damionrashford

@damionrashford source repo

162 skills
0 followers
7 hours ago last updated

▌
Modes Pattern · damionrashford bundle
The modes pattern

0
installs
▌
Autoresearch · damionrashford bundle
Autonomous ML experiment loop for improving NBA prediction models. Modifies autoresearch/experiment.py, runs evaluations, keeps/discards results based on NBA_CORE composite score. Use when user says "run autoresearch", "improve models", "run experiments", "optimize predictions", or "autoresearch loop".

0
installs
▌
Repo Greet · damionrashford
Prints a greeting and the sandbox host info by running its bundled script.

0
installs
▌
Sum Writer · damionrashford
Compute a sum of integers and write only the total to result.txt in the workspace root.

0
installs
▌
Dashboard · damionrashford bundle
Launch a live NotebookLM-style dashboard for managing sources and generating outputs. Use when the user wants a visual interface, dashboard, or UI for their notebook.

0
installs
▌
Ingest · damionrashford bundle
Ingest and vectorize PDFs or text files for RAG retrieval. Use when the user provides a PDF, document, or text file they want to analyze, study, or generate content from.

0
installs
▌
Generate · damionrashford bundle
Generate rich outputs from ingested sources — flashcards, quizzes, reports, slide decks, mind maps, infographics, data tables, or audio overviews. Use when the user wants to create any output from their documents.

0
installs
▌
Appeal · damionrashford
Review a standing verdict as a second panel, admitting new counters and evidence the first pass missed, then re-run and report what changed. Use when the user disputes a verdict, says it was too harsh or too generous, asks to appeal, asks for a second opinion on an analysis, or says the judge got it wrong.

0
installs
▌
Verdict · damionrashford
Deliver a structured verdict on any idea, argument, or proposal, identifying what survives scrutiny, what doesn't, and what needs more work. Includes the gadfly sting, the one uncomfortable truth nobody wants to say. Use when the user asks for a verdict, bottom line, final assessment, 'what survives', or 'give it to me straight'.

0
installs
▌
Crucible · damionrashford
Stress-test any idea, proposal, or plan by finding its weakest points, probing hidden assumptions with Socratic questions, and identifying failure modes through red team analysis. Use when the user asks to stress-test, poke holes, find weaknesses, red team, challenge, or ask 'what could go wrong' or 'what am I missing'.

0
installs
▌
Steelman · damionrashford
Build the strongest possible version of an argument, then argue the complete opposite with equal conviction. Use when the user asks to steelman something, argue both sides, make the strongest case, or understand the best version of an opposing view.

0
installs
▌
Devils Advocate · damionrashford
Full adversarial analysis of any idea, proposal, or argument. Runs steelman, crucible, and verdict in sequence for a complete challenge drawing from 10 reasoning traditions. Use when the user asks to play devil's advocate, run a full challenge, or says 'tear this apart' or 'give me the full treatment'.

0
installs
▌
Osascript UI · damionrashford bundle
Automate native macOS app UIs via System Events Accessibility API. Use when traversing UI element trees, clicking buttons by label, reading text field values, or listing menu bar items. Does NOT work on Electron apps (Slack, VSCode, Chrome).

0
installs
▌
Osascript Apps · damionrashford bundle
osascript-apps

0
installs
▌
Osascript Data · damionrashford bundle
Read macOS app SQLite databases directly. Use when reading iMessage chat history, Chrome browsing history, Safari history, or any local app SQLite DB. Always copy the DB before querying — most apps lock the file while running.

0
installs
▌
Osascript Audio · damionrashford bundle
Control macOS system audio via osascript. Use when getting or setting system volume, toggling mute, listing audio input/output devices, or checking which device is the default output.

0
installs
▌
Osascript Chrome · damionrashford bundle
Automate Google Chrome with osascript/JXA. Use when listing/focusing/closing/navigating/reloading tabs, muting tabs, managing windows, executing JavaScript, scraping page content, extracting links, filling forms, reading localStorage/cookies/audio state, or reading Chrome history/bookmarks/downloads/extensions/profiles.

0
installs
▌
Osascript Notify · damionrashford bundle
macOS notifications and system event watching. Use when sending notifications, creating actionable notifications with buttons, watching for screen lock/unlock, detecting network changes, or listening to Darwin/NSDistributedNotification system events.

0
installs
▌
Osascript System · damionrashford bundle
Inspect macOS system state with osascript/JXA. Use when listing running apps, enumerating windows with positions and IDs, taking targeted screenshots by window, querying display geometry, or using the ObjC bridge (NSWorkspace, CGWindow, NSFileManager).

0
installs
▌
Osascript Launchd · damionrashford bundle
Create and manage macOS LaunchAgents and LaunchDaemons. Use when setting up background automation, scheduled tasks, file watchers (WatchPaths), interval polling, or persistent daemons that survive logout or reboot.

0
installs
▌
Osascript Network · damionrashford bundle
Inspect macOS network state. Use when getting current WiFi SSID, signal strength, and channel; listing all network interfaces with IP/MAC addresses; or watching for network connect/disconnect events via Darwin notifications.

0
installs
▌
Osascript Sysinfo · damionrashford bundle
Read macOS system state. Use when checking battery percentage and charge state, getting OS version and hardware specs, listing startup login items, or reading macOS user defaults (NSUserDefaults / plist app preferences).

0
installs
▌
Osascript Clipboard · damionrashford bundle
Read and write the macOS clipboard with full type support. Use when reading clipboard text, HTML, RTF, images, or file paths (Finder copy); writing rich content; detecting clipboard changes via changeCount; or intercepting content between copy and paste.

0
installs
▌
Osascript Subprocess · damionrashford bundle
Run subprocesses from JXA/osascript using NSTask. Use when you need separate stdout/stderr streams, async execution, stdin piping, kill signals, exit codes, or running uv Python scripts from within a JXA automation script.

0
installs
▌
Learn · damionrashford bundle
Interactive ML education with 3 university-grade courses (CS229 Stanford, Applied ML Python, ML Engineering), 36+ structured lessons, decision frameworks, and interview prep. Supports study, quiz, explain, design, debug, and progress modes. Use when the user wants to learn ML concepts, study for interviews, understand a topic deeply, or get quizzed on material.

0
installs
▌
Media · damionrashford bundle
Extract content from YouTube videos and generate podcasts, video overviews, quizzes, flashcards, reports, and slide decks from research papers using Google NotebookLM. Use when the user wants to extract a YouTube transcript, analyze a video, turn a paper into a podcast, generate an audio summary, create a quiz from a paper, make slides from research, or automate any NotebookLM workflow.

0
installs
▌
Serve · damionrashford bundle
Compress, deploy, and serve trained ML models in production. Covers model compression (quantization, pruning, distillation, ONNX export), inference APIs, containerization, CI/CD pipelines, monitoring, health endpoints, model versioning, and reproducibility packaging. Use when the user has a trained model and wants to reduce its size, deploy it, serve it, containerize it, build an inference API, set up monitoring, write a model card, create a CI/CD pipeline, or package for reproducibility.

0
installs
▌
Train · damionrashford bundle
Train ML models and iterate systematically with experiment tracking. Full coverage of supervised learning: Naive Bayes, KNN, Discriminant Analysis (LDA/QDA), SVM/SVR, Decision Trees, Ensemble Methods (Random Forest, XGBoost, LightGBM), GLM (Poisson, Gamma, Tweedie), Gaussian Process, Ridge/Lasso/ElasticNet, and Neural Networks (PyTorch). Covers data splitting, cross-validation, metrics, persistence, hyperparameter search, and TSV-based experiment tracking. Use when the user wants to train a model, fit a classifier or regressor, evaluate performance, do cross-validation, run experiments, tune hyperparameters, or compare runs.

