Use this skill when the user wants to add or port a new model architecture to MLX-VLM — mapping a Hugging Face modeltype to a new file under mlxvlm/models, writing the ModelConfig, matching layer/weight names, reusing a similar existing model, adding a test class, and validating the port. Covers vision-language…
Use this skill when the user wants to benchmark an MLX-VLM change and present the numbers in a PR — fork-vs-main A/B comparisons, isolated-module micro-benchmarks, median-of-N timing with warmup, peak-memory reporting, correctness checks, parameter sweeps, and self-contained reproducible bench scripts to paste into a…
Use this skill when the user wants to convert a Hugging Face model to MLX or quantize/dequantize one with mlxvlm.convert, including bits and group size, quant modes (affine, mxfp4, nvfp4, mxfp8), RTN vs AWQ, mixed-bit recipes, dtype casts, calibration (text or multimodal), local vs Hub paths, revisions, uploading to…
Annotates VCF variants and normalizes HGVS nomenclature with public, license-free annotators (Ensembl VEP REST, VEP/SnpEff/ANNOVAR offline) and links variants to gnomAD population frequencies and the clinical context OpenMed extracts. Use when the user wants to predict variant consequences, map HGVS to genomic…
Package multiple FHIR R4 resources produced from OpenMed output into a single valid transaction Bundle ready to POST to an EHR, using OpenMed's verified bundle assembler openmed.clinical.exporters.fhir.tobundle. Covers deterministic urn:uuid fullUrls, automatic in-Bundle reference rewriting, request blocks…
Generates and verifies 21 CFR Part 11-style audit trails — who/what/when, electronic signatures, and tamper-evidence — for OpenMed pipelines in GxP and clinical-trial (GCP) settings. Use when the user runs OpenMed in a regulated/validated environment and needs an attributable, time-stamped, tamper-evident record of…
Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.
Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or…
Use this skill to generate well-branded interfaces and assets for Vocello (a local-first, Apple-native macOS voice-generation app — formerly QwenVoice). Contains essential design guidelines, colors, type, fonts, assets, and a Mac-app UI kit for prototyping voice-studio interfaces, marketing surfaces, and slides.
Watch a video from YouTube, Instagram, X/Twitter, Vimeo, TikTok or any of 1800 yt-dlp sites (or a local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or local mlx-whisper fallback, no API key), and hands the result to Claude so it can answer questions about…
Route /memo requests to the local memo MCP memory server. Use for searching, asking, saving, listing, getting, updating, deleting, reindexing, stats, and doctor commands. Prefer mcpmemomemo tools; use the memo CLI only for maintenance commands not exposed over MCP.
Add a lifecycle hook to /.aictl/hooks.json. Walks the user through choosing the right event, matcher, command, and timeout, then merges the new entry into the existing config without disturbing other hooks.
Check each provider for newly released models, compare against the supported set, add any missing ones, and update the per-provider docs and website accordingly.
Update README.md, CLAUDE.md, the docs/ tree (ARCH.md, INSTALL.md, USAGE.md, CONFIG.md, PROVIDERS.md, TOOLS.md, EXTENSIONS.md, CODINGAGENT.md, SERVER.md), and the website (website/index.html, website/terminal.html, website/server.html, website/desktop.html) to match the current project state.
Speak a short spoken alert to the user via the vox text-to-speech CLI whenever you hand the turn back to them — a task finished (pass or fail, however long it took), you're blocked and need input/a decision/approval, something broke, or you're about to go quiet on a long job. Assume the user is NOT watching the…
Guides and validates architecture-aware ports of PyTorch/Hugging Face models to Apple MLX, inspects existing local MLX projects, and plans evidence-gated optimizations for Apple Silicon. Use when the user asks to run, port, convert, inspect, quantize, benchmark, or fix a model (LLM, VLM, audio/TTS/ASR, diffusion, SSM…
A batch workflow for archiving Douyin favorites or all posts from selected creators into Obsidian. It uses account cookies, rate limits, downloading, transcription, deduplication, and optional scheduled synchronization.
A workflow for turning Douyin videos or image posts into text, summaries, intent judgments, and archived notes. Douyin is a Chinese social-media platform for short videos and image posts.