MLOps
模型部署、评估与运维
slime-user
yzlnew
Guide for using SLIME (LLM post-training framework for RL Scaling). Use when working with SLIME for reinforcement learning training of language models, including setup, configuration, training execution, multi-turn interactions, custom reward models, tool calling scenarios, or troubleshooting SLIME workflows. Covers GRPO, GSPO, PPO, Reinforce++, multi-agent RL, VLM training, FSDP/Megatron backends, SGLang integration, dynamic sampling, and custom generation functions.
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.
Classification Modeling
aj-geddes
Build binary and multiclass classification models using logistic regression, decision trees, and ensemble methods for categorical prediction and classification
swiftui-view-refactor
pondorasti
Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view's layout/ordering, handle view models safely (non-optional when possible), or standardize how dependencies and @Observable state are initialized and passed.
quality-scoring
akaszubski
"Multi-dimensional data assessment for training quality evaluation including IFD scoring, factuality, and reasoning validation. Use when scoring training data or evaluating dataset quality. TRIGGER when: quality scoring, data assessment, IFD, factuality, training data quality. DO NOT TRIGGER when: code quality, test coverage, documentation, non-data tasks."
prompt-engineering
akaszubski
"Prompt engineering patterns for writing agent prompts and skill files — constraint budgets, register shifting, HARD GATE patterns, anti-personas. Use when writing or reviewing agents/.md or skills//SKILL.md. TRIGGER when: agent prompt, skill file, prompt engineering, model-tier compensation, HARD GATE, prompt quality. DO NOT TRIGGER when: user-facing docs, README, CHANGELOG, config files."
realign-meta-framework
akaszubski
Production-ready Claude Code 2.0 setup for autonomous development
ux-kano-model
geekatron
"Kano model feature classification and prioritization sub-skill for the /user-experience parent skill. Classifies product features into Must-be (M), Performance (O), Attractive (A), Indifferent (I), and Reverse (R) categories using the functional/dysfunctional questionnaire pair methodology (Kano et al., 1984). Computes Customer Satisfaction (CS) coefficients (Better/Worse) for priority matrix visualization. Produces feature classification reports, priority matrices, and survey design templates. Sample size awareness: 5-8 respondents yields directional classification only (MEDIUM confidence); 20+ respondents required for statistical classification (Berger et al., 1993). Invoked by ux-orchestrator during Wave 4 lifecycle-stage routing or when user intent is \"Need to prioritize features\" at any lifecycle stage. Triggers: Kano, must-be, attractive, one-dimensional, performance feature, satisfaction, feature classification, delighter, feature prioritization, CS coefficient."
fal-audio
fal-ai-community
Text-to-speech and speech-to-text using fal.ai audio models. Use when the user requests "Convert text to speech", "Transcribe audio", "Generate voice", "Speech to text", "TTS", "STT", or similar audio tasks.
fal-platform
fal-ai-community
fal.ai Platform APIs for model management, pricing, usage tracking, and cost estimation. Use when user asks "show pricing", "check usage", "estimate cost", "setup fal", "add API key", or platform management tasks.
fal-upscale
fal-ai-community
Upscale and enhance image resolution using AI. Use when the user requests "Upscale image", "Enhance resolution", "Make image bigger", "Increase quality", or similar upscaling tasks.
letta-development-guide
letta-ai
Comprehensive guide for developing Letta agents, including architecture selection, memory design, model selection, and tool configuration. Use when building or troubleshooting Letta agents.
letta-configuration
letta-ai
Configure LLM models and providers for Letta agents and servers. Use when setting model handles, adjusting temperature/tokens, configuring provider-specific settings, setting up BYOK providers, or configuring self-hosted deployments with environment variables.
github-flow
metalagman
Use this skill when working with the lightweight GitHub Flow branching model. Ideal for projects with continuous deployment where 'main' is always deployable.
gitflow
metalagman
Use this skill when managing git branches, releases, or hotfixes according to the Gitflow workflow. It enforces naming conventions and synchronization policies.
model-evaluation-benchmark
rysweet
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for model benchmarking, comparison evaluation, or performance testing between AI models.
agent-sdk
rysweet
Comprehensive knowledge of Claude Agent SDK architecture, tools, hooks, skills, and production patterns. Auto-activates for agent building, SDK integration, tool design, and MCP server tasks.
owasp-ai-testing
mastepanoski
AI trustworthiness testing using OWASP AI Testing Guide v1. Execute 44 test cases across 4 layers (Application, Model, Infrastructure, Data) with practical payloads and remediation.
SKILL.md — 舔狗训练营 · 训练沙盒总控
TammyTan516
```
pytm
AgentSecOps
Python-based threat modeling using pytm library for programmatic STRIDE analysis, data flow diagram generation, and automated security threat identification. Use when: (1) Creating threat models programmatically using Python code, (2) Generating data flow diagrams (DFDs) with automatic STRIDE threat identification, (3) Integrating threat modeling into CI/CD pipelines and shift-left security practices, (4) Analyzing system architecture for security threats across trust boundaries, (5) Producing threat reports with STRIDE categories and mitigation recommendations, (6) Maintaining threat models as code for version control and automation.
seedance-storyboard
elementsix
将任何想法转换成即梦 Seedance 2.0 专业分镜提示词。当用户想要生成视频、制作短视频、创作分镜、使用 Seedance/即梦/剪映 AI 视频时调用。
start-feature
leeovery
"Start a new feature through the full pipeline. Gathers context via structured interview, creates a discussion, then bridges to continue-feature for specification, planning, and implementation."
woodpecker-cli
fred-drake
Reference for the Woodpecker CI command-line tool. Use when working with Woodpecker CI pipelines, managing repositories, secrets, registries, organizations, or users via the CLI. Covers pipeline operations (start, stop, approve, logs), repository management, secret/registry configuration, and local pipeline execution.
bambu-studio-ai
heyixuan2
"Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pipeline: search → generate → analyze → colorize → slice → print → monitor. Supports all 9 Bambu Lab printers (A1 Mini, A1, P1S, P2S, X1C, X1E, H2C, H2S, H2D)."