0
installs
▌
Analyze · damionrashford bundle
Statistical analysis, hypothesis testing, A/B testing, cohort analysis, segmentation, trend detection, business metrics, pre-delivery validation, and data visualization. Use when the user asks to "analyze this data", "run a statistical test", "compare groups", "find trends", "do A/B test analysis", "segment customers", "calculate KPIs", "validate this analysis", "check my work", "sanity check", "review my numbers", "make a chart", "create a dashboard", "plot the data", "visualize results", or mentions hypothesis testing, cohort analysis, business analytics, data validation, bar charts, line charts, heatmaps, scatter plots, or data storytelling.

0
installs
▌
Explain · damionrashford bundle
Explain model predictions with SHAP, LIME, integrated gradients, and permutation importance. Generates summary plots, waterfall charts, and force plots. Use when debugging predictions, auditing for bias, or communicating model behavior to stakeholders.

0
installs
▌
Ml Docs · damionrashford bundle
On-demand ML/data science library expert. Use when the user asks how to use any function, class, or method from NumPy, Pandas, scikit-learn, Matplotlib, TensorFlow, Keras, PyTorch, Seaborn, SciPy, statsmodels, XGBoost, LightGBM, Hugging Face Transformers, OpenCV, NLTK, spaCy, Plotly, Dask, PySpark, SQLAlchemy, or Jupyter. Fetches and synthesizes official API docs, parameter reference, and working code examples. Also use when the user asks "how do I do X in pandas/numpy/torch/sklearn", needs to understand a deep learning layer or training loop, asks about NLP pipelines, computer vision transforms, statistical tests, SQL ORM patterns, or big data ops.

0
installs
▌
Evaluate · damionrashford bundle
Systematic evaluation of ML models, experiments, and AI system outputs. Multi-dimensional rubrics, LLM-as-judge, bias detection, and structured comparison frameworks. Use when the user asks to "evaluate model performance", "compare models", "build evaluation rubrics", "assess output quality", "detect model bias", or mentions evaluation frameworks, LLM-as-judge, model comparison, or quality assessment.

0
installs
▌
Notebook · damionrashford bundle
Create, clean, organize, optimize, and convert Jupyter notebooks. Build new notebooks from scratch with proper cell structure, cell IDs, and Colab compatibility. Extract reusable functions, add documentation, generate requirements.txt, and convert to scripts. Use when the user wants to create a notebook, clean a notebook, organize cells, extract functions, convert to script, or optimize a notebook for production.

0
installs
▌
Research · damionrashford bundle
Search, fetch, download, and extract ML/AI research papers from 7 free academic sources. Find and download ML datasets from 5 free sources (HuggingFace, OpenML, UCI, Papers with Code, Kaggle). Review a paper, critique methodology, assess reproducibility, evaluate experimental design. Convert research papers, articles, or technical documents into working code prototypes. Use when the user wants to find papers, search arxiv, get citations, download a PDF, extract text from a paper, find/download datasets, review/critique a research paper, implement a paper, prototype an algorithm, or convert research to working code.

0
installs
▌
Data Prep · damionrashford bundle
Explore, clean, and engineer datasets end-to-end: statistical profiling, distribution checks, missing value analysis, duplicate detection, outlier removal, type fixing, encoding, create features, encode categories, transform columns, add rolling windows, build interaction terms, and feature engineering. Supports pandas, polars, and PySpark. Use when the user wants to explore data, profile columns, understand a dataset, clean data, handle missing values, remove duplicates, fix data types, preprocess a dataset before modeling, create features, encode categories, transform columns, add rolling windows, build interaction terms, or do feature engineering.

0
installs
▌
Fine Tune · damionrashford bundle
Fine-tune language models with LoRA, QLoRA, or full fine-tuning. Covers unsloth (4x memory reduction), PEFT, trl SFTTrainer, DPO, instruction tuning with chat templates, dataset preparation, and evaluation. Use when fine-tuning any HuggingFace model on custom data.

0
installs
▌
MCP Builder · damionrashford bundle
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

0
installs
▌
Drift Detect · damionrashford bundle
Detect data drift, concept drift, and model performance degradation in production. Uses PSI, KS-test, and chi-squared for statistical drift, plus evidently and nannyml for automated reports. Use when monitoring a deployed model or comparing training vs production data distributions.

0
installs
▌
Autoexperiment · damionrashford bundle
Autonomous time-budget experiment loop. Modify a training script, train for a fixed wall-clock budget, evaluate, record, repeat. Inspired by karpathy/autoresearch. Use for overnight architecture search, systematic hyperparameter sweeps, or any iterative model improvement workflow.

0
installs
▌
Claude Code · damionrashford bundle
Comprehensive Claude Code knowledge base — plugins, hooks, skills, agents, MCP, channels, headless mode, permissions, settings, and all extensibility features. Use when building, configuring, debugging, or extending Claude Code.

0
installs
▌
Context Engineering · damionrashford bundle
Context engineering for building production LLM applications: context window management, degradation patterns, optimization strategies, memory system selection, multi-agent architecture, filesystem context patterns, and tool design principles. Use when building LLM apps, RAG pipelines, AI agents, multi-agent systems, or when designing memory, tool APIs, or context strategies for any language model application.

0
installs
▌
Vfx Usd · damionrashford bundle
Author and inspect Pixar Universal Scene Description (USD) files: usdcat (print/convert between .usda ASCII / .usdc crate binary / .usdz package), usdview (interactive Qt viewer), usdedit (round-trip edit via ASCII), usdzip (create/inspect .usdz AR packages), usdrecord (offline Hydra render to image sequence), usdresolve (asset path resolution), usdtree (stage hierarchy), usdchecker (validate schema + packaging), usddiff (structural diff), usdstitch / usdstitchclips (value-clip assembly), usdGenSchema (generate schema bindings). Core concepts: Stage, Layer, Prim, Attribute, Relationship, Composition Arcs (sublayer/reference/payload/inherit/specialize/variantSet - LIVRPS strength ordering). Schemas: UsdGeom, UsdLux, UsdShade, UsdSkel, UsdPhysics, UsdMedia, UsdRender, UsdVol, UsdUI. Docs at openusd.org/release/. Use when the user asks to work with USD files, convert between USD flavors, render a USD scene, validate USD for Apple AR delivery (.usdz), or author USD programmatically.

0
installs
▌
Media Sd · damionrashford bundle
Open-source AI image generation via ComfyUI (GPL-3.0, node-based runner) with STRICTLY permissive-license models: FLUX.1 [schnell] (Apache 2.0, Black Forest Labs fastest high-quality 4-step distilled model), Kolors (Apache 2.0, Kuaishou photorealistic diffusion), Sana (Apache 2.0, NVIDIA efficient DiT that runs on ~12GB VRAM), Lumina-Next (Apache 2.0, Shanghai AI Lab high-resolution), HunyuanDiT (Tencent License 2.0, commercial-permissive with a 100M-MAU cap), PixArt-Sigma. Text-to-image, image-to-image, ControlNet conditioning, LoRA adapters, ComfyUI node-graph workflows, HuggingFace diffusers pipeline. Use when the user asks to generate AI images, do text-to-image, create AI art, build or run a ComfyUI workflow, apply ControlNet, stack LoRAs, run a local diffusion server, use FLUX-schnell, use Kolors, use Sana, use Lumina, use HunyuanDiT, use PixArt, or specifically asks for OSI-open / Apache-licensed / commercial-safe image models.

