Agent Skills by rnben
Showing 79 vetted skills indexed across 1 GitHub repositories.
rnbendogfood
Automate exploratory QA testing of web applications with screenshots and structured reports.
rnbenopenhue
Control Philips Hue lights, rooms, and scenes via the OpenHue CLI.
rnbenyoutube-content
Fetch YouTube transcripts and generate chapters, summaries, threads, and blog posts.
rnbenheartmula
Generate music from lyrics and tags using HeartMuLa models.
rnbensongsee
Generate spectrograms and multi-panel audio feature visualizations from audio files.
rnbengif-search
Search and download Tenor GIFs using curl and jq.
rnbenfind-nearby
Find nearby places using OpenStreetMap data by coordinates, addresses, city names, or zip codes.
rnbenapple-reminders
Manage Apple Reminders from the terminal using remindctl commands.
rnbenimessage
Read and send iMessages and SMS from the macOS command line via imsg.
rnbenfindmy
Automate Find My on macOS to locate Apple devices and AirTags.
rnbenapple-notes
Manage Apple Notes from the terminal using the memo CLI.
rnbenjupyter-live-kernel
Run stateful Python code iteratively through a live Jupyter kernel.
rnbendspy
Build declarative AI pipelines orchestrating LM tasks across providers.
rnbenaudiocraft-audio-generation
Convert textual prompts into music and sound effects with configurable settings.
rnbenevaluating-llms-harness
Evaluate LLMs across 60+ benchmarks using the lm-eval framework.
rnbenhuggingface-hub
Search, download, and manage Hugging Face Hub models, datasets, and Spaces via CLI.
rnbensegment-anything-model
Segment arbitrary objects in images using point, box, or mask prompts.
rnbenguidance
Constrain LLM outputs with regex and grammars for valid JSON, XML, and code.
rnbenclip
Classify images and rank text prompts with a pretrained CLIP model.
rnbenfine-tuning-with-trl
Fine-tune language models with TRL for RLHF alignment workflows.
rnbengrpo-rl-training
Automate GRPO-RL fine-tuning workflows with TRL for language models.
rnbengguf-quantization
Quantize llama.cpp models to GGUF format for CPU inference.
rnbenserving-llms-vllm
Deploy high-throughput LLM serving with vLLM for OpenAI-compatible endpoints.
rnbenobliteratus
Remove refusal behavior from open-weight LLMs via CLI-driven abliteration.