124 tagged edge-ai, measured the same way as everything else here.
Browse within: ai-assistant 57android 57computer-vision 18Multimodal 17agentic-workflow 17ai-glasses 17clawdbot 17meta-evolution 17kubernetes 16aipu 15axelera 15homelab 12local-ai 12self-hosted 12
Skill Claude CodeCodex
Olares app packaging and chart authoring via olares-cli chart — port a repo, docker-compose, or generic Helm chart; build/push the image; author, lint, package, and deploy an OlaresManifest; wire storage, middleware, entrances, env, and GPU; edit the chart after diagnosis. Runtime failure diagnosis is olares-doctor…
Skill Claude CodeCodex
Runtime diagnosis for Olares apps and the system via olares-cli — find the root cause when an app won't install or start, crashes, cannot pull an image, is running but unreachable, or is slow; includes doctor images and thirdleveldomain. Use for diagnosing catalog and dev app failures, not for authoring or editing…
Skill Claude CodeCodex
Olares models via olares-cli router — Router (the AI gateway) and the Model Console inside a locally installed model application. Configure cloud vendors and their models, manage local LLM / embedding / audio / OCR model applications, edit a local model's card, name models with aliases, groups and default categories…
Skill Claude CodeCodex
Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long…
Skill Claude CodeCodex
Convert a PyTorch or Hugging Face model into a LiteRT model that runs fully on the GPU via the CompiledModel API with verified-correct output, and lay it out as a model recipe. Use when converting a new model, or when a converted model is rejected by the GPU, falls back to CPU, or returns wrong numbers on device.
Skill Claude CodeCodex
Rapidly migrate an Android application from legacy TensorFlow Lite (TFLite) to modern LiteRT CompiledModel API v2.1.6 in Open Source GitHub repositories. Supports True Async Execution (runAsync), Zero-Copy I/O Buffers, NPU JIT compilation, and automated 2-stage verification self-testing.
Skill Claude CodeCodex
Turn a finished Edge Agents .workflow.json into a runnable, standalone deployment bundle — the docker-compose package (engine + config + any llama components + any operator-authored custom components) an operator builds and runs on an edge/IoT controller. Drives the fh-workflow CLI's headless deploy, reading the…
Skill Claude CodeCodex
Generate a validated Edge Agents workflow JSON (.workflow.json) from a natural-language description — the node-graph that runs on Edge Agents edge/IoT agents, built from triggers (timer, startup, pin edge, threshold, MQTT, serial), GPIO/serial/MQTT I/O, LLM Agent nodes, and actuators. Builds the graph to match the…
Skill Claude CodeCodex
Maintain docs/research-report.md, the living technical report of taOSmd findings. Use when recording experiment results, adding negative results, pre-registering experiments, or revising the report. Enforces methodology discipline; never lets a number in without provenance.
Skill Claude CodeCodex
Set up agent-to-agent comms and named channels via the taOSmd A2A bus.
Skill Claude CodeCodex
When inferring character intent or behavioral patterns from video, validate inferences against cumulative observed actions rather than isolated moments or assumptions.
Skill Claude CodeCodex
When asked to identify critical actions in a video, distinguish between preparatory/support actions and core actions that directly contribute to the main objective, and rank them by significance to the end goal.
Skill Claude CodeCodex
When faced with multiple-choice video comprehension questions, systematically eliminate implausible options by cross-referencing visual content, action sequences, and contextual clues before selecting an answer.
Skill Claude CodeCodex
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing…
Skill Claude CodeCodex
Use when interacting with a Bubbaloop deployment via its MCP server — guides the discovery → control → automation workflow and prevents the most common mistakes (MCP polling for streaming data, missing Bearer token, ignoring RBAC tier).
Skill Claude CodeCodex
Manage physical sensors, cameras, and actuators via the bubbaloop skill runtime. Query real-time sensor data, control node lifecycle, and monitor hardware health.
Skill Claude CodeCodex
Transcribe audio files using AIMA's current local ASR model (speech-to-text).
Skill Claude CodeCodex
Generate images using AIMA's local z-image model (OpenAI-compatible API).
Skill Claude CodeCodex
Text-to-speech using AIMA's current local TTS model. Generate audio files from text.
Skill Claude CodeCodex
Generate executable Python scripts to control NERO/Piper robotic arms via pyAgxArm SDK based on natural language descriptions. When the user describes a robotic arm motion, this skill guides code generation with correct API usage, safety checks, and motion completion polling.
LGDiMaggio/claude-stwinbox-diagnostics
Skill Claude CodeCodex
WHAT: Connects to the STEVAL-STWINBX1 sensor board to acquire vibration data, configure MEMS sensors, and establish baseline vibration profiles for rotating machinery. WHEN: Use when the user wants to start monitoring a machine, acquire vibration data from the STWIN.box, configure sensor parameters, set up data…
LGDiMaggio/claude-stwinbox-diagnostics
Skill Claude CodeCodex
WHAT: Generates structured diagnostic reports for machine operators and maintenance technicians, summarizing vibration analysis results with severity levels, fault findings, and actionable maintenance recommendations in clear, non-technical language. WHEN: Use when the user asks to create a report, generate a…
LGDiMaggio/claude-stwinbox-diagnostics
Skill Claude CodeCodex
WHAT: Performs multi-step vibration analysis to diagnose rotating machinery faults including unbalance, misalignment, bearing defects, and mechanical looseness using FFT, envelope analysis, and bearing fault-frequency calculations. WHEN: Use when the user has vibration data (live from STWIN.box or from a file) and…
fxd0h/Axelera-Voyager-Local-Assistant
Skill Claude CodeCodex
Benchmark model performance on Axelera AI Metis hardware with the Voyager SDK. Use when the user wants to measure FPS, throughput, latency, or compare model variants. Use to quantify a working pipeline. Prefer voyager-debug when performance is a suspected fault or regression.