MLOps
模型部署、评估与运维
gamification-triad
Coowoolf
Use when designing retention mechanisms, habit loops, or auditing why users drop off despite engaging with core features, to structure gamification beyond superficial badges
notebook-ml-architect
BjornMelin
Expert guidance for auditing, refactoring, and designing machine learning Jupyter notebooks with production-quality patterns. Use when: (1) Analyzing notebook structure and identifying anti-patterns, (2) Detecting data leakage and reproducibility issues, (3) Refactoring messy notebooks into modular pipelines, (4) Generating templates for ML workflows (EDA, classification, experiments), (5) Adding reproducibility instrumentation (seeding, logging, env capture), (6) Converting notebooks to Python scripts, (7) Generating experiment summary reports. Triggers on: ML notebook, Jupyter audit, notebook refactor, data leakage, experiment template, ipynb best practices, notebook to script, reproducibility.
The 'Explorer vs. Lecturer' Coaching Model
Coowoolf
105 Product Management Skills extracted from Lenny's Podcast - For use with Claude Code / Cursor / Windsurf
AI Safety Auditor
jmsktm
Audit AI systems for safety, bias, and responsible deployment
pinecone-mcp
pinecone-io
Reference for the Pinecone MCP server tools. Documents all available tools - list-indexes, describe-index, describe-index-stats, create-index-for-model, upsert-records, search-records, cascading-search, and rerank-documents. Use when an agent needs to understand what Pinecone MCP tools are available, how to use them, or what parameters they accept.
speckit-tasks-zh
forztf
基于speckit工作流的任务生成技能，用于根据可用设计文档生成可操作的、依赖有序的tasks.md。当需要基于spec.md、plan.md、data-model.md、contracts/等设计文档为功能开发生成详细任务列表时使用此技能。触发词包括"speckit tasks"、"生成任务"、"任务规划"、"功能任务分解"、"创建tasks.md"等。
Computer Vision Helper
jmsktm
Assist with image analysis, object detection, and visual AI tasks
pydantic
jiatastic
Pydantic models and validation. Use when: (1) Defining schemas, (2) Validating input/output, (3) Generating JSON schema.
Business Plan Writer
jmsktm
Create comprehensive business plans, financial projections, and strategic documents for funding or planning
arboreto
hxk622
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
geniml
hxk622
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
wardyn-ci
cjohnstoniv
Generate a Wardyn sandbox policy + CLI invocation (or full pipeline job) for running a governed sandboxed task in CI — GitHub Actions, Azure DevOps, or any headless/unattended launch. Use when the user wants to run Wardyn in CI/a pipeline, generate a wardyn policy or run config, launch a sandbox non-interactively, or asks about wardyn run --wait / --image / task_mode / ci-run.sh. Triggers on "wardyn in CI", "CI sandbox policy", "pipeline sandbox", "headless wardyn run", "unattended governed run", "generate a wardyn policy".
design-system-foundations
KentoShimizu
"Define scalable design-system foundations with clear ownership and adoption boundaries. Use when multiple teams need shared component standards, foundational patterns, and ownership rules to deliver consistent UI across products; do not use for backend data-model or deployment pipeline decisions."
two-sigma-ml-at-scale
copyleftdev
Build trading systems in the style of Two Sigma, the systematic investment manager pioneering machine learning at scale. Emphasizes alternative data, distributed computing, feature engineering, and rigorous ML infrastructure. Use when building ML pipelines for alpha research, feature stores, or large-scale backtesting systems.
architecture-ddd
KentoShimizu
"Domain-driven design workflow for bounded context partitioning, aggregate design, and context mapping in complex domains. Use when domain complexity or organizational scaling requires explicit model boundaries; do not use for small CRUD domains without competing language models."
db-conceptual-modeling
KentoShimizu
"Conceptual data modeling workflow for domain entities, relationships, and lifecycle boundaries. Use when teams must align on domain meaning before logical/physical schema decisions; do not use for index-only or migration-only tasks."
skill-composer
whynowlab
Compose multiple skills into a unified workflow pipeline. Combine research, creativity, review, and other skills into custom multi-step processes. Use when a task requires chaining skills together, creating custom workflows, or designing compound skill sequences. Triggers on "워크플로우", "workflow", "파이프라인", "pipeline", "스킬 조합", "combine skills", "복합 프로세스".
openscad-iterative-modeling
fboldo
Iteratively generate OpenSCAD (SCAD) code, render PNG previews, visually critique the result, and refine in a tight loop until the model matches. Use when the user asks to create a 3D model, design a part, make a bracket/enclosure/mount, render in OpenSCAD, export STL, or any request that can be expressed as parametric CSG geometry. Requires the OpenSCAD MCP server tools (render_scad_png, export_scad_stl).
machine-learning
pluginagentmarketplace
Supervised & unsupervised learning, scikit-learn, XGBoost, model evaluation, feature engineering for production ML
project-development
Svenja-dev
Design and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing between LLM and traditional approaches, or structuring batch processing pipelines.
summarize
ZhihaoAIRobotic
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
currying-inference
marius-townhouse
Use when generic types aren't inferred. Use when builder patterns need better types. Use when creating new inference sites.
accurate-environment-model
marius-townhouse
Use when defining global types. Use when augmenting window. Use when typing environment variables. Use when working with build-time constants. Use when configuring type definitions.
chunking-strategies
latestaiagents
Optimize document chunking for RAG performance and retrieval quality. Use this skill when splitting documents, choosing chunk sizes, implementing semantic chunking, or improving RAG retrieval accuracy. Activate when: chunking, split documents, chunk size, text splitting, document processing, RAG performance, semantic chunking, overlap.