Validate DAG node outputs against schemas and reliability criteria.
npx skills add https://github.com/curiositech/port-daddy --skill dag-quality
Please help me install this Agent Skill. Skill: dag-quality Source: https://github.com/curiositech/port-daddy/tree/main/skills/dag-quality Command: npx skills add https://github.com/curiositech/port-daddy --skill dag-quality
DAG-based workflows often stall due to unvalidated node outputs. This skill provides a quality gate by validating outputs against schemas, scoring confidence, detecting hallucinations, monitoring convergence, and guiding iterative improvements.
Begin by feeding the latest DAG node output to the dag-quality skill to obtain a quality assessment and actionable iteration guidance.
High-intent search queries and answers about installing and using this skill.
Validating DAG node outputs against schemas involves checking structured data to ensure it meets predefined criteria before progression. This skill gates DAG workflows by applying schema validation, confidence scoring, and hallucination detection to individual node outputs, preventing unvalidated data from stalling downstream steps.
Hallucination detection in DAG workflows identifies unreliable or fabricated AI-generated outputs before they propagate. You need it when orchestrating AI agents iteratively, as it scores node confidence and gates progression to ensure only verified, reliable outputs advance to subsequent workflow steps.
Implementing convergence monitoring for iterative AI agent refinement requires tracking output stability across DAG iterations. This skill evaluates convergence and generates structured feedback synthesis, guiding re-execution decisions to determine whether nodes should continue iterating or finalize based on reliability criteria.
Yes, this DAG quality gating approach works without external dependencies. It operates as a standalone skill with no required dependencies, allowing you to directly feed DAG node outputs into the skill to obtain quality assessments and actionable iteration guidance.
The best way to automate quality checks for unvalidated DAG node outputs is implementing a quality gate that evaluates outputs against schemas and reliability criteria. This skill automates schema validation, confidence scoring, and feedback synthesis to seamlessly gate progression between DAG steps in AI agent orchestration.
AI agent workflows stall due to unvalidated node outputs when downstream steps cannot process unreliable or non-conforming data. This skill resolves stalls by validating outputs against schemas, detecting hallucinations, and synthesizing structured feedback to guide iterative improvements and gate progression.
aquariuscookValidate n8n workflow structure, data flow, and error handling.
REVREBELEvaluate and refine AI agent outputs through iterative feedback loops.
ax-llmGenerate typed AxFlow workflow code for AI pipelines.
MichelMokbelRun automated verification checks on Node.js codebases with git rollback.
