Results for “quality”

Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology, including dataset creation, metric selection, failure analysis, and iterative improvement.

Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards. Use when improving a skill with multiple quality issues, iterating on a new skill until it meets standards, or automated fix-review cycles instead of manual editing.

Design structured evaluation rubrics for scoring LLM and agent outputs — defining quality dimensions, scoring scales, hard gates, score descriptions, and edge cases. Load when the user asks to create an eval rubric, define evaluation criteria, design scoring dimensions, write an eval spec, or says "what should I evaluate", "design a rubric", "create eval criteria", "define quality dimensions", "evaluation rubric for", "how do I measure quality of". Sub-skill of eval-output orchestrator.

Evaluate everything the PA agent manages — tasks, skills, PA network health, billing, calendar connections, and memory quality. Use when: owner asks for an evaluation, wants to know what's working and what isn't, or requests a performance report. Combines supervisor status with quality scoring.

Two-stage review engine with four-layer quality model for the WinDAGs meta-DAG. Receives completed node outputs and produces ReviewResult containing QualityVector. Stage 1 (Haiku) checks Floor + Wall on every node. Stage 2 (Sonnet) runs Ceiling evaluation conditionally using economic escalation formula. Enforces BC-EVAL-001 through BC-EVAL-006. Activate when operating as the Evaluator role in the meta-DAG, when reviewing node outputs, when computing quality vectors, or when deciding Stage 2 escalation.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Profile an unfamiliar dataset — shape, grain, quality, nulls, distributions, and duplicates — before any analysis is trusted.

Build and review high-quality technical docs as well as agent instruction files in your repository.

Validates agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).

Monitor a live model for data quality, input and prediction drift, performance decay, and fire retraining triggers.

Pre-ingestion verification for epistemic quality in RAG systems with 9-point verification and Two-Round HITL workflow

Guides creation of high-quality Agent Skills with domain expertise, anti-pattern detection, and progressive disclosure best practices. Activate on keywords: create skill, review skill, skill quality, skill best practices, skill anti-patterns, improve skill, skill audit. NOT for general coding advice, slash commands, MCP development, or non-skill Claude Code features.

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Use this agent when you need to run linting and code quality checks on Ruby and ERB files. Run before pushing to origin.

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

KV cache compression for LLM inference — 4.4x compression, 2x context capacity, near-lossless quality. ICLR 2026 paper implementation with vLLM integration.

Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.

`analysis-agent`/`task-agent`/`review-agent`: use for structure, workspace or package bootstrap, config, scripts, or quality gates; skip without an initialization decision.

Guide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements.

GAN-inspired Generator-Evaluator agent harness for building high-quality applications autonomously. Based on Anthropic's March 2026 harness design paper.

Create publication-quality statistical graphics in Python with dataset-oriented plotting, semantic mapping, and automatic statistical estimation.

Create publication-quality statistical graphics in Python with dataset-oriented plotting, semantic mapping, and built-in statistical estimation.

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

Use when auditing Codex skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Audit a proposed assessment for construct validity, reliability, and alignment to learning objectives. Use when reviewing or quality-assuring assessments before deployment.

Diagnoses and improves Qdrant search relevance by isolating embedding model, configuration, or query strategy issues.

Applies quantitative and qualitative analysis techniques, interprets experimental data, validates procedures, and selects appropriate methods with uncertainty quantification.

Create publication-quality statistical graphics in Python with seaborn, covering relational, distribution, and categorical plots with pandas integration.

Build high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Covers design principles, architecture, implementation patterns, and evaluation-driven development.

Create publication-quality statistical graphics directly from tabular datasets, covering relational, distribution, categorical, regression, and matrix plots with minimal code.

Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact. Use when building or reviewing automated feedback in digital learning tools.

Create publication-quality statistical graphics from tabular datasets with minimal code, supporting multivariate analysis, statistical estimation, and complex multi-panel figures.

Refactor SwiftUI views toward small, explicit, stable view types with MV data flow, dedicated subviews, and correct Observation usage.

Create publication-quality statistical graphics with dataset-oriented plotting, multivariate analysis, and automatic statistical estimation using minimal code.