0
installs
▌
Vfx Oiio · damionrashford bundle
VFX-grade image processing with OpenImageIO: oiiotool (stack-based Swiss Army knife - load/save, resize/crop/rotate/blur, metadata, compositing, color management via OCIO, deep images), iconvert (format conversion), iinfo (metadata dump), igrep (search metadata), idiff (perceptual diff), maketx (build tiled MIP-map textures for renderers), iv (GUI viewer). Handles OpenEXR, TIFF, DPX, Cineon, JPEG, JPEG 2000, JPEG XL, HEIC/HEIF/AVIF, PNG, BMP, RAW (LibRaw), FITS, PSD, WebP, PNM, Targa, IFF, SGI, Radiance HDR, GIF, DDS, Field3D, OpenVDB, Ptex. Direct OCIO integration (--colorconvert, --ociolook, --ociodisplay, --ociofiletransform). Docs at openimageio.readthedocs.io. Use when the user asks to convert image formats at VFX scale, apply color management, build MIP-map textures, read DPX/Cineon/EXR/OpenVDB, do deep compositing, or batch-process imagery with oiiotool.

0
installs
▌
Cv Opencv · damionrashford bundle
Computer vision on images + video with OpenCV (docs.opencv.org/4.x/): core (Mat / ndarray, linalg), imgproc (filtering, morphology, geometric transforms, color conv, histograms, contours), imgcodecs (imread/imwrite — PNG, JPEG, TIFF, WebP, EXR), videoio (VideoCapture / VideoWriter — FFMPEG, GStreamer, V4L2, AVFoundation, MSMF backends), calib3d (camera calibration, stereo, solvePnP, homography), features2d (ORB, AKAZE, BRISK, KAZE, SIFT), objdetect (FaceDetectorYN, FaceRecognizerSF, HOG, ArUco, QRCode), dnn (ONNX/TF/Caffe/Darknet, CUDA + OpenVINO + Vulkan backends, model zoo at github.com/opencv/opencv_zoo), photo (inpainting, denoising, HDR Debevec/Robertson), stitching (panorama), video (optical flow Farneback/LK/DIS, BackgroundSubtractorMOG2/KNN, tracking KCF/CSRT/MIL/Nano/Vit/DaSiamRPN). Python-first via cv2. Use when the user asks to detect faces, track objects, run YOLO inference, capture + process webcam frames, calibrate a camera, stitch a panorama, or use OpenCV from Python/C++.

0
installs
▌
Media Dmx · damionrashford bundle
Stage lighting protocols: DMX512-A (ANSI E1.11 serial, 250 kbps RS-485, 512 slots per universe, RDM E1.20 bidirectional config), Art-Net 4 (UDP port 6454, ASCII Art-Net header + 15-bit universe addressing from Artistic Licence), sACN / E1.31 (UDP multicast 239.255.X.Y port 5568 with universe sync + priority), Open Lighting Architecture (OLA — olad daemon, ola_streaming_client, ola_recorder, ola_dmxconsole, ola_patch, ola_rdm_get/set, ola_artnet, ola_e131, ola_usbpro for Enttec USB Pro), Enttec Open DMX + USB Pro serial framing. Use when the user asks to control stage lights, send DMX, drive an Art-Net node, stream sACN, discover RDM devices, patch a lighting rig from code, send a show cue, record/playback a DMX show, or bridge OSC/MIDI to lighting.

0
installs
▌
Media Osc · damionrashford bundle
Open Sound Control (OSC) wire protocol: OSC 1.0 and 1.1 spec, packet layout (address pattern + comma-prefixed type tag + 4-byte-aligned args), OSC bundles with NTP timetags, address-pattern matching (?/*/[]/{}), OSC over UDP/TCP/SLIP, liblo CLIs (oscsend, oscdump), python-osc library, Stanford CCRMA spec home. Use when the user asks to send an OSC message, dump incoming OSC packets, write a Python OSC client or server, bridge OSC to MIDI or DMX, control a visualizer/DAW/livecoding environment (SuperCollider/TouchDesigner/Max/Resolume) over OSC, build a show-control system, or parse the OSC wire format.

0
installs
▌
Media Sox · damionrashford bundle
Audio processing with SoX (Swiss Army Knife of audio): format conversion, trim/cut, pad, reverse, speed/pitch change, fade, silence detection and removal, noise profile + reduction, synth tones, channel ops, dither. Use when the user asks to process audio with SoX, trim silence, remove noise with sox noise-profile/noisered (better than ffmpeg afftdn for some cases), generate synth audio, apply a sox effects chain, or convert audio formats with precise dither control.

0
installs
▌
Media Svd · damionrashford bundle
Open-source AI video generation with STRICTLY permissive-license models: LTX-Video (Apache 2.0, Lightricks realtime-ish text-to-video), CogVideoX-2B / -5B (Apache 2.0, Tsinghua + Zhipu, 2024), Mochi-1 (Apache 2.0, Genmo), AnimateDiff (Apache 2.0, motion module that animates any diffusion image model), Wan-Video (Apache 2.0, Alibaba 2025 high quality). Text-to-video (t2v), image-to-video (i2v), motion-controlled animation via AnimateDiff, ComfyUI workflow integration. Use when the user asks to generate a video from a text prompt, animate a still image, make a short AI clip, run CogVideoX, use LTX-Video, use Mochi, use Wan-Video, use AnimateDiff, or specifically asks for Apache-licensed / OSI-open / commercial-safe video generation models. Does NOT include Stable Video Diffusion (SVD OpenRAIL-M NC), Sora, Runway, Kling — all proprietary or non-commercial. HunyuanVideo is mentioned but flagged for its commercial cap.

0
installs
▌
Media Tag · damionrashford bundle
AI image and video tagging, captioning, zero-shot classification, and semantic search with open-source + commercial-safe vision-language models: CLIP (MIT, OpenAI, zero-shot classification + text-image similarity, ViT-B/32 to ViT-L/14), SigLIP (Apache 2.0, Google, sigmoid loss, outperforms CLIP on most benchmarks), BLIP-2 (BSD-3-Clause, Salesforce, strong image captioning), LLaVA / LLaVA-NeXT / LLaVA-OneVision (Apache 2.0, open vision-language model for detailed description + VQA + video). Use when the user asks to auto-tag photos, generate alt text, caption an image, describe a video scene-by-scene, build a CLIP semantic-search index, classify images by free-form text labels ("cat vs dog vs car"), bulk-label a folder, generate WCAG alt text, do zero-shot classification, ask a VLM to describe what is happening in a video, or pick between CLIP/SigLIP/BLIP-2/LLaVA.

0
installs
▌
Ndi Tools · damionrashford bundle
Use NDI SDK tools and CLIs (Vizrt/NewTek NDI): NDI Send, NDI Find, NDI Recorder, NDI Studio Monitor, NDI Bridge, NDI Discovery Service, NDI Benchmark, DistroAV (OBS plugin formerly obs-ndi). Source SRGB/HDR video over LAN via mDNS discovery + SpeedHQ codec on TCP/UDP 5960+, redistribute with Advanced SDK routing, integrate with OBS/ffmpeg/GStreamer plugins. Use when the user asks to send an NDI stream, receive NDI, find NDI sources on the network, record NDI to disk, bridge NDI over WAN, install NDI Tools, use DistroAV in OBS, or work with NDI sources from the command line.

