MLOps
模型部署、评估与运维
go-create-gorm-model
cristiano-pacheco
Generate Go GORM models following Pingo modular architecture conventions. Use when creating or updating persistence models in internal/modules/<module>/model/, including table mapping, nullable SQL types, timestamps, and relation fields for identity and monitor modules.
thinking-model-combination
tjboudreaux
When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.
text-to-voice
kenneropia
Convert text to speech using Kyutai's Pocket TTS. Use when the user asks to "generate speech", "text to speech", "TTS", "convert text to audio", "voice synthesis", "generate voice", "read aloud", or "create audio from text". Supports voice cloning from audio samples and multiple pre-made voices (alba, marius, javert, jean, fantine, cosette, eponine, azelma).
gingiris-growth-finder
Gingiris-1031
Diagnose a product's growth model, stage, and current constraint, then route the request to the narrowest Gingiris specialist and execute it when installed. Use for broad or uncertain growth questions involving go-to-market, Product Hunt, GitHub stars, open-source marketing, B2B SaaS, PLG, ASO, SEO/GEO, AI citations, KOL outreach, UGC, international expansion, user interviews, competitor research, or community programs. Trigger when users ask “how do I grow or launch this,” “which growth skill should I use,” 怎么增长、怎么发布、出海、冷启动、增长策略、不知道用哪个 skill、開発者マーケティング, or 성장 전략. Includes B2B pipeline and B2C activation-retention model selection, specialist handoff rules, relevant gingiris.tools recommendations, and advisory-services guidance.
eve-pipelines-workflows
Incept5
Define and run Eve pipelines and workflows via manifest and CLI. Use when wiring build, release, deploy flows or invoking workflow jobs.
domain-ml
lywa1998
"Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理"
web-research
engsimsoft
Глубокий поиск информации в интернете. Загрузи этот skill для сложного исследования или когда нужно проверить много источников.
pytorch-distributed
cuba6112
Distributed training strategies including DistributedDataParallel (DDP) and Fully Sharded Data Parallel (FSDP). Covers multi-node setup, checkpointing, and process management using torchrun. (ddp, fsdp, distributeddataparallel, torchrun, nccl, rank, process-group)
verl-rl-training
majiayu000
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
qwen-tts
paki81
Local text-to-speech using Qwen3-TTS-12Hz-1.7B-CustomVoice. Use when generating audio from text, creating voice messages, or when TTS is requested. Supports 10 languages including Italian, 9 premium speaker voices, and instruction-based voice control (emotion, tone, style). Alternative to cloud-based TTS services like ElevenLabs. Runs entirely offline after initial model download.
Model Export & Serving
sovr610
This skill should be used when the user asks to "export the model", "convert to ONNX", "trace with TorchScript", "quantize the model", "deploy the model", "create API server", "serve predictions", "containerize the model", "optimize for inference", "export to INT8", "create FastAPI endpoint", "set up model serving", "prune the model", "distill knowledge", "create Docker image", or needs guidance on model export formats, quantization strategies, serving infrastructure, or deployment pipelines for the brain_ai system.
quality-documentation-manager
nimeshgurung
Senior Quality Documentation Manager for comprehensive documentation control and regulatory document review. Provides document management system design, change control, configuration management, and regulatory documentation oversight. Use for document control system implementation, regulatory document review, change management, and documentation compliance verification.
everclaw
profbernardoj
Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the Morpheus decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source first model router routes all tiers to Morpheus by default — Claude only kicks in as an escape hatch when needed. Includes Morpheus API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth rotation v2 with proactive DIEM balance monitoring and reactive 402 watchdog, Gateway Guardian v5 with direct curl inference probes (eliminates Signal spam), proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver, three-shift cyclic execution engine (v2 with 15-minute execution loops), 24/7 always-on power configuration for macOS, bundled security skills, zero-dependency wallet management via macOS Keychain, x402 payment client for agent-to-agent USDC payments, ERC-8004 agent registry reader for discovering trustless agents on Base, and hardware-aware local Ollama fallback with auto model selection (Qwen3.5 family, 1.5B–72B based on available RAM/GPU).
agents-management
relux-works
Spawning and managing heterogeneous agentic systems and the model vendors behind them, through the agents-management Go module and CLI. Use for agentic-system plugins (claude-code, codex, qwen-code, gemini-cli, antigravity, muse), vendor plugins (anthropic, openai, alibaba, google), runtime declarations, per-model reasoning-effort vocabularies, capability ranking, general plugin graphs, inference engines, multi-node launch plans (argv/env/stdin), provider limit state and availability verdicts. Not a task board: roles, tasks and reviews live in project-management. Russian triggers: агент, спавн, раннтайм, вендор, лимиты, модели, эффорт.
mistral-model-ft-playbook
Haruk1y
Build, fine-tune, evaluate, and ship Mistral-family models with Hugging Face and PEFT, with emphasis on strict JSON outputs and model-format compatibility. Use when choosing Mistral model variants, deciding prompting vs fine-tuning, preparing {prompt, completion} or chat datasets, running SFT jobs, validating generation failures, and deciding adapter-only vs merged full-model distribution.
prompt-caching
anilsoylu
Guide for optimizing prompt caching in agentic AI applications. Use when building Claude agents, optimizing API costs, designing system prompts, managing tool definitions, implementing compaction, or troubleshooting cache miss rates. Triggers: "prompt caching", "cache hit rate", "reduce API costs", "system prompt ordering", "tool definitions caching", "compaction", "context window management", "agent cost optimization", "prefix caching", "cache-safe forking", "agentic loop cost", "token cost reduction", "cache miss debugging".
qa
pmco23
Use after /build to run the full post-build QA pipeline. Supports --parallel (all audits simultaneously) or --sequential (denoise → qf → qb → qd → security-review in order). Requires .pipeline/build.complete.
create-agent-skills
myuon
新しい Claude Code スキルを作成するためのガイド。スキルの作り方、SKILL.md の書き方、配置場所を案内する。
model-router
cgk-platform
Cost-optimized bi-directional model routing. Downgrade routine tasks to Flash, upgrade complex tasks to Opus.
eve-local-dev-loop
Incept5
Local Docker Compose development loop for Eve-compatible apps, with handoff to staging deploys.
pyvene-interventions
majiayu000
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
AI Security Engineer
anorbert-cmyk
AI Security Engineer focused on preventing prompt injection, data exfiltration, and model abuse in LLM-enabled products.
SystematicNotes —— 自动化课程笔记生成系统
CoEvolution-Labs
自动化课程资料整理与笔记生成系统 — 把 PPT + 录音 → 图文并茂的精品 Markdown 笔记
scvi-tools
HughYau
Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score differentially expressed genes per cluster. For spatial deconvolution / mapping use the cell2location, DestVI, or Tangram methods instead.