MLOps
模型部署、评估与运维
pict-test-designer
omkamal
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected results.
jupyter-to-marimo
marimo-team
Convert a Jupyter notebook (.ipynb) to a marimo notebook (.py).
check-the-provider-before-you-catalog
brcampidelli
Verify the route's live index before recording a model slug, price or served context window.
SKILL.md — 舔狗训练营 · 训练沙盒总控
TammyTan516
```
mcp-memory-gateway
IgorGanapolsky
The Agentic Feedback Studio & Veto Layer. Persistent agent memory, high-density context packs, and Agentic Guardrails (V2V) for Claude Code, Codex, and Gemini.
nvidia-specdecode-al-doctor
IgorGanapolsky
Fail-closed speculative-decoding AL/D doctor for ThumbGate. Checks speedup ≤ AL/(1+ρD), attention D=128/G-1, tile alignment, and maps to checkpoint-speculative-decoding-acceptance. Steal from NVIDIA co-design blog — never clone TensorRT/EAGLE/Model-Optimizer. Slash: /nvidia-specdecode-al-doctor.
ai-pricing
chadboyda
"When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins. Also use when the user mentions 'AI pricing,' 'usage-based pricing,' 'consumption pricing,' 'outcome pricing,' 'BYOK,' 'bring your own key,' 'per-seat pricing,' 'pricing tiers,' 'AI margins,' 'cost per token,' or 'pricing model.' This skill covers pricing strategy, packaging, and margin management for AI-native products."
gtm-metrics
chadboyda
"When the user wants to define GTM metrics, build a metrics dashboard, measure pipeline efficiency, or track AI product performance. Also use when the user mentions 'GTM metrics,' 'revenue latency,' 'pipeline metrics,' 'TTFV,' 'time-to-first-value,' 'data health,' 'attribution,' 'conversion rate,' 'CAC,' 'LTV,' 'NRR,' 'GTM dashboard,' 'magic number,' 'pipeline velocity,' or 'funnel metrics.' This skill covers GTM measurement from metric selection through dashboard design, including AI-specific cost metrics, attribution models, and weekly review cadences."
partner-affiliate
chadboyda
"When the user wants to build a partner program, launch an affiliate program, design integration partnerships, or create distribution partnerships. Also use when the user mentions 'partnerships,' 'affiliate program,' 'referral program,' 'partner ecosystem,' 'integration partner,' 'reseller,' 'co-marketing,' 'PartnerStack,' or 'revenue share.' This skill covers partner and affiliate program design from recruitment through performance optimization."
Skill: checkpoint-strategy
strikersam
Pairs with release-readiness — checkpoint validation before model release
Release Readiness Handshake (RRH) Skill
OmniNode-ai
Opt-in preflight validation via Release Readiness Handshake (RRH) -- runs A1 (collect) -> A2 (validate) -> A3 (store) pipeline before side-effecting phases
debug-pipeline
RHEcosystemAppEng
Diagnose OpenShift Pipelines (Tekton) CI/CD failures including PipelineRun failures, TaskRun step errors, workspace/PVC binding issues, and authentication problems. Automates multi-step diagnosis: PipelineRun status, failed TaskRun analysis, step container logs, and related resource checks. Use this skill when pipelines fail, hang, or produce unexpected results. Triggers on /debug-pipeline command or phrases like "pipeline failed", "PipelineRun error", "TaskRun failed", "tekton error", "pipeline stuck", "pipeline timeout".
golang-concurrency-patterns
bobmatnyc
"Go concurrency patterns for production services: context cancellation, errgroup, worker pools, bounded parallelism, fan-in/fan-out, and common race/deadlock pitfalls"
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."
peft
wundercorp
Fine-tune large LLMs with LoRA on limited GPU memory.
arkit-visionos-developer
tomkrikorian
Build and debug ARKit features for visionOS, including ARKitSession setup, authorization, data providers (world tracking, plane detection, scene reconstruction, hand tracking), anchor processing, and RealityKit integration. Use when implementing ARKit workflows in immersive spaces or troubleshooting ARKit data access and provider behavior on visionOS.
spatial-swiftui-developer
tomkrikorian
Design and implement visionOS SwiftUI scenes that integrate RealityKit content. Use when building spatial UI with RealityView, Model3D, attachments, volumetric windows, ImmersiveSpace, or spatial gestures, or when choosing SwiftUI vs RealityKit APIs for 3D presentation.
model-router
nguyenthienthanh
"Automatically select optimal Claude model (Haiku/Sonnet/Opus) based on task complexity to reduce costs while maintaining quality."
start
TakaGoto
"Begin your RAG learning journey — assess your level and pick a learning path"
r3f-loaders
EnzeD
React Three Fiber asset loading - useGLTF, useLoader, Suspense patterns, preloading. Use when loading 3D models, textures, HDR environments, or managing loading states.
positioning-icp
chadboyda
"When the user wants to define their ideal customer profile, position an AI product, build messaging architecture, or validate product-market fit. Also use when the user mentions 'ICP,' 'ideal customer profile,' 'positioning,' 'PMF,' 'product-market fit,' 'messaging,' 'buyer persona,' 'enrichment signals,' 'market positioning,' or 'competitive positioning.' This skill covers market positioning, ICP definition, messaging architecture, and PMF validation for AI-native products."
plan
jh941213
복잡한 작업 전 계획 수립. Plan 모드에서 사용하거나 "계획", "플랜", "어떻게 구현" 등의 키워드에 자동 활성화.
compact-guide
jh941213
컨텍스트 관리 가이드. "컨텍스트", "토큰", "compact" 키워드에 활성화.
openscad
goncalossilva
"Create and render OpenSCAD 3D models. Generate preview images from multiple angles, extract customizable parameters, validate syntax, and export STL files for 3D printing platforms like Printables."