ML Ops
Machine learning operations
knowledge-query
by GongLingRui
专注于竖屏短剧知识库查询和信息检索，提供专业知识服务。适用于查询剧本桥段、高能情节、创作技巧、商业运营等专业知识
django-drf
by prowler-cloud
Django REST Framework patterns. Trigger: When implementing generic DRF APIs (ViewSets, serializers, routers, permissions, filtersets). For Prowler API specifics (RLS/RBAC/Providers), also use prowler-api.
pipeline
by ReinaMacCredy
Sequential agent chains with context passing. Run agents in series where each stage receives output from prior stages.
scaffolding
by dotnet
'Implementation details for EF Core scaffolding (reverse engineering). Use when changing ef dbcontext scaffold pipeline implementation, database schema reading, CSharpModelGenerator, or related classes.'
model-building
by dotnet
'Implementation details for EF Core model building. Use when changing ConventionSet, ModelBuilder, IConvention implementations, ModelRuntimeInitializer, RuntimeModel, or related classes.'
migrations
by dotnet
'Implementation details for EF Core migrations. Use when changing MigrationsSqlGenerator, model diffing, migration operations, HistoryRepository, the Migrator or related classes.'
beam-concepts
by apache
Explains core Apache Beam programming model concepts including PCollections, PTransforms, Pipelines, and Runners. Use when learning Beam fundamentals or explaining pipeline concepts.
saleor-django-migration
by saleor
Generate Django schema migrations for the Saleor codebase using manage.py makemigrations. Use when (1) a new Django model is created, (2) model fields are added/altered/removed, (3) user explicitly asks to create a migration. This skill covers ONLY synchronous schema migrations (CreateModel, AddField, AlterField, RemoveField, etc.) — NOT data migrations with RunPython or RunSQL. If unsure whether the migration is schema-only, ask the user.
nemo-curator
by davila7
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
mix-engineer
by bitwize-music-studio
Polishes raw Suno audio by processing per-stem WAVs (vocals, drums, bass, other) with targeted cleanup, EQ, and compression, then remixing into a polished stereo WAV ready for mastering. Use after audio import and before mastering.
code-quality
by tursodatabase
General Correctness rules, Rust patterns, comments, avoiding over-engineering. When writing code always take these into account
reference-core
by angular
Explains the mental model and architecture of the code under packages/core. You MUST use this skill any time you plan to work with code in packages/core
sag
by elizaOS
ElevenLabs text-to-speech with mac-style say UX.
summarize
by elizaOS
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
claude-opus-4-5-migration
by aiskillstore
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
evaluating-code-models
by davila7
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.
huggingface-accelerate
by davila7
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
vrm-springbone-physics
by Project-N-E-K-O
Debugging and fixing VRM SpringBone physics issues in three-vrm, including hair/clothing physics that flies upward, sticks out horizontally, or behaves unnaturally.
speculative-decoding
by davila7
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
model-pruning
by davila7
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
peft-fine-tuning
by davila7
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
aoti-debug
by pytorch
Debug AOTInductor (AOTI) errors and crashes. Use when encountering AOTI segfaults, device mismatch errors, constant loading failures, or runtime errors from aot_compile, aot_load, aoti_compile_and_package, or aoti_load_package.
gemini-delegation
by athola
Gemini CLI delegation workflow implementing delegation-core for Google's
release-publish
by mono
Publish SkiaSharp packages and finalize the release. Use when user says "publish X", "finalize X", "tag X", or "finish release X". This is the FINAL step - after release-testing passes. Publishes to NuGet.org, creates tag, GitHub release, and closes milestone. Triggers: "publish the release", "push to nuget", "create github release", "tag the release", "close the milestone", "annotate release notes", "testing passed what's next", "finalize 3.119.2", "release is ready".