Loading...
Loading...
Found 105 Skills
Run Playwright smoke tests, debug failures, and verify fixes
Post-restart smoke tests + auto-fix for gbrain and OpenClaw environments. Tests critical services, auto-fixes known issues, extensible via user-defined test scripts in ~/.gbrain/smoke-tests.d/*.sh.
Create a Mastra project using create-mastra and smoke test the studio in Chrome
Run interactive smoke tests for voxtype. Tests recording cycles, CLI overrides, signal handling, and service management. Use after installing a new build.
Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real `data/` source and predicts on a *disjoint* portion that deliberately carries **no pre-history buffer**. The assertion is structural — the number of predictions must equal the number of rows in the predict grid. A pipeline that loads-then-features-then-splits will silently drop the cold-start rows of the predict slice and the test will fail with a row-count mismatch; a pipeline that marks X early and references upstream history nodes from feature steps will pass trivially. The smoke test is the executable proof of the X-marker placement rule from `build-ml-pipeline`. TRIGGER when: `test-ml-pipeline` has dispatched here to write the smoke test for an approved experiment; `pytest tests/smoke/` is failing on row count; the user asks "why is the smoke test failing?"; a pipeline edit in `build-ml-pipeline` needs an executable proof; an experiment script changes the pipeline shape and the matching smoke test needs revisiting. SKIP when: the design note does not exist or is not yet approved (route to `iterate-ml-experiment`); the user is asking about a regression test or schema invariant (route to `regression-test-ml-pipeline` / `distribution-test-ml-pipeline` once those exist); the question is the *interpretation* of CV metrics, not predict-time correctness (route to `evaluate-ml-pipeline`). HOW TO USE: read the matching experiment's `journal/NN_*.md` and `experiments/NN_*.py` first to understand the pipeline's source binding (what env-dict keys does `build_learner` expect?). Then construct two env-dicts from the **real `data/` source** — a train env and a predict env — such that the predict env carries *only the rows we want predictions for* and *no pre-history buffer*. The hard assertion is that the prediction count matches the predict-env row count exactly. The soft assertion is that the smoke set's MAE is within `3 × CV_mean` (or the task-appropriate analogue). **Do not write the design note or run CV — that's other skills' job.**
Launch the app and hands-on verify that changes work by interacting with it. Use when the user asks to "smoke test", "test it manually", "verify it works", "try it out", "run a smoke test", "check it in the browser", or "does it actually work". Not for unit/integration tests.
Start the dev server, discover API routes from the codebase, hit every endpoint, and report which ones return errors.
Use this temporary smoke-test skill to verify skills.sh indexing and download snapshot behavior for a fresh UnifAPI agent skills repository.
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / LLM model end-to-end, generate a reproducible HF training pipeline, smoke-test a HuggingFace model locally before scale-up, push a fine-tuned model to the HF Hub with a model card, or emit a self-contained rerun skill for an existing HuggingFace finetune. Supports image classification, object detection, semantic / instance / panoptic segmentation, depth estimation, image-text-to-text VLM (SFT / LoRA), and LLM SFT / DPO / GRPO. Six-step workflow: inspect and qualify, hardware and NGC image, research, generate and smoke, train + eval + infer, push and emit rerun skill.
Apply when installing, publishing, upgrading, or rolling back a VTEX IO storefront theme app (`vendor.store-theme` or any app that owns `store/blocks.json`, `store/routes.json`, and `store/contentSchemas.json`). Covers how Site Editor and theme content are scoped by the app's MAJOR version, why a major version bump leaves the new major with no merchant content and silently falls back to default theme content, the safe install-in-workspace, migrate- content with the `updateThemeIds` mutation, smoke-test, then promote workflow, the 3-way mine-wins merge that `vtex workspace promote` performs against `vtex.pages-graphql` VBase (with automatic per-minute `userData_backup` snapshots when conflicts are resolved), and the support-led recovery path. Use for any operation that changes which version of a content-holding app is installed in `master`.
Use when selecting, installing, configuring, smoke-testing, documenting, or troubleshooting MCP servers for academic search, arXiv, Semantic Scholar, OpenAlex, Crossref, PubMed, Zotero, Overleaf, Google Scholar, paper metadata, or scholarly source tooling.
Verifies a Taubyte Go function locally via the `taubyte/go-wasi` Docker recipe (preferred over `tau build`, with tmpfs+bind-mount-ro to avoid root-owned artifacts in the source tree), and verifies a function actually serves on Dream by curling the gateway with the right `Host:` header (plus `/etc/hosts` mapping for `*.localtau`). Use when locally compiling a Go function to WASM, when smoke-testing a function before pushing, or when probing a Dream-hosted HTTP function from the laptop.