Loading...
Loading...
Found 49 Skills
PR-backed and current-main optimization manual for `moonshotai/Kimi-K2*` and `moonshotai/Kimi-K2.5*` in SGLang. Use when Codex needs to recover, extend, or audit Kimi optimizations, including K2 router/MoE fast paths, K2 thinking Marlin paths, K2.5 wrapper/multimodal/runtime plumbing, W4AFP8/W4A16 quant tracks, parser contracts, LoRA coverage, and backend-specific validation.
Monochrome — Ivory ledger paper with all-black type; Lora serif headlines, Jost body, no color at all. Anything that should feel like a hand-typeset ledger: user research synthesis, white papers, longform reports, academic and policy briefs, advisory deliverables, bilingual EN/CN reports.
External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron policy setup, HF import/export, checkpoint/resume, non-colocated vLLM refit, delta weight transfer, optional LoRA/generation variants, and questions such as "does this model work in NeMo-RL", "run NeMo-RL e2e", or "external RL loop validation". Covers running NeMo-RL Megatron policy jobs from a Bridge checkout, choosing GRPO/SFT/checkpoint/non-colocated refit variants, setting PYTHONPATH so NeMo-RL imports the local Bridge tree, and reporting pass/fail evidence.
IoT protocols: Zigbee (mesh), Z-Wave (home), LoRaWAN (long-range), CoAP (lightweight), Matter (interoperable), Thread (I
Craft high-quality natural-language image prompts for any modern text-to-image or image-edit model that accepts flowing English. Trigger when the user wants help writing, rewriting, improving, or translating an English natural-language image prompt — including "write me an image prompt", "improve this image prompt", "describe this scene for an image model", or "convert these tags into a natural language prompt". Do NOT trigger for requests that are purely about dispatching to an image API, choosing samplers/schedulers, picking LoRAs, or setting up ControlNet — those belong to a runtime skill.
Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes promotion, when choosing a quantization format for a target device, or when an exported model fails its smoke test.
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
Conducts a guided conversational interview with the user about the image or scene they want to create, asking pertinent questions to fully understand their vision, then synthesizes a perfect model-appropriate prompt with recommended settings. Use when the user says "I want to create...", "help me make an image of...", "I have an idea for...", or asks for help crafting a prompt.
Master fine-tuning of large language models for specific domains and tasks. Covers data preparation, training techniques, optimization strategies, and evaluation methods. Use when adapting models for specialized applications, reducing inference costs, or improving domain-specific performance.
Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer
Use when editing ComfyUI workflow JSON, adding nodes, wiring connections, modifying workflows, adding ControlNet/LoRA/upscaling to a workflow, or submitting workflows to ComfyUI.
Train personalized AI agents with reinforcement learning from conversational feedback using OpenClaw-RL's async framework