kevinnft

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

Plan mode: write markdown plan to .hermes/plans/, no exec.

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.

Generate visual assets (ASCII art, diagrams, banners) for repos and documentation

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Manim CE animations: 3Blue1Brown math/algo videos.

Read, search, create, and edit notes in the Obsidian vault.

Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

Run 150+ AI applications in the cloud via the inference.sh platform. Triggers on "generate image with FLUX", "create video", "use Veo/Seedance", "run inference.sh", "infsh CLI", "single key for image+video+LLM". One API key covers image generation (FLUX, Reve, Seedream, Grok, Gemini), video (Veo, Wan, Seedance, OmniHuman, HunyuanVideo), LLMs (Claude, Gemini, Kimi, GLM-4), search (Tavily, Exa), 3D

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).