Dockerfile mistakes can create insecure and unreliable container images. This skill provides Hadolint workflows, rule guidance, remediation examples, and reusable CI configurations.

Container findings are difficult to rank across severity, exploitability, and exposure. This skill guides Grype scans and practical remediation priorities.

Inconsistent API definitions can hide security and governance defects. This skill guides Spectral configuration, OWASP-focused linting, custom rules, reporting, and CI integration.

API traffic is difficult to inspect, modify, and replay across clients. This skill provides structured mitmproxy workflows for authorized security testing and debugging.

Packet captures are difficult to inspect quickly and consistently. This skill provides TShark workflows for filtering traffic, extracting evidence, and reporting findings.

Coordinating several AI workers can make roles, tasks, and progress difficult to track. This skill manages Agentix teams through a structured API workflow.

UI and UX work often loses consistency across screens, states, and decisions. This skill gives Claude, Codex, and Claude Code a concise checklist for design reviews and documentation.

Testing work often becomes inconsistent across planning, execution, and reporting. This skill helps Claude, Codex, and Claude Code guide structured test operations.

Parallel AI work fails when roles, checkpoints, and reports are unclear. This skill gives Claude, Codex, and Claude Code teams a repeatable child-agent operating process.

Schema changes can break validators, consumers, and existing signal data. This skill guides scoped Zod schema updates with compatibility checks, deterministic validation, and focused tests.

ECC changes quickly, so remembered catalogs and install guidance can become outdated. This skill checks current repository files before recommending components or actions.

Maintainers often need consistent issue triage across reports, comments, and code evidence. This skill provides a focused workflow and response templates for FiftyOne GitHub issues.

Duplicate and near-duplicate images can distort dataset quality and model training. This skill guides Claude, Codex, or Claude Code through FiftyOne Brain workflows to find, review, and remove redundant samples.

Image datasets can hide clusters, outliers, and label problems. This skill guides Claude, Codex, and Claude Code through FiftyOne embedding visualizations.

FiftyOne plugin work can require many files, APIs, and testing steps. This skill guides agents through planning, code generation, local install, and iteration.

Computer vision teams need repeatable ways to load media, labels, and predictions into FiftyOne. This skill guides Claude, Codex, and Claude Code through dataset creation, import validation, and model inference.

Dataset imports often fail when media, annotations, and multimodal folders use different formats. This skill guides scanning, detection, package setup, import, grouping, and validation in FiftyOne.

FiftyOne contributors need consistent Python style across imports, docstrings, utilities, and validation. This skill provides focused conventions and checklists for compatible code.

GKE operations can be complex across deployment, scaling, identity, and troubleshooting. This skill provides practical workflows, commands, and production patterns for reliable GKE management.

Search visibility depends on crawlability, metadata, page structure, and structured data. This skill helps Claude, Codex, and Claude Code apply practical SEO checks and recommendations.