agent activation by replacing dynamic selection with structured per-agent evaluations, making downstream reporting consistent.
Snowflake-LabsA concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略
AppsilonTranslate CORE validation results into an HTML report and JSON verdict.
riezEnforce the Specify-Limit-Isolate-Create-Evaluate workflow for subagent orchestration.
DevOttsBuild deterministic evaluation harnesses for LLM classifiers with exact-match scoring.
