Results for “output-enforcement”

Orchestrator for the eval-output skill suite — evaluate LLM and agent outputs for quality, accuracy, helpfulness, and safety using structured rubrics and LLM-as-judge techniques. Load when the user says "evaluate this output", "score this response", "run an eval", "LLM as judge", "evaluate agent output", "how good is this response", "rate this answer", "eval this", or provides an LLM output that should be assessed for quality. Single entry point for all output evaluation workflows.

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk. Use when evaluating a third-party skill before installing, enabling, updating, publishing, or distributing it; reviewing an untrusted SKILL.md, agent configuration, MCP integration, archive, or repository; comparing a package with a known-good version; or investigating unexpected tool, network, credential, or filesystem behavior.

Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.

Produces an evidence-backed inventory of live automations (jobs, hooks, connectors, MCP servers, wrappers) and recommends keep/merge/cut/fix-next actions before rewriting anything.

Measures whether coding agents actually follow skills, rules, or agent definitions by generating test scenarios, running agents, and classifying tool calls to report compliance rates.

Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this", "which response is better", "score this against the rubric", "judge this output", "LLM as judge this". Sub-skill of eval-output orchestrator.

Use before delivering any work product to validate quality. This skill provides a standardized checklist that every agent must complete before marking work as done, ensuring consistent quality across all deliverables regardless of agent or company.

Executes DAG workflows with parallel wave processing, agent spawning, context isolation, permission enforcement, and full execution tracing. Use when running a planned DAG, managing concurrent agent execution, enforcing isolation boundaries, or tracing execution for debugging. Activate on "execute DAG", "run workflow", "spawn agents", "parallel execution", "execution trace", "agent isolation". NOT for planning DAGs (use dag-planner), validating outputs (use dag-quality), or matching skills (use dag-skills-matcher).