austn-tools
Generate content using austn.net AI services (TTS, images, etc.)
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Generate content using austn.net AI services (TTS, images, etc.)
Auto router patterns for this project. Intelligent model selection via task classification, cost tier diversity, high-stakes override, weighted tier selection. Triggers on "auto router", "model select…
Create and maintain automation scripts and modules for pilot workflows and integrations. Use when automating repetitive tasks, integrating APIs, or generating reliable, repeatable code for pilots to a…
Set up autonomous coding agent projects with long-running harnesses using Archon MCP for state management. Creates complete project scaffolds with initializer/coding agent prompts, feature tracking, s…
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference…
Use when implementing ANY Apple Intelligence or on-device AI feature. Covers Foundation Models, @Generable, LanguageModelSession, structured output, Tool protocol, iOS 26 AI integration.
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a G…
Provision brain-computer interface interaction capabilities.
Automatically activates when detecting complex, multi-task requests that would benefit from parallel execution. Activates when user mentions "build [system]", "implement [feature] with multiple compon…
Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimi…
Search, filter, and retrieve Claude/Codex history indexed by the automem CLI. Use when the user wants to index history, run lexical/semantic/hybrid search, fetch full transcripts, or produce LLM-frien…
Build AI applications on AWS using Bedrock, SageMaker, and AI/ML services with best practices for enterprise deployment
Generate AWS architecture diagrams from infrastructure JSON. Use when user asks to "generate diagram", "create AWS diagram", "visualize infrastructure", or "draw architecture".
Vision framework API, VNDetectHumanHandPoseRequest, VNDetectHumanBodyPoseRequest, person segmentation, face detection, VNImageRequestHandler, recognized points, joint landmarks, VNRecognizeTextRequest…
Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, or co…
Design and refactor beam tracking ML/RL pipelines (CSI teacher vs RSRP student), enforce shape contracts, and produce inference-safe models.
Programmatic asset compliance validation using vision analysis and Northcote scorecard. Eliminates manual validation loops—upload image, receive scored JSON with correction prompts in 30 seconds.
Automates Apple Voice Memos (Mac Catalyst, no dictionary) via JXA using filesystem/SQLite access and System Events UI scripting. Use when asked to "automate Voice Memos", "export voice recordings", "a…
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool API…
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference…
Use when working with AWS Strands Agents SDK or Amazon Bedrock AgentCore platform for building AI agents. Provides architecture guidance, implementation patterns, deployment strategies, observability,…
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
An internal cognitive engine for quantitative root cause analysis. Use this autonomously when you need to weigh competing hypotheses, prevent anchoring bias, or determine the most efficient next diagn…
BeatLab JSON contract for 16-step (0-15) pianoSequence & drumSequence. Use when generating or editing beats.