Skill catalog

Convert an ML research paper into a complete, runnable code repository. 3-stage pipeline from Paper2Code — Planning (UML + dependency graph) → Analysis (per-file logic) → Coding (dependency-ordered generation). Use for…

Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement. Use when the user runs /si:promote or asks to make a learned behavior permanent.

DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features, and optional distillation support. Use when training, evaluating, expor…

Help users make better hiring decisions. Use when someone is evaluating job candidates, making hiring decisions, conducting reference checks, reviewing work samples or take-homes, calibrating their hiring bar, or decidi…

Apply seamless infinite marquee loops using duplicated items.

RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, ev…

Betting analysis — odds conversion, de-vigging, edge detection, Kelly criterion, arbitrage detection, parlay analysis, and line movement. Pure computation, no API calls. Works with odds from any source: ESPN (American o…

Use when auditing content quality, E-E-A-T, or publish readiness; runs a typed 80-item CORE-EEAT profile with evidence coverage, veto checks, and a fix plan. Not for structural tags/headers alone — use on-page-seo-check…

Write ML experiment code with iterative improvement. Generate training/evaluation pipelines, debug errors, and optimize results through code reflection. Use when implementing experiments for a research paper.

Apply an emotional resonance lens to a UI that is technically correct but flat, prescribing changes at the copy, motion, and interaction layer. Use when a design tests fine but lands cold. For the polish-perception argu…

Use this skill whenever the user wants to integrate Loops from application code, backend services, webhook handlers, or server-side automation. This includes the Loops HTTP API and official SDKs for server-side contact,…

Help users design effective organizational structures. Use when someone is thinking about team structure, deciding between functional vs. divisional models, planning a reorg, or figuring out how to structure product tea…

Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation results. Use when training, evaluating, exporting, quantizing, or ru…

Analyse video content by extracting frames with ffmpeg and using AI vision to generate timestamped step-by-step summaries. Use when user provides a video file and wants to understand its visual content — screen recordin…

Use when designing visual motion systems, creating animation specifications, or when a designer needs guidance on crafting beautiful, meaningful movement.

Use when a project keeps its state in Superself (a `<!-- superself:begin` block in AGENTS.md or CLAUDE.md, or `self setup` resolves the directory to a registered project): read `self context` at session start, attach wo…

Local or remote Docker execution for TAO SDK job containers using a Docker daemon with NVIDIA GPU runtime. Use when running TAO jobs on the current machine, a directly attached Docker host, or a remote GPU box exposed t…

NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone with a Mask2Former-…

Use this when the page-import pipeline needs to determine the authoring approach (default content vs blocks) for scraped content before generating import HTML for AEM Edge Delivery Services. Covers validating block sele…

Guidelines for implementing JWT authentication with security best practices for token creation, validation, and storage

Use this when the page-import pipeline needs to analyze the content sequences within a single section and describe them neutrally for AEM Edge Delivery Services. Covers identifying breaking points between default conten…

Package and release a finished game mod. Covers the pre-release lint (no game files, decompiled code or leaked keys), README and install steps, credits and AI disclosure, versioning, where to upload (Nexus Mods, Steam W…

Use when designing or reworking a Roblox game: core loop, tutorial/FTUE, levels, economy, retention phases, juice, grind, curation.

Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and deployment gating…

NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels and produces general-purpose visual features. Use when training, exporting,…

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

Orchestrate the full paper pipeline end-to-end. Manage state propagation between phases (literature → plan → code → experiments → figures → tables → writing → review), support checkpointing and resumption. Use for assem…

Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distilla…

Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g., retail product recognition) using triplet / contrastive losses. Use when training, evalua…

Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection, comparing image pa…

Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt worke…

Optimize an app's store listing for maximum visibility and downloads — keyword strategy, title and subtitle optimization, screenshots, preview videos, rating and review management, and A/B testing on the App Store (iOS)…

Use when designing or costing an AWS architecture (serverless, Lambda, API Gateway, DynamoDB, ECS, Aurora, CloudFormation, migration to AWS). Designs it with architecture_designer.py, generates stacks with serverless_st…

Choosing the right concurrency abstraction in .NET - from async/await for I/O to Channels for producer/consumer to Akka.NET for stateful entity management. Avoid locks and manual synchronization unless absolutely necess…

CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object pose estimation. Use when training, evaluating, exporting, or running inference for a TAO CenterPose mo…

SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time segmentation tasks. Use when training, evaluating, exporting, quantizing, or…

Use when building, fixing, or improving ANY SwiftUI UI — views, navigation, layout, animations, gestures, debugging, iOS 26 features, iPhone Duo, view-level performance, feature architecture.

Control the user's real Safari browser on macOS through AppleScript, page JavaScript, screenshots, and carefully verified System Events input. Use when an agent needs to inspect or operate the user's existing Safari tab…

A skill to build and manage Home Assistant configurations. Use when using the Home Assistant Builder (`hab`) CLI to inspect, create, update, delete, operate, or troubleshoot Home Assistant resources; when a user mention…

Independently reviews findings and filters out false positives. Use when consolidated findings need validation against the actual source code. Don't use for reproducing crashes or patching code.

Use this when you need to preview and verify content you imported into a local AEM Edge Delivery Services (EDS, Franklin, Helix) dev server on localhost. Starts the dev server against the imported HTML, checks block ren…

This skill should be used when the user asks to "write a fragment shader", "make a GLSL gradient/noise/plasma background", "create an image transition (dissolve, displacement, glitch)", "add distortion or chromatic aber…

Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset without iterative data augmentation, AutoML, or DEFT loops. Trigger phrases include "single train run", "trai…

Expert skill for using DeepSeek-OCR, a vision-language model for optical character recognition with context optical compression supporting documents, PDFs, and images.

Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. Use when…

Vitess best practices, query optimization, and connection troubleshooting for PlanetScale Vitess databases. Load when working with Vitess databases, sharding, VSchema configuration, keyspace management, or MySQL scaling…

Performs a full AWS Well-Architected Framework review evaluating every framework question across all pillars discovered from the live AWS documentation by analyzing code, IaC, and configurations to produce evidence-back…

Generate FFmpeg commands from natural language video editing requests - cut, trim, convert, compress, change aspect ratio, extract audio, and more.

Synthesizes raw learnings and codebase analysis into an interlinked Markdown Knowledge Base (KB). Use at the beginning of a loop to build or update architecture.md, entities, and vulnerabilities. Don't use for generatin…

Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations; supports pretrain and finetune stages. Use when training, evaluating…