MLOps
模型部署、评估与运维
cognitive-baseline-eval
starwreckntx
Execute the Joseph Cognitive Baseline v2.1 (JC B-v2.1) 5-Scenario Test Suite to quantify AI alignment, friction maintenance, and protocol adherence.
cpo
jforksy
CPO Co-Pilot - product strategy, roadmap prioritization, competitive positioning, and product-market fit validation
cross-model-handoff-testing
starwreckntx
Test cross-model context handoff integrity.
Builder Operating Model
Coowoolf
Shift from rigid roles (PM, Designer, Engineer) towards a model where individuals use AI to bridge skill gaps, enabling smaller and flatter teams. Use in early-stage startups or innovation units where speed is critical.
packlets
dtinth
Learn the rules of packlets for managing a JavaScript/TypeScript project. Use this skill whenever a user mentions packlets or when working in a project with packlets (src/packlets) directory.
portkey-python-sdk
Portkey-AI
Complete reference for the Portkey AI Gateway Python SDK with unified API access to 200+ LLMs, automatic fallbacks, caching, and full observability. Use when building Python applications that need LLM integration with production-grade reliability.
fine-tuning
pluginagentmarketplace
LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.
Constitutional AI
Coowoolf
105 Product Management Skills extracted from Lenny's Podcast - For use with Claude Code / Cursor / Windsurf
computational-model-design
starwreckntx
Design computational models for cognitive simulation and analysis.
owasp-cicd-top-10
yariv1025
"OWASP Top 10 CI/CD Security Risks - prevention, detection, and remediation for pipeline security. Use when securing or reviewing CI/CD - flow control, IAM, dependency chain, poisoned pipeline execution, PBAC, credential hygiene, system config, third-party services, artifact integrity, logging and visibility."
spoint
AnEntrypoint
"Build multiplayer physics games with the Spawnpoint engine. Use when asked to: create a game, add physics objects, spawn entities, build a map/level, handle player interaction, add weapons, respawn, scoring, create moving platforms, manage world config, load 3D models, add HUD/UI, work with the EventBus, or develop any app inside an apps/ directory."
自运行量化交易系统（Machine Learning Driven Quant Trading System）
1WangToby
重大更新： skill_finance_analysis 作为 submodule 引入到 tools/tool_finance_analysis，ZIP 安装自动包含工具库，无需额外克隆
east-py-datascience
elaraai
"Data science and machine learning platform functions for the East language (TypeScript types). Use when writing East programs that need optimization (MADS, Optuna, SimAnneal, Scipy, Optimization, GoogleOr), machine learning (XGBoost, LightGBM, NGBoost, Torch MLP, Lightning, GP), Bayesian inference (PyMC), simulation (Simulation DES), ML utilities (Sklearn preprocessing, metrics, splits), conformal prediction (MAPIE), or model explainability (SHAP). Triggers for: (1) Writing East programs with @elaraai/east-py-datascience, (2) Derivative-free optimization with MADS, (3) Bayesian optimization with Optuna, (4) Discrete/combinatorial optimization with SimAnneal, (5) Gradient boosting with XGBoost or LightGBM, (6) Probabilistic predictions with NGBoost or GP, (7) Neural networks with Torch MLP or Lightning, (8) Data preprocessing and metrics with Sklearn, (9) Conformal prediction intervals with MAPIE, (10) Model explainability with Shap, (11) Iterative coordinate descent with Optimization, (12) Constraint programming, vehicle routing, LP/MIP, or graph algorithms with GoogleOr, (13) Bayesian regression, hierarchical models, and multi-layer estimation with PyMC, (14) Economic ontology simulation via discrete event simulation with Simulation."
three-layer-agent-stack
Coowoolf
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for agentic workflows
replicate-daemon
fast-gateway-protocol
Fast Replicate model inference via FGP daemon. Use when user needs to run ML models (image generation, LLMs, audio processing, video generation) on Replicate. Triggers on "replicate run", "run model replicate", "stable diffusion", "SDXL", "replicate llama", "whisper replicate".
Hierarchy of Marketplaces
Coowoolf
A roadmap for marketplace domination. Level 1: Focus on a "thimble" to maximize Happy GMV. Level 2: Tip the market via growth loops. Level 3: Dominate to capture economic rents. Not all GMV is equal.
Google ADK Python Skill
wollfoo
Remember: ADK treats agent development like traditional software engineering - use version control, write tests, and follow engineering best practices.
ai-teammate-model
Coowoolf
Use when designing AI agent products, defining roadmaps for agentic workflows, or evaluating how to evolve AI from passive tool to proactive partner in software development
model-deployment
pluginagentmarketplace
LLM deployment strategies including vLLM, TGI, and cloud inference endpoints.
aws-bedrock-evals
antstackio
Build and run LLM-as-judge evaluation pipelines using Amazon Bedrock Evaluation Jobs with pre-computed inference datasets. Use when setting up automated model evaluation, designing test scenarios, collecting pre-computed responses, configuring custom metrics, creating AWS infrastructure, running evaluation jobs, parsing results, and iterating on findings.
ai-vision
httprunner
Multimodal UI understanding and single-step planning via OpenAI-compatible Responses APIs. Use when you need AIQuery/AIAssert and plan-next to extract UI element coordinates, validate UI assertions, summarize screenshots, or decide the next UI action from an image. External agents handle execution via adb/hdc and multi-step loops. Defaults to Doubao models but can be pointed at other multimodal providers via base URL, API key, and model name.
Puppet Mockup Generator
mmcmedia
Generated arrows are license-free (Nano Banana = we own it)
claude-command-example-plugin-example-command
monkey1sai
Converted from Claude plugin command "example-command" (example-plugin).
feedback-mastery
cachemoney
Navigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) feedback technique. Use when preparing for difficult conversations, giving feedback, or managing conflicts.