0
installs
▌
Ptz Onvif · damionrashford bundle
Discover and control ONVIF IP cameras via SOAP/XML with WS-Security UsernameToken digest: onvif-util (libonvif github.com/sr99622/libonvif), onvif-cli (github.com/gardere/onvif-cli), python-onvif-zeep (PyPI onvif-zeep), onvif_control (bash + WS-Security), gonvif (Go). WS-Discovery multicast to 239.255.255.250:3702 finds ProbeMatch responses. Services: Device Management, Media (RTSP URIs), PTZ, Imaging, Events, Recording/Search/Replay, Analytics. Profiles: S (deprecated 2027), T (H.264/H.265 + metadata), G (recording), M (analytics), A/C/D (access). Use when the user asks to discover ONVIF cameras, get an RTSP stream URL, move a PTZ via ONVIF (ContinuousMove/AbsoluteMove/GotoPreset), grab a snapshot, authenticate with UsernameToken digest, or query a camera's ONVIF capabilities.

0
installs
▌
Ptz Visca · damionrashford bundle
Control PTZ cameras with Sony VISCA protocol (RS-232/485 serial 9600/38400 8N1, or UDP:52381 with 8-byte payload header): pan/tilt/zoom/focus/exposure/WB commands, libvisca + libvisca-ip, python-visca, pyvisca, pysca, visca-over-ip. Supported cameras: Sony (BRC/SRG/FR7/FCB modules), PTZOptics, AVer Pro-AV, Panasonic AW-series partial, Bolin, Avonic, Lumens, Marshall, Canon CR-N subset. Use when the user asks to drive a PTZ camera, move a PTZOptics/Sony cam, send pan-tilt over IP, control a camera preset, zoom/focus from a script, build a VISCA packet, or integrate a PTZ rig into OBS/vMix.

0
installs
▌
Audio Jack · damionrashford bundle
Route professional low-latency audio with JACK Audio Connection Kit (jackaudio.org): jackd server (ALSA/CoreAudio/PortAudio/ASIO backends), jack_control (D-Bus JACK2 config), jack_lsp (list ports/connections), jack_connect/jack_disconnect (manage links), jack_cpu_load, jack_samplerate, jack_bufsize (runtime period size), jack_transport, jack_rec (multi-channel WAV recording), jack_iodelay (round-trip latency), jack_wait, jack_midi_dump. JACK1 C maintenance vs JACK2 C++ multicore. Modern Linux swaps jackd for PipeWire's libjack shim — same client API. JackTrip for uncompressed multichannel UDP over the Internet. Use when the user asks to run a JACK server, connect audio clients, measure roundtrip latency, record from JACK ports, set JACK period size, or bridge JACK over the network with JackTrip.

0
installs
▌
Ffmpeg Drm · damionrashford bundle
DRM and media encryption with ffmpeg: HLS AES-128 (-hls_key_info_file, -hls_enc, key rotation), HLS SAMPLE-AES, MPEG-DASH Common Encryption (CENC) with cenc_mp4 / cbcs schemes, ClearKey, fmp4 encrypted segments, cryptor protocol for playback. Use when the user asks to encrypt an HLS stream, set up AES-128 HLS, do sample-AES, package CENC DASH, rotate HLS keys, generate a key info file, protect VOD content, or configure ClearKey signaling.

0
installs
▌
Media Gpac · damionrashford bundle
Advanced MP4 / ISOBMFF authoring and diagnostics with GPAC (MP4Box, gpac): fragmented MP4, DASH+CMAF packaging, MP4 surgery (extract, dump, edit boxes), CENC encryption, sidx injection, sub-track management, raw track export, BIFS/LASeR, ROUTE/DVB-MABR. Use when the user asks to use MP4Box, fragment a MP4, extract tracks by ID, dump MP4 box structure, inject sidx indexing, CMAF-package for DASH, repair MP4 that ffmpeg can't, or do advanced ISO-BMFF surgery.

0
installs
▌
Media Midi · damionrashford bundle
MIDI 1.0 and 2.0 wire protocol, control surfaces, and SMF file authoring: sendmidi/receivemidi (macOS/Linux/Windows), ALSA amidi/aconnect/aplaymidi/arecordmidi/aseqdump (Linux), mido and python-rtmidi (cross-platform Python), SMF chunks (MThd/MTrk with VLQ delta times), Universal MIDI Packet (UMP) groups for MIDI 2.0, MIDI-CI negotiation, standard CC numbers, General MIDI program tables, sysex framing. Use when the user asks to send MIDI messages, trigger notes from a script, route a control surface, parse or write a .mid file, bridge MIDI over USB/BT, work with UMP packets, run MIDI-CI property exchange, or speak MIDI to a synth/DAW from the CLI.

0
installs
▌
Obs Config · damionrashford bundle
Install and configure OBS Studio programmatically: install via brew cask / winget / Flatpak / apt, author profiles (basic.ini, streamEncoder.json, recordEncoder.json), author scene collections (scenes JSON), manage global.ini, set defaults for encoder / output / audio / hotkeys, cross-platform config paths. Use when the user asks to install OBS, set up an OBS profile, create a scene collection from code, configure OBS defaults without the GUI, edit basic.ini, manage multiple OBS profiles, or script a fresh OBS install with known-good settings.

0
installs
▌
Ffmpeg Ivtc · damionrashford bundle
Inverse telecine, deinterlacing variants, and frame-rate conversion with ffmpeg: fieldmatch, decimate, pullup, detelecine, mpdecimate, dejudder, w3fdif, separatefields, weave, tinterlace, kerndeint, estdif, phase, repeatfields, vfrdet, fieldhint, fieldorder, il, mcdeint, telecine. Use when the user asks to IVTC a telecined file, convert 29.97i to 23.976p, reverse 3:2 pulldown, fix interlaced broadcast content, detect duplicate fields, convert PAL to NTSC frame rates, or clean up mixed interlacing.

0
installs
▌
Ffmpeg Whip · damionrashford bundle
WebRTC egress with ffmpeg whip muxer (FFmpeg 7.0+): publish live AV to a WHIP (WebRTC-HTTP Ingestion Protocol) endpoint, low-latency sub-second delivery, encoder constraints (H.264 baseline/main, Opus audio), ICE/STUN handling. Use when the user asks to push to WHIP, stream via WebRTC, publish to a WebRTC ingest endpoint, send sub-second live to Cloudflare/Mux/Millicast, output to a WHIP URL, or do browser-playable live streaming without HLS/DASH.

0
installs
▌
Media Batch · damionrashford bundle
Batch ffmpeg and media processing at scale with GNU parallel, xargs, and shell patterns: parallel transcode fleets, shard jobs across cores, log aggregation, retry logic, idempotent pipelines, find + parallel recipes, progress reporting. Use when the user asks to batch transcode a folder, parallelize ffmpeg jobs, use GNU parallel with ffmpeg, build a media processing pipeline at scale, process a large media library, or scale ffmpeg to many cores with safe job isolation.

