Popular Coding & Development Skills

T

Tao Train Mask Auto Label

MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations

T

Tao Train Mask Grounding Dino

Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for

T

Tao Train Metric Learning Recognition

Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for

T

Tao Train Nvdinov2

NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation

T

Tao Train Pose Classification

Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences

T

Tao Train Reid

Person re-identification (ReID). Learns discriminative embeddings to match the same person across different

T

Tao Train Rtdetr

RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with

T

Tao Train Segformer

SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature

T

Tao Train Single Step

Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset

T

Tao Train Sparse4d

Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable

T

Tao Validate Dataset Format

Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do

T

Tilegym Adding Cutile Kernel

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.

T

Tilegym Converting Cutile To Julia

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when converting, porting, or translating cuTile Python kernels to Julia cuTile.jl, or debugging/optimizing existing Julia cuTile translations.

T

Tilegym Converting Cutile To Triton

Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.

T

Tilegym Cutile Python

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.

T

Tilegym Improve Cutile Kernel Perf

Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.

T

Tilegym Monkey Patch Kernels To Transformers

Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.

W

Warp Compile Time Optimizer

Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start or stalls at the first wp.launch; seconds of compiling before real work begins; JIT modules recompiling on every run or every CI job. Only applies when the code being optimized uses Warp kernels. Not for steady-state kernel runtime, memory, correctness, building Warp itself from source, or nvcc/C++ build times.

W

Warp Debug Gradients

Use to diagnose and fix incorrect gradients in differentiable Warp programs. Anything trained, optimized, calibrated, or fit through Warp kernels depends on wp.Tape gradients, so treat any misbehavior of such a workflow as a gradient problem until proven otherwise — use this when training diverges or NaNs, won't train at all, stalls or plateaus above the expected loss, converges to a wrong or biased answer, is worse than a reference implementation, works at small scale but fails at production scale, or fails a QA/validation recheck. Also for explicit symptoms — exploding, NaN/inf, zero, or subtly wrong gradients, suspected wp.Tape/backward issues, gradcheck failures — but users usually describe only the surface symptom ("the sim explodes", "the fit gets dragged toward outliers") without mentioning gradients: make that leap. Not for forward-only Warp work, build/install problems, or autograd issues in other frameworks without Warp.

C

Create Ideas

Generate ideas in one shot using creative sampling

D

Do In Steps

Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.

I

Implement Task

Implement a task step by step with automated LLM-as-Judge verification at the end of each phase

J

Judge

Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation

J

Judge With Debate

Evaluate solutions through multi-round debate between independent judges until consensus

L

Launch Sub Agent

Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification

M

Multi Agent Patterns

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

A

Actualize

Reconcile the project's FPF state with recent repository changes

A

Analyse

Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target

A

Analyse Problem

Comprehensive A3 one-page problem analysis with root cause and action plan

A

Analyze Issue

Analyze a GitHub issue and create a detailed technical specification

A

Apply Anthropic Skill Best Practices

Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure

A

Attach Review To Pr

Add line-specific review comments to pull requests using GitHub CLI API

C

Cause And Effect

Systematic Fishbone analysis exploring problem causes across six categories

C

Create Agent

Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns

C

Create Command

Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration

C

Create Hook

Create and configure git hooks with intelligent project analysis, suggestions, and automated testing

C

Create Pr

Create pull requests using GitHub CLI with proper templates and formatting

C

Create Rule

Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.

C

Critique

Comprehensive multi-perspective review using specialized judges with debate and consensus building

D

Decay

Manage evidence freshness by identifying stale decisions and providing governance actions

D

Do And Judge

Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop

D

Do Competitively

Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis

G

Git Worktrees

Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.

K

Kaizen

Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.

L

Load Pr Comments

Use to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.

M

Memorize

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

A

Agent Evaluation

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

P

Plan Do Check Act

Iterative PDCA cycle for systematic experimentation and continuous improvement