Loading...
Loading...
Found 10,569 Skills
Generates a Jupyter notebook that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, and RLVR trainers, including RLVR Lambda reward function creation.
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches across nodes, planning upgrades, documenting cluster configuration, or troubleshooting version-related issues on HyperPod. Triggers on requests about versions, compatibility, component checks, or upgrade planning for HyperPod clusters.
Generates a Jupyter notebook that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. Use when the user says "deploy my model", "create an endpoint", "make it available", or asks about deployment options. Identifies the correct deployment pathway (Nova vs OSS), generates deployment code, and handles endpoint configuration.
Search the web with DuckDuckGo as a no-API-key fallback or second source. Use when the normal web search tool or primary search provider is rate-limited, failing, unavailable, not delivering enough useful results, or producing weak results, and you want quick text, news, image, or video search results, instant-answer lookups, or DuckDuckGo bang resolution without browser automation.
[AUTO-INVOKE] MUST be invoked BEFORE creating git commits, PRs, or code reviews. Covers Conventional Commits, PR templates, review requirements, and AI-assisted development rules. Trigger: any task involving git commit, git push, PR creation, or code review.
Use when breaking work into discrete steps, tracking progress through multi-step implementations, or managing implementation task lists. Triggers when an approved plan needs to be converted into tracked tasks, when progress reporting is needed during execution, or when checkpoint reviews are required between task batches.
Use when validating that implementation meets specification requirements — applies acceptance-driven backpressure with behavioral validation gates that prevent completion claims without passing tests. Triggers: spec-to-code validation, feature completion verification, pre-merge acceptance gate, release readiness check.
Use when running autonomous loops, repeated operations, or when detecting stagnation patterns - enforces rate limits, protects configuration files, manages recovery with cooldown periods, and prevents infinite loops during autonomous development
Use when the user needs standalone HTML/CSS/JS artifacts — interactive demos, prototypes, single-file applications, or visual tools that run independently in a browser. Triggers: user says "artifact", "demo", "prototype", "single-file app", "HTML tool", "interactive widget", "standalone page", building something that runs in a browser without a build step.
Use when validating subjective quality criteria that cannot be deterministically tested — applies LLM-based evaluation with structured rubrics for tone, aesthetics, UX feel, documentation quality, and code readability. Triggers: documentation quality check, error message tone review, UX copy evaluation, code readability assessment, design aesthetic review.
Use when completing work on a feature branch, preparing to merge, or cleaning up after development is done. Triggers: branch work is complete, user says "merge", "create PR", "finish branch", "done with this branch", ready for code review.
DefiLlama API integration for DeFi analytics - TVL, stablecoin yields, vault/APY ranking, protocol revenue, fees, DEX volume, chain flows, bridges, and treasury data. Best for DeFi research, stablecoin farming, yield strategy screening, and protocol/chain market intelligence.