0
installs
▌
Media Depth · damionrashford bundle
Monocular depth estimation with open-source + commercial-safe models: Depth-Anything v2 (Apache 2.0, TikTok/ByteDance 2024, current SOTA small/base/large) via HuggingFace transformers, MiDaS v3.1 (MIT, Intel ISL classic with DPT/BEiT/Swin backbones). Extract depth maps from a single image or video, enable 2.5D parallax / Ken Burns effects, drive Blender/Unreal Z-depth passes, replace LiDAR capture, convert 2D → stereo 3D via depth-driven parallax. Use when the user asks to estimate depth, compute a depth map, run Depth Anything, run MiDaS, get a disparity map, animate a 2.5D parallax shot from a still, build a stereo pair from a 2D photo, extract Z-depth for compositing, drive a VFX pipeline with monocular depth, convert 2D video to side-by-side 3D, or produce a depth video for the Looking Glass / Blender camera tracker.

0
installs
▌
Media Matte · damionrashford bundle
AI background removal and matting for stills + video with open-source + commercial-safe models: rembg (MIT, bundles u2net / isnet / sam backends), BiRefNet (MIT, 2024 SOTA bilateral reference segmentation), RMBG-2.0 (Apache 2.0, briaai's 2025 model — note v2.0 is Apache, v1.4 was NC and is NOT used here), RobustVideoMatting / RVM (GPL-3.0, temporal-coherent video matting). No green screen required — neural nets predict alpha on arbitrary backgrounds. Use when the user asks to remove a background from an image or video, extract a subject without a greenscreen, auto-matte a person, cut out a product photo, replace a video background, create a transparent PNG from a photo, generate an alpha channel for compositing, or do video-coherent matting on moving subjects.

0
installs
▌
Media Shaka · damionrashford bundle
Commercial DRM packaging with Shaka Packager (packager): Widevine (Common Encryption for DASH+HLS), PlayReady, FairPlay, multi-DRM, ClearKey, key rotation, CMAF packaging, EMSG markers, SCTE-35 ad signaling. Use when the user asks to package Widevine DRM, build FairPlay HLS, do multi-DRM DASH+HLS CMAF, integrate with a Widevine/PlayReady license server, ship studio-grade DRM-protected content, or package CENC with PSSH boxes.

0
installs
▌
Media Ytdlp · damionrashford bundle
Download videos, audio, playlists, and channels from YouTube, Twitch, Twitter/X, TikTok, Instagram, Vimeo, Facebook, and 1000+ other sites using yt-dlp. Use when the user asks to download a YouTube video, rip a playlist, grab a Twitch VOD, download audio as MP3, extract subtitles from a web video, get best-quality stream, download channel uploads, archive web video, or fetch media from any streaming site.

0
installs
▌
Obs Plugins · damionrashford bundle
OBS plugin authoring and ecosystem: scaffold a new C++ plugin from obs-plugintemplate (CMake, cross-platform GitHub Actions CI), register obs_source_info / obs_output_info / obs_encoder_info / obs_service_info, implement obs_module_load / obs_module_unload with OBS_DECLARE_MODULE, plus install / configure common community plugins (StreamFX, Advanced Scene Switcher, Move, NDI, Source Record, Backtrack, obs-websocket). Use when the user asks to write an OBS plugin, build a custom source / output / encoder, use obs-plugintemplate, install a specific OBS plugin, or set up the OBS plugin build environment.

0
installs
▌
Vfx Openexr · damionrashford bundle
Work with OpenEXR VFX image format: exrheader (dump header attributes), exrinfo (concise info), exrmaketiled (scanline to tiled for MIP-map access), exrenvmap (latlong / cube environment-map conversion), exrmakepreview (embed thumbnail), exrmultipart (split/combine multi-part), exrmultiview (split/combine stereo multi-view), exrstdattr (read/write standard attributes), exrcheck (validate), exr2aces (convert to ACES-compliant EXR), exrmanifest (deep ID manifest), exrmetrics. Scanline vs tiled, multi-part (EXR 2+), deep images (deepscanline/deeptile), chromaticities, compression types (NONE/RLE/ZIPS/ZIP/PIZ/PXR24/B44/B44A/DWAA/DWAB/HTJ2K). EXR 2.x multi-part + deep data + DWAA/DWAB; EXR 3.x rewritten OpenEXRCore C API (thread-safe), Imath split out. Docs at openexr.com. Use when the user asks to inspect an EXR, convert EXR to tiled or multi-part, handle deep compositing data, embed thumbnails, or validate a VFX EXR pipeline.

0
installs
▌
Webrtc Pion · damionrashford bundle
Build Go WebRTC applications with Pion (pion/webrtc/v4 — pkg.go.dev): primitives including PeerConnection, MediaEngine, SettingEngine, RTPSender, RTPReceiver, RTPTransceiver, DataChannel, TrackLocalStaticRTP, TrackLocalStaticSample, TrackRemote, ICEAgent, DTLSTransport, SCTPTransport, SRTPSession, Interceptor pipeline, StatsReport. Runnable examples: broadcast (minimal 1-to-N SFU), sfu-ws (WebSocket-signaled SFU), simulcast, play-from-disk, save-to-disk, save-to-webm, data-channels, whip-whep, ice-tcp, ice-single-port, insertable-streams, rtp-forwarder, rtp-to-webrtc. Sibling libs: pion/rtp, pion/rtcp, pion/sdp/v3, pion/ice/v3, pion/dtls/v3, pion/srtp/v3, pion/turn/v4, pion/mediadevices. SFUs built on Pion: ion-sfu, LiveKit, Galene. Use when the user asks to write a WebRTC server in Go, build an SFU from scratch, implement WHIP/WHEP endpoints, save WebRTC tracks to disk, or prototype a Pion pipeline.

0
installs
▌
Webrtc Spec · damionrashford bundle
Search and fetch WebRTC specs from W3C and IETF: W3C WebRTC 1.0 (RTCPeerConnection, RTCRtpSender/Receiver/Transceiver, RTCDataChannel, RTCDtlsTransport, RTCIceTransport, RTCSctpTransport, RTCStatsReport), WebRTC-Extensions (simulcast, encoded transforms), WebRTC Stats, Media Capture and Streams (getUserMedia), Screen Capture, WebCodecs, WebTransport. IETF RFCs: 8825 (overview), 8826/8827/8828 (security), 8829+9429 (JSEP), 8831/8832 (data channels), 8834 (RTP in WebRTC), 8835 (transports), 8836 (congestion), 8837 (DSCP), 8866 (SDP, obsoletes 4566), 8445 (ICE), 8489 (STUN), 8656 (TURN), 5764 (DTLS-SRTP), 3711 (SRTP), 3550 (RTP), 6184 (H.264), 7798 (HEVC), 7741 (VP8), 7587 (Opus), 9725 (WHIP), draft-ietf-wish-whep (WHEP). Use when the user asks to look up an SDP attribute, verify an ICE behavior, check an RFC number for WebRTC, or find the canonical spec for a WebRTC feature.

0
installs
▌
Audio Wasapi · damionrashford bundle
Manipulate Windows audio via WASAPI (learn.microsoft.com/coreaudio): SoundVolumeView + svcl.exe (NirSoft — set default device, per-app volumes, save/load profiles), AudioDeviceCmdlets PowerShell module (Get-AudioDevice, Set-AudioDevice, Get-AudioDevicePlaybackMute), nircmd setdefaultsounddevice. Shared mode (Windows engine resamples all streams to endpoint fixed format) vs Exclusive mode (bit-perfect, audiophile, ~sub-3ms latency with IAudioClient3 + event-driven callbacks). WASAPI then MMDevice then Audio Engine (audiodg.exe) then WDM/KS. ASIO is Steinberg's parallel stack bypassing Windows audio. Virtual audio devices: VB-Audio Virtual Cable, VoiceMeeter/Banana/Potato. Use when the user asks to change Windows default audio device, route app audio, use VoiceMeeter, install VB-Cable, set a specific device from PowerShell, or enable exclusive-mode low-latency output.

