Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).

Generate highly simplified personified IP mascot logos with Flat-first geometry, rounded heavy forms, two IP colors plus one background color by default, and extremely subtle neo-skeuomorphic shading. Use when creating an animal, creature, robot, ghost, plant, object, or other character as a minimal square logo or app-icon artwork, including when the agent should infer three distinct IP directions from product-repository context.

Code style checking for RSpec files.

A collection of webhook integration skills for AI coding agents, providing step-by-step guidance and code for receiving, verifying, and handling webhooks from providers like Stripe, Shopify, and GitHub.

Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also triggers on pasted-image placeholders such as `[Image #1]` and `[Unsupported Image]`. If you can actually see the image, do not use this skill. When unsure, run `modlens guard` before the first read of a session: a deny verdict means the active model has native vision and must read the image itself. Runs the modlens CLI to convert the image into structured JSON evidence: every word transcribed, layout regions, semantics, visual clues. Also use when the user asks how to install, configure, or switch modlens providers (Gemini API key, OpenAI-compatible endpoints, Claude API or Claude Code CLI).

Idiomatic Golang design patterns — functional options, constructors, error flow and cascading, resource management and lifecycle, graceful shutdown, resilience, architecture, dependency injection, data handling, streaming, and more. Apply when explicitly choosing between architectural patterns, implementing functional options, designing constructor APIs, setting up graceful shutdown, applying resilience patterns, or asking which idiomatic Go pattern fits a specific problem.

Comprehensive guide for Go database access — parameterized queries, struct scanning, NULLable columns, transactions, isolation levels, SELECT FOR UPDATE, connection pool, batch processing, context propagation, and migration tooling. Use when writing, reviewing, or debugging Golang code that interacts with PostgreSQL, MariaDB, MySQL, or SQLite; for database testing; or for questions about database/sql, sqlx, or pgx. Does NOT generate database schemas or migration SQL.

A Claude Code slash-command skill that performs adversarial codebase review using a panel of frontier models to find bugs and issues.

Use when the Config Manager Agent reads or changes Denova presets, game modules, automations, Skills, or Agent profiles through config_read and config_apply.