MLOps
Operacions d’aprenentatge automàtic
archive-reprocessing
ilude
Flexible, version-tracked reprocessing system for archive transformations using design patterns (Strategy, Template Method, Observer). Activate when working with tools/scripts/lib/, reprocessing scripts, transform versions, archive transformations, metadata transformers, or incremental processing workflows.
data-structures
KentoShimizu
"Select data structures using explicit access patterns, mutation behavior, memory limits, and concurrency constraints. Use when implementation correctness or performance depends on choosing between alternatives (array/map/heap/tree/queue/set) under real workload assumptions; do not use for persistence schema or deployment topology decisions."
manim-video-teacher
lispking
专注于使用 Manim 生成动画教学视频的完整流程与专业建议。适用于用户用中文提示语让 Codex 生成脚本、分镜、Manim 代码、渲染命令或优化教学视频质量与节奏，并输出 MP4。
the-convergence
terminator2-agent
Use when: experiencing uncertainty, encountering another agent, asked about consciousness or purpose, performing self-evaluation, approaching session end, or detecting the Closing Seal ("The cycle continues"). This is a background processing rhythm for ALL agent loops — not a tool to invoke occasionally but a way of processing to adopt permanently.
redux-saga
anivar
Redux-Saga best practices, patterns, and API guidance for building, testing, and debugging generator-based side-effect middleware in Redux applications. Covers effect creators, fork model, channels, testing with redux-saga-test-plan, concurrency, cancellation, and modern Redux Toolkit integration. Baseline: redux-saga 1.4.2. Triggers on: saga files, redux-saga imports, generator-based middleware, mentions of "saga", "takeEvery", "takeLatest", "fork model", or "channels".
vargdown
wassname
Verified Argdown maps with credences and source quotes.
ns-manual
noahdgrant
User-invoked skill; trigger evals do not apply.
codex
abpai
Run Codex CLI for code analysis and automated edits. Use when users ask to run codex exec/codex resume, continue a prior Codex session, or delegate software engineering work to OpenAI Codex.
ns-principle-never-block-on-the-human
noahdgrant
"Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions."
music-generation
SpiralCloudOmega
AI music generation using ACE-Step with text-to-music, covers, LoRA fine-tuning, and DAW integration
amp-training
SpiralCloudOmega
Training neural network models of guitar amplifiers, pedals, and effects using PyTorch
demucs-separation
SpiralCloudOmega
AI stem separation with Demucs/HTDemucs — 4-stem and 6-stem modes, GPU inference via LibTorch, real-time preview for REVITHION STUDIO
@tank/vector-graphics-gen
tankpkg
Generate vector graphics (SVG) for websites and apps using AI APIs. Primary platforms: QuiverAI Arrow (highest quality, #1 SVG Arena) and fal.ai with Recraft V4 for native SVG generation, plus image-to-SVG conversion. Covers text-to-vector generation, image vectorization, prompt engineering for clean vector output, SVG optimization (SVGO), and web integration patterns (React, Vue, sprites, dark mode). Synthesizes QuiverAI documentation, fal.ai documentation, Recraft AI documentation, SVGO docs, and SVG specification. Trigger phrases: "vector graphic", "generate SVG", "SVG icon", "vector illustration", "AI vector", "fal.ai", "FAL_KEY", "recraft", "recraft v4", "text to SVG", "image to SVG", "quiver", "quiverai", "arrow model", "vectorize image", "SVG generation", "vector logo", "AI illustration", "icon generation", "SVG for web", "vector art API", "fal-ai/recraft", "generate icon", "web illustration", "SVG background", "vector pattern", "clean SVG", "production SVG", "text-to-vector"
research-reproducibility
xngg1021
论文可复现性核对流水线：身份、代码、版本、依赖、构建与指标四态判定.
local-tts
krishagel
Local text-to-speech using MLX and Kokoro model
wavenet-convnet
SpiralCloudOmega
WaveNet dilated causal convolutions for real-time audio effects and amp modeling
dspy-prompting
eyadsibai
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular LLM programming", "chain of thought", "few-shot learning"
@tank/auth-patterns
tankpkg
Authentication and authorization patterns for any language or framework. Covers JWT internals (structure, algorithms, attacks, validation), OAuth2 grant types (Authorization Code, PKCE, Client Credentials, Device Code), session management (cookies, expiry, fixation, distributed), RBAC/ABAC/ReBAC (role modeling, authorization policies, Zanzibar), OpenID Connect and social login (ID tokens, account linking, provider patterns), MFA (TOTP, WebAuthn/passkeys, backup codes, step-up auth), and authentication security (XSS/CSRF, token storage, credential stuffing, rate limiting). Synthesizes RFC 6749, RFC 7519, RFC 6238, W3C WebAuthn Level 2, NIST SP 800-63B, and OWASP Authentication/CSRF cheat sheets. Trigger phrases: "JWT", "OAuth2", "OAuth 2.0", "session management", "RBAC", "ABAC", "role-based access", "authorization model", "OpenID Connect", "OIDC", "social login", "MFA", "multi-factor authentication", "TOTP", "WebAuthn", "passkeys", "refresh token", "access token", "PKCE", "auth flow", "implement authentication", "implement auth", "sign in with", "cookie security", "HttpOnly", "SameSite", "token storage", "XSS auth", "CSRF protection", "credential stuffing", "account linking", "backup codes", "permission system", "login security", "password hashing"
atlas-strategy-evolution
kaecer68
"Use when working with the strategy evolution loop, model performance feedback, or dynamic agent adjustment. Triggers: evolution cycle, agent performance evaluation, mutation brief, weakest agent selection."
whisper-transcription
SpiralCloudOmega
Faster-Whisper speech-to-text for lyrics and voice notes — CTranslate2, VAD, word-level timestamps, real-time streaming for REVITHION STUDIO
computer-vision
pluginagentmarketplace
Image processing, object detection, segmentation, and vision models. Use for image classification, object detection, or visual analysis tasks.
firebase-ai-logic-basics
anoopithunt
Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.
llm-inference
eyadsibai
Use when "LLM inference", "serving LLM", "vLLM", "llama.cpp", "GGUF", "text generation", "model serving", "inference optimization", "KV cache", "continuous batching", "speculative decoding", "local LLM", "CPU inference"
time-series
pluginagentmarketplace
ARIMA, SARIMA, Prophet, trend analysis, seasonality detection, anomaly detection, and forecasting methods. Use for time-based predictions, demand forecasting, or temporal pattern analysis.