0
installs
▌
Cv Mediapipe · damionrashford bundle
Google MediaPipe Tasks API (current supported, NOT legacy mediapipe.solutions): Vision Tasks (Face Detector, Face Landmarker, Face Stylizer, Hand Landmarker, Gesture Recognizer, Pose Landmarker, Holistic Landmarker, Object Detector, Image Classifier, Image Segmenter, Interactive Segmenter, Image Embedder, Image Generator), Audio Tasks (Audio Classifier), Text Tasks (Text Classifier, Text Embedder, Language Detector), GenAI Tasks (LLM Inference — on-device Gemma/Phi-2/Falcon/StableLM). Three run modes: IMAGE, VIDEO, LIVE_STREAM (async). Python: mediapipe.tasks.python.vision/audio/text/genai. Docs at ai.google.dev/edge/mediapipe/solutions. Model Maker for transfer learning. Use when the user asks to detect pose/face/hand landmarks, classify an image, run a body-pose model, segment people, recognize gestures, do on-device LLM inference via MediaPipe, or build a mobile/embedded CV pipeline.

0
installs
▌
Ffmpeg Probe · damionrashford bundle
Inspect media files with ffprobe: format, streams, codecs, duration, bitrate, resolution, fps, color space, channel layout, metadata, chapters, and per-frame/packet analysis, output as JSON/CSV/INI/XML. Use when the user asks to inspect a video, check codec, get resolution/bitrate/fps/duration, detect HDR, list streams/tracks, dump metadata, count frames, find keyframes, get container info, or pipe media info into a pipeline.

0
installs
▌
Ffmpeg Synth · damionrashford bundle
Generate synthetic test media with ffmpeg lavfi sources: testsrc, testsrc2, smptebars, smptehdbars, rgbtestsrc, yuvtestsrc, allyuv, allrgb, colorchecker, color (solid), mandelbrot, cellauto, life, gradients, zoneplate, sine tone, anullsrc, anoisesrc. Use when the user asks to generate test bars and tone, create a calibration clip, make SMPTE color bars, generate a sine tone, output silence, create a test video, produce a solid-color background, generate 1 kHz reference tone, or build synthetic assets for pipeline testing.

0
installs
▌
Media Demucs · damionrashford bundle
AI audio source separation with Demucs and Spleeter: isolate vocals / drums / bass / other stems from mixed audio, karaoke track extraction, music remixing prep, Hybrid Transformer Demucs (htdemucs), 2-stem and 4-stem and 6-stem models, GPU-accelerated. Use when the user asks to separate vocals from a song, extract drums/bass/other stems, make a karaoke track, isolate stems with AI, remove music from speech, prep stems for remixing, or use Demucs.

0
installs
▌
Media Ocr AI · damionrashford bundle
Modern AI OCR with open-source + commercial-safe models: PaddleOCR (Apache 2.0, Baidu, 80+ languages, layout analysis, tables), EasyOCR (Apache 2.0, JaidedAI, 80+ languages, easiest install), Tesseract 5 (Apache 2.0, mature LSTM backend, 100+ languages), TrOCR (MIT, Microsoft transformer, the only one that really handles cursive handwriting). Extract text from images and PDFs, structured layout (headers/paragraphs/tables), multilingual documents, handwriting, receipts, invoices, screenshots, scanned forms, signage, whiteboards. Use when the user asks to OCR an image, read text from a picture, extract text from a scanned PDF, parse a receipt or invoice, detect table structure, transcribe handwriting, process a multilingual document (English/Japanese/Chinese/Arabic/etc.), handle CJK or RTL scripts, or pick between PaddleOCR vs EasyOCR vs Tesseract vs TrOCR.

0
installs
▌
Media Tts AI · damionrashford bundle
Modern AI text-to-speech + voice cloning with open-source + commercial-safe models: Kokoro (Apache 2.0, 82M params, realtime on CPU, top TTS Arena ranking, 8+ languages), OpenVoice v2 (MIT, voice cloning), CosyVoice 2 (Apache 2.0, 2025 SOTA cloning from Alibaba), Chatterbox (MIT, Resemble AI zero-shot cloning + emotion control), Bark (MIT, expressive + non-verbal sounds like laughs/sighs), Orpheus (Apache 2.0, Canopy AI Llama-3-based expressive), Piper (MIT, fastest embedded TTS), StyleTTS2 (MIT, Kokoro's architecture base), Parler-TTS (Apache 2.0, prompt-controlled voice). Use when the user asks to synthesize speech, clone a voice, read text aloud, generate audiobook narration, add TTS to an app, replace Core Audio say with better quality, or create AI voiceovers.

0
installs
▌
Otio Convert · damionrashford bundle
Convert and manipulate editorial timelines with OpenTimelineIO (OTIO) CLIs: otioconvert (format-to-format: EDL/FCP7-XML/FCPXML/AAF/OTIO-JSON), otiocat (concatenate/print), otiostat (timeline statistics), otiotool (filter/edit/rebuild timelines), otiopluginfo (list installed adapters), otioview (Qt viewer). Round-trip between Premiere Pro, Final Cut Pro 7/X, Avid Media Composer, DaVinci Resolve, GStreamer Editing Services. Use when the user asks to convert a Final Cut XML to Premiere, read an AAF, author an EDL, translate between NLE formats, filter an OTIO timeline programmatically, extract timeline stats, or view a timeline.

0
installs
▌
Workflow Hdr · damionrashford
End-to-end HDR authoring — HDR10 (static MDC + MaxCLL/MaxFALL), HDR10+ dynamic metadata JSON, Dolby Vision profiles 5/7/8.1/8.4, HLG, PQ↔HLG conversion, SDR↔HDR tone-mapping (hable/mobius/reinhard/bt2390/aces), dovi_tool + hdr10plus_tool orchestration, and multi-format dual-delivery. Use when the user says "HDR10+", "Dolby Vision", "PQ to HLG", "tone-map to SDR", "ACES RRT", "HLG broadcast", "DV profile 7 to 8.1", "YouTube HDR", or anything HDR-color-pipeline.

0
installs
▌
Ffmpeg 360 3d · damionrashford bundle
360° / VR and stereoscopic 3D video with ffmpeg: v360 filter (equirectangular, cubemap 3x2/6x1/1x6, fisheye, flat, hequirect, dfisheye, cylindrical, perspective, barrel, sinusoidal, half_equirectangular, stereographic, mercator, ball, hammer, pannini, eac, c3x2/c6x1/c1x6, rfish), stereo3d filter (SBS ↔ TAB ↔ interlaced ↔ anaglyph), framepack, spatial audio placeholder. Use when the user asks to convert 360 video projections, equirectangular to cubemap, unwrap fisheye, convert side-by-side 3D to top-bottom, make anaglyph 3D, reproject 360 video, or handle VR180/VR360 content.

