plugins/python-master/skills/python-ffmpeg/SKILL.md
Expert guide to FFmpeg from Python for video/audio processing, encoding, streaming, and media manipulation. PROACTIVELY activate for: (1) Python+FFmpeg via ffmpeg-python, PyAV, subprocess, moviepy; (2) encoding (H.264, H.265/HEVC, VP9/WebM, AV1); (3) hardware acceleration (NVIDIA NVENC, Intel QSV, AMD AMF, VAAPI); (4) audio extraction, conversion, filter chains; (5) video filters (scale, crop, rotate, text/image overlays, color); (6) trim/concat workflows; (7) HLS, DASH, RTMP streaming; (8) metadata probing (ffprobe, ffmpeg.probe); (9) thumbnails (single + sprite sheets); (10) frame-accurate PyAV; (11) bug debugging (audio loss after filters, subprocess deadlocks, Windows paths, -y prompts); (12) GIF, speed change, picture-in-picture, blur/quality detection. Provides: library selection, install steps, copy-pasteable encoding recipes, hardware-accel flag reference, error handling, subprocess best practices, performance tuning for production Python+FFmpeg pipelines.
npx skillsauth add JosiahSiegel/claude-plugin-marketplace python-ffmpegInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill for Python-driven FFmpeg work: encoding, filtering, audio processing, metadata probing, streaming, thumbnails, PyAV frame access, subprocess integration, and production troubleshooting.
Use when the user asks for tasks covered by the frontmatter triggers, especially implementation guidance, debugging, architecture choices, production hardening, or performance-sensitive decisions in this domain. Start from this orchestrator, then load the focused reference file that matches the requested detail level.
overwrite_output() with ffmpeg-python or -y with subprocess, plus captured stderr for diagnostics.ffmpeg.output(...) or copied explicitly.Path(...).as_posix() or as subprocess argument-list entries, not hand-quoted command strings.development
This skill should be used when the user asks to train, debug, scale, or improve ML models. PROACTIVELY activate for: (1) PyTorch, TensorFlow/Keras, JAX, Flax, Hugging Face Trainer/Accelerate training loops, (2) distributed training, DDP/FSDP/DeepSpeed, TPU/GPU setup, (3) mixed precision AMP/bf16, gradient accumulation, checkpointing, seeding, (4) overfitting, imbalance, loss functions, regularization, LR schedules, warmup, (5) memory optimization, gradient checkpointing, offloading, quantization-aware training. Provides: reproducible training best practices across deep learning and classical ML.
development
This skill should be used when the user asks to productionize, track, version, govern, monitor, or automate ML systems. PROACTIVELY activate for: (1) MLflow, Weights & Biases, Neptune, Comet, ClearML experiment tracking, (2) model registry, model versioning, artifact lineage, reproducibility, (3) Kubeflow, SageMaker Pipelines, Vertex AI Pipelines, Azure ML pipelines, Databricks workflows, (4) CI/CD, continuous training/evaluation, A/B tests, canary/shadow deployments, (5) drift detection, model monitoring, data validation, responsible AI governance. Provides: end-to-end MLOps architecture and operational safeguards.
development
This skill should be used when the user asks to optimize, export, serve, compress, or accelerate ML inference. PROACTIVELY activate for: (1) latency, throughput, p95/p99, batching, concurrency, KV cache, memory, or cost issues, (2) quantization INT8/INT4, GPTQ, AWQ, bitsandbytes, pruning, sparsity, distillation, (3) ONNX export, ONNX Runtime, TensorRT, TorchScript, torch.compile, XLA, OpenVINO, Core ML, TFLite, (4) Triton, TorchServe, TF Serving, BentoML, Seldon, KServe configuration, (5) edge deployment, CPU/GPU/TPU/Inferentia serving. Provides: hardware-aware inference optimization and safe benchmarking.
testing
This skill should be used when the user asks to tune hyperparameters, run sweeps, optimize search spaces, or use AutoML. PROACTIVELY activate for: (1) Optuna, Ray Tune, FLAML, AutoGluon, Hyperopt, Nevergrad, KerasTuner, W&B sweeps, (2) grid search, random search, Bayesian optimization, TPE, Gaussian processes, evolutionary search, (3) ASHA, Hyperband, successive halving, multi-fidelity optimization, population-based training, (4) learning-rate finder, batch-size search, early stopping, pruning, (5) reproducible sweep design and experiment analysis. Provides: budget-aware hyperparameter search strategy.