vercel-cli

Offload heavy builds, full test suites and parallel experiments from the local machine to Vercel Sandboxes with the `vercel sandbox` CLI. Use when a local machine is overloaded or shared by several agents, when a test suite should be sharded, or when many tasks should run side by side without consuming local CPU, memory or disk.

Vercel Agent guidance — dashboard and Slack chat, code review, production investigation, approved actions, and product installation. Use when configuring or working with Vercel's AI assistant.

Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation. Shared across Functions, Routing Middleware, and Builds. Use when implementing caching strategies beyond framework-level caching.

Vercel Routing Middleware guidance — request interception before cache, rewrites, redirects, personalization. Works with any framework. Supports Edge, Node.js, and Bun runtimes. Use when intercepting requests at the platform level.

Vercel's React and Next.js performance rules (70 rules in 8 categories ordered by impact - eliminating waterfalls, bundle size, server-side performance, client-side data fetching, re-renders, rendering performance, JavaScript performance, and advanced patterns). Use when writing, reviewing, or refactoring React components, Next.js pages, or data fetching for performance. Not an accessibility or TypeScript style guide.

Vercel Queues guidance — durable topics with at-least-once delivery, independent consumer groups, retries, delays, and idempotency keys via @vercel/queue (JS) or vercel-queue (Python). Use when deferring background work, buffering traffic, fanning out events, or choosing between Queues and Workflows.

Vercel Marketplace expert guidance — discovering, installing, and managing third-party integrations via the `vercel integration` CLI. Use when building any app that needs an external capability without a dedicated skill — commerce (stores, storefronts, selling products), payments (checkout, subscriptions, billing), observability/monitoring, messaging/email, search, or CMS — or when discovering, installing, or managing integrations.

Score how ready a website, domain, or public MCP endpoint is for AI agents using Is Agentic, and read or act on the resulting report. Use when asked to check a site's agent readiness, get its Is Agentic score, fetch a scored report as JSON, or fix the issues that lower a site's score.

Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module subsets based on each module's label eligibility. Use when the user asks to "route VCN gap samples", "split AOI gaps for k-NN mining and AnomalyGen", or prepare the immediate next step after DEFT gap analysis in a VCN AOI SDA iteration.

Port a published computer vision paper's official code and training recipe onto a customer's own dataset, or diagnose why such a transfer produced bad numbers. Use this whenever someone wants to reproduce a CV paper, run a paper's repo on their own images, fine-tune a published detection/segmentation/classification/keypoint model on customer data, adapt a training recipe to a new dataset, or figure out why a fine-tuned vision model scores well on validation but fails in production. Also use for post-mortems on any failed or disappointing CV training run, and whenever a user mentions mAP that looks too good, a model that "worked in training but not in deployment", or transferring hyperparameters from a paper to their own data. Trigger even if the user only says "train a model on my dataset" and a published architecture or repo is involved.

Run iterative improvement for NVIDIA TAO CLIP / SigLIP image-text retrieval on attribute-labelled data. Use when a request combines retrieval evaluation, weak-attribute or caption-pair mining, repeated retraining, and a stopping condition based on a retrieval KPI, validation plateau, or iteration budget; the customer need not know the DEFT or People Attribute Search (PAS) names. The self-contained workflow performs dataset preparation, zero-shot evaluation, attribute gap analysis, caption-space k-NN mining, history-aware selection, retraining, and re-evaluation. Treat `tao-deft-pas` as shorthand for this canonical `tao-run-deft-pas` workflow. Do not use for standalone CLIP training, one-off evaluation or embedding, generic k-NN mining, or AOI/ChangeNet DEFT workflows.

Run the full DEFT smart-data-augmentation loop for NVIDIA TAO Grounding DINO object detection: zero-shot baseline inference, KPI analysis, per-class gap analysis, SigLIP embedding of weak images, unique-neighbor mining against a source pool, ODVG dataset staging, and retraining — repeated for a fixed number of iterations. Also prepares the source pool the loop mines from, as a separate run: Co-DETR pseudo-labeling, folding to the target classes, KITTI→COCO→ODVG conversion, and embedding. Use for prompts like "run the DEFT OD loop", "run smart data augmentation for grounding dino", "mine and retrain my detection model", "improve OD mAP with gap analysis and mining", "prep the source pool", or "pseudo-label my unlabeled images for mining"; do not use for standalone TAO training, one-off inference, or gap analysis alone.

Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ gaps", "extract VLM false positives and false negatives", or identify failure cases from a predictions JSON for DEFT root-cause analysis on a binary-classification VLM workflow.

Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary cases.

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.

Kumo-Anomaly — diffusion-based anomaly detection and fine-tuning for multivariate time series. Use when the user asks to "fine-tune Kumo-Anomaly", "run Kumo-Anomaly inference", "detect anomalies with diffusion", "time series anomaly detection", "finetune Kumo-Anomaly", "use perform_anomaly_analysis_with_diffusion", "automl Kumo-Anomaly", "hyperparameter search Kumo-Anomaly", "hyperparameter optimization" or mentions "curriculum_medium.yaml", "final_model.pth", "kumo-anomaly", "sdk/anomaly_analysis", or "TSDiffuser_Generic".