Loading...
Loading...
Found 163 Skills
Behavioral guardrails for Cavekit agents. Four principles — think before coding, simplicity first, surgical changes, goal-driven execution — that prevent over-engineering, silent assumptions, scope creep, and unfocused work. Every task-builder, reviewer, planner, and inspector must internalize these before writing a single line. Trigger phrases: "guardrails", "karpathy", "scope creep", "over-engineering", "stop adding features", "surgical fix".
Run and interact with KarpathyTalk, an open markdown-based developer social network with GitHub auth, SQLite, and an LLM-friendly JSON/markdown API.
Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals. Triggers on "review my diff", "check complexity", "am I overcomplicating this", "karpathy check", "before I commit", or any code quality concern where the LLM might be overcoding.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Research tool for visually exploring BLS Occupational Outlook Handbook data with an interactive treemap, LLM-powered scoring pipeline, and data scraping/parsing utilities.
Use when normal web_fetch cannot read a page, when a site blocks basic fetching, or when the user needs YouTube content in AI-ready form. Guides fallback use of Firecrawl for single-page web scraping and SerpApi for YouTube search/video metadata/transcripts only.
Write competitive research proposals for NSF, NIH, DOE, and DARPA. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.
Design and implement straight-through processing and operational automation for securities operations. Use when measuring STP rates and identifying manual touchpoints in an existing process, replacing review-all workflows with exception-based processing, selecting automation patterns for account opening trade processing settlement reconciliation or billing, designing integration between portfolio management custodian CRM and order management systems, building exception queuing categorization and auto-resolution workflows, evaluating RPA vs API-based vs hybrid automation for legacy systems, establishing operational controls and audit trails for automated environments, conducting process mining or root cause analysis on exception volumes, or setting STP rate targets and continuous improvement programs.
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. This is the default entry point for any "run the AOI workflow", "fine-tune my PCB AOI model end-to-end", "improve my AOI ChangeNet model", or "AOI workflow with AutoML" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. "run JUST the DEFT loop", "skip AutoML, only DEFT"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include "run the AOI workflow", "AOI end-to-end", "AutoML + DEFT", "AutoML then DEFT", "tune hyperparameters then DEFT", "DEFT with AutoML at both ends", "warm-start DEFT", "improve my AOI model".
Guidance for training FastText text classification models with constraints on model size and accuracy. This skill should be used when training FastText models, optimizing hyperparameters, or balancing trade-offs between model size and classification accuracy.
Run AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter optimization, HPO, automl, automl_settings, AutoMLRunner, tao_automl, bayesian search, hyperband, ASHA, LLM-guided search, autoresearch, or wants to tune training hyperparameters for any TAO network. Platform-agnostic — runs on any SDK (Lepton, Brev, SLURM, Kubernetes, Docker).
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and experiment-craft (5-step diagnostic on failure). Use when: user has a planned experiment, needs to reproduce baselines, organize experiment workflow, or systematically validate a method. Do NOT use for debugging a specific experiment failure (use experiment-craft) or designing which experiments to run (use paper-planning).