0
installs
▌
Ffmpeg Detect · damionrashford bundle
Detect-and-act workflows with ffmpeg analysis filters: cropdetect (autocrop black bars), silencedetect, blackdetect, freezedetect, blurdetect, blockdetect, scdet (scene-change detection), idet (interlace detection), signalstats broadcast QC, readeia608 (CEA-608 caption read), readvitc (VITC timecode read). Use when the user asks to autocrop black bars, detect silences, find black frames, detect scene cuts, check if video is interlaced, find freeze frames, auto-split on scene changes, read embedded timecode, or parse detection output into cut points.

0
installs
▌
Hdr Dovi Tool · damionrashford bundle
Author Dolby Vision RPU dynamic metadata with dovi_tool: info (parse RPU + per-frame JSON), generate (RPU from XML/JSON/HDR10+/madVR), editor (JSON-driven edits), export (RPU to JSON / scene markers / L5), plot (level graphs), convert (profile 7 to 8.1), demux (BL+EL split), mux (BL+EL recombine), extract-rpu (out of HEVC Annex-B), inject-rpu (into HEVC Annex-B), remove (strip DV NAL). Plus an end-to-end pipeline subcommand that chains ffmpeg hevc_mp4toannexb + extract-rpu + inject-rpu + mkvmerge/MP4Box. Supports DV profiles 4, 5, 7, 8.1, 8.4. Use when the user asks to extract or inject a Dolby Vision RPU, convert DV profile 7 to 8.1, edit a DV metadata JSON, or repackage HEVC with DV.

0
installs
▌
Media Lipsync · damionrashford bundle
Open-source AI lip-sync and talking-head animation with STRICTLY permissive-license models: LivePortrait (MIT, Kuaishou 2024, drives FACIAL motion — head pose, expression, lip-region — of a single still image from a driving audio OR a driving video of a real face), LatentSync (Apache 2.0, ByteDance 2025, pure lip-region diffusion that re-syncs an existing video's mouth to a new audio track). Use when the user asks to lip-sync a video to new audio, dub a clip and fix the lip alignment, animate a photo with speech, turn a still portrait into a talking head, sync mouth movement, use LivePortrait, use LatentSync. Does NOT include Wav2Lip (research-only derivatives), SadTalker (weights NC-derived), HeyGen / D-ID / Synthesia (commercial APIs) — all excluded.

0
installs
▌
Media Moviepy · damionrashford bundle
Programmatic video editing in Python with MoviePy: build videos from clips, text overlays, transitions, compositing, audio manipulation, frame-by-frame custom effects via numpy, concatenate / subclip / fx / resize / rotate. Use when the user asks to build a video programmatically, use MoviePy, make a video from Python code, do numpy frame manipulation, build a template video pipeline in Python, or generate videos dynamically from data.

0
installs
▌
Media Upscale · damionrashford bundle
AI super-resolution for images and video beyond ffmpeg's outdated built-in DNN models (SRCNN 2014 / ESPCN 2016 / EDSR 2017). Open-source + commercial-safe only: Real-ESRGAN (BSD-3-Clause, the current default for photos/video), Real-CUGAN (MIT, anime-optimized), SwinIR (Apache 2.0, transformer-based), HAT (Apache 2.0, 2023 SOTA), GFPGAN (Apache 2.0, face restoration), waifu2x-ncnn-vulkan (MIT, classic anime), Upscayl (AGPL-3.0, GUI wrapper around Real-ESRGAN), chaiNNer (GPL-3.0, node pipeline for arbitrary models). Realistic 2x / 4x / 8x SR for photos, film scans, low-res archives, anime, screenshots, game textures. Use when the user asks to upscale an image, super-resolution a video, enhance an old photo, restore a face, upscale anime, rescale game textures, do AI upscaling, or when ffmpeg's built-in SRCNN/ESPCN/EDSR isn't good enough.

0
installs
▌
Media Whisper · damionrashford bundle
Speech-to-text transcription and subtitle generation with whisper.cpp and faster-whisper: extract spoken text from audio/video, generate SRT/VTT subtitles, translate speech to English, word-level timestamps, multilingual support, speaker diarization optional. Use when the user asks to transcribe a video, auto-generate subtitles from speech, create captions, translate a foreign-language clip to English, extract dialogue as text, build an ASR pipeline, or process podcast audio into a transcript.

0
installs
▌
Obs Scripting · damionrashford bundle
Write Python / Lua scripts that run inside OBS Studio: script lifecycle (script_load, script_unload, script_description, script_properties, script_defaults, script_update, script_save, script_tick), registering frontend event callbacks, hooking signals, accessing sources + scenes + filters from a script, using obspython / obslua bindings, building script UIs with obs_properties_t. Use when the user asks to write an OBS Python script, write an OBS Lua script, automate something inside OBS without a compiled plugin, add a script-side hotkey, build a tools-menu script, or hook OBS signals from Python.

0
installs
▌
Obs Websocket · damionrashford bundle
Remote-control a running OBS Studio instance via obs-websocket (WebSocket API, default port 4455): authenticate with SHA-256 challenge+salt, Identify handshake, start/stop streaming and recording, switch scenes, toggle sources and filters, set audio mixer levels, trigger replay buffer + virtual camera, subscribe to live events, send request batches. Use when the user asks to control OBS from a script, switch OBS scenes remotely, start or stop recording programmatically, automate a stream, send an obs-websocket request, subscribe to CurrentProgramSceneChanged events, connect to ws://host:4455, or build a browser/CLI OBS remote.

0
installs
▌
Audio Pipewire · damionrashford bundle
Route and introspect Linux audio/video/MIDI graphs with PipeWire: pw-cli (interactive object/module control), pw-dump (full graph JSON with --monitor), pw-link (list/create/destroy port links), pw-cat / pw-play / pw-record (playback+record), pw-top (real-time DSP load + xrun viewer), pw-metadata (shared metadata store), pw-loopback (source/sink bridges), pw-midiplay/pw-midirecord, pw-jack (JACK client compat shim), pw-mon, pw-profiler. WirePlumber session manager handles routing/defaults/profiles. Replaces PulseAudio (via pipewire-pulse) and JACK (via libjack.so shim) simultaneously. Use when the user asks to route Linux audio, link two apps, list audio devices on Linux, create a loopback, record system audio, monitor the audio graph, or set up a virtual audio device on modern Linux.

0
installs
▌
Decklink Tools · damionrashford bundle
Capture and play back SDI/HDMI video via Blackmagic DeckLink hardware: ffmpeg decklink indev/outdev (-f decklink -list_devices 1, -f decklink -list_formats 1, -f decklink -i 'DeckLink Mini Recorder 4K', -f decklink 'DeckLink Mini Monitor'), SDK Samples (CapturePreview, LoopThroughPreview, SignalGenerator test-pattern output, StatusMonitor, DeviceList, TestPattern, 3DVideoFrames, StreamOperations, FrameServer, AudioMixer). Pixel formats (uyvy422 = bmdFormat8BitYUV, v210 = bmdFormat10BitYUV), four-CC display modes (Hp60 = 1080p60, 4k60 = UHD60). Requires Desktop Video driver + ffmpeg built --enable-decklink. Use when the user asks to capture from DeckLink, output to SDI, ingest HDMI via Blackmagic, list DeckLink devices/formats, generate test patterns out SDI, or install the DeckLink SDK.

0
installs
▌
Ffmpeg Capture · damionrashford bundle
Record from capture devices with ffmpeg: screen/desktop (avfoundation on macOS, gdigrab/dshow on Windows, x11grab/kmsgrab on Linux), webcam (avfoundation/dshow/v4l2), microphone, system audio, and list available devices. Use when the user asks to record the screen, capture desktop, record webcam, record microphone, screencast, grab a region of the screen, capture system audio, or list input devices.

0
installs
▌
Ffmpeg Hwaccel · damionrashford bundle
Use hardware acceleration with ffmpeg: NVIDIA NVENC/NVDEC/CUDA, Intel Quick Sync (QSV), VA-API (Linux Intel/AMD), VideoToolbox (macOS Apple Silicon/Intel), AMD AMF (Windows), Vulkan, plus hwupload/hwdownload filters for full-GPU pipelines. Use when the user asks to encode with GPU, use NVENC, use QSV, use VideoToolbox on Mac, use VAAPI, accelerate ffmpeg with GPU, speed up transcoding, or do zero-copy GPU-to-GPU filtering.

0
installs
▌
Ffmpeg Mxf Imf · damionrashford bundle
Professional broadcast and film delivery with ffmpeg: MXF (SMPTE 377M OP1a/OP-Atom) mux/demux, IMF (Interoperable Master Format SMPTE 2067) for Netflix/studio delivery, GXF, broadcast timecode (drop-frame / non-drop-frame), SMPTE 2022 / SMPTE 2110 IP essences, XDCAM profiles. Use when the user asks to work with MXF files, author IMF packages, handle broadcast-exchange containers, deal with SMPTE timecode, read MXF operational patterns, do IMP delivery to Netflix, or do professional post-production mastering.

0
installs
▌
Ffmpeg Quality · damionrashford bundle
Measure encode quality with ffmpeg reference-vs-distorted filters: libvmaf (Netflix VMAF), psnr, ssim, vmafmotion, identity, msad, blockdetect, blurdetect. Use when the user asks to measure VMAF, run VMAF scoring, compute PSNR, compute SSIM, compare encoded vs source quality, benchmark a codec, find the best CRF for a target VMAF, verify encoder output, or QA a transcoded file against the original.

0
installs
▌
Gphoto2 Tether · damionrashford bundle
Tether DSLR / mirrorless cameras via USB or PTP/IP using gphoto2 (gphoto.org) + libgphoto2: --auto-detect, --list-cameras, --capture-image, --capture-image-and-download, --capture-preview (live-view JPEG), --capture-movie, --capture-tethered (wait for shutter release), --list-files, --get-file, --get-all-files, --summary, --list-config / --get-config / --set-config (shutterspeed, aperture/f-number, ISO, focusmode, autofocusdrive, manualfocusdrive, drivemode, batterylevel - key names vary per camera driver), --wait-event, --shell, --stdout (pipe mode). PTP/IP over Wi-Fi via ptpip:IP or ptpip:IP:PORT syntax. Supports Canon, Nikon, Sony, Fujifilm, Panasonic, Olympus, Pentax, Leica, Hasselblad and more (live list at gphoto.org/proj/libgphoto2/support.php). Use when the user asks to tether a DSLR, auto-capture from Python, bulk-download from a camera, remotely change aperture/ISO/shutter, drive live-view, build a photobooth/timelapse, or connect over PTP/IP.

0
installs
▌
Media Exiftool · damionrashford bundle
Read and write EXIF, IPTC, XMP, GPS, and maker-note metadata for photos and videos with ExifTool (exiftool -g -json -P -overwrite_original). Use when the user asks to read EXIF tags, edit photo metadata, strip GPS data from images, write IPTC keywords, set camera model, shift timestamps across a folder, copy metadata between files, write XMP sidecar files, or batch-rewrite metadata.

0
installs
▌
Media Musicgen · damionrashford bundle
Open-source AI music generation with permissive-license models: Riffusion (MIT, spectrogram-to-audio music from text), YuE (Apache 2.0, Chinese Academy 2025 full-song generation with vocals), Stable Audio Open (Stability community license, commercial up to 1M ARR). Text-to-music, genre-conditioned generation, full song with structure, continuation from existing audio, stem splits via media-demucs. Use when the user asks to generate music from text, create AI songs, make background music for video, generate a jingle, produce royalty-free music with open-source models, make a full song with vocals, or continue an existing musical idea.

0
installs
▌
Webrtc Livekit · damionrashford bundle
Deploy LiveKit WebRTC SFU (docs.livekit.io — Apache-2.0 Go binary): livekit-server (SFU binary, YAML + env config), livekit-cli (admin + load-testing — create-token, load-test, room list, room join), livekit-egress (record/stream-out to HLS/MP4/RTMP), livekit-ingress (RTMP/WHIP/SRT/URL ingest), livekit-agents (realtime AI voice/video agents). Data model: Room, Participant, Track, TrackPublication. JWT access tokens with grants (room, roomJoin, canPublish, canSubscribe, canPublishData, hidden, recorder). SDKs: JS/TS, Python, Go, Rust, Swift, Kotlin, Flutter, Unity, React/React Native, Node.js, Ruby, PHP. Redis for multi-node. TURN via bundled Pion or external coturn. Cloud vs self-hosted options. Use when the user asks to run a LiveKit server, mint room tokens, record a LiveKit room, build a conferencing app, integrate LiveKit Agents, or deploy a WebRTC SFU with full SDK coverage.

0
installs
▌
Audio Coreaudio · damionrashford bundle
Manipulate macOS audio at the Core Audio HAL layer: afinfo (audio file metadata), afplay (play), afconvert (convert format/rate/bit-depth/channel layout), say (TTS), SwitchAudioSource (change default input/output/system device — brew install switchaudio-osx), audiodevice CLIs (npm/Go variants), AppleScript via osascript to drive System Preferences Sound. HAL plugins at /Library/Audio/Plug-Ins/HAL/ load virtual drivers (BlackHole 2ch/16ch/64ch, Loopback, Background Music). Aggregate Device (drift-corrected multi-in) and Multi-Output Device via Audio MIDI Setup.app or AudioHardwareCreateAggregateDevice. Use when the user asks to change default macOS audio device, route audio between apps on Mac, install BlackHole, build an Aggregate Device, convert audio files with afconvert, or script Mac audio from the terminal.

0
installs
▌
Ffmpeg Audio Fx · damionrashford bundle
Creative and restoration audio effects with ffmpeg: chorus, flanger, aphaser, tremolo, vibrato, aecho, crystalizer, adecorrelate, adeclick, adeclip, apsyclip, asoftclip, speechnorm, dialoguenhance, adynamicequalizer, adynamicsmooth, afreqshift, aphaseshift, asupercut, asuperpass, asuperstop, atilt, afftfilt, bandpass, bandreject, biquad, allpass, ladspa, lv2. Use when the user asks to add echo/chorus/flanger, create psychedelic audio effects, enhance dialogue, de-click vinyl rips, soft-clip audio, apply LADSPA or LV2 plugins, or shift frequency.

0
installs
▌
Ffmpeg Captions · damionrashford bundle
Closed captions CEA-608/708 with ffmpeg: -a53cc 1 passthrough, readeia608 extraction, SCC and MCC and STL import/export, ccextractor handoff, 608 → SRT conversion, burning 608 to picture, preserving captions in MPEG-TS and MP4 and MOV. Use when the user asks to extract CEA-608 captions, preserve 708 captions, convert SCC to SRT, burn broadcast captions into video, pass through captions during transcode, or extract closed captions from a ProRes/MXF/TS file.

0
installs

162 published skills · page 1 of 2