Loading...
Loading...
Found 911 Skills
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.**
Display colorful ANSI art of the word "ultrathink". Use when the user says "ultrathink" or invokes /ultrathink.
Create world-class, accessible, responsive interfaces with sophisticated interactive elements including chat, terminals, code display, and streaming content. Use when building user interfaces that need professional polish and developer-focused features.
Comprehensive PDF processing and manipulation. Creates, extracts, merges, splits, and transforms PDF documents with full format support.
Tactical negotiation framework based on Chris Voss's "Never Split the Difference." Use when preparing for negotiations, during live negotiation scenarios, analyzing counterpart behavior, crafting responses to difficult conversations, handling objections, salary/contract negotiations, or when asked about negotiation techniques like mirroring, labeling, calibrated questions, or the Ackerman method.
WatermelonDB models, observation patterns, and React integration. Use when writing or debugging model code, observers (findAndObserve, query.observe), or screens that display live-updating DB data.
Zoho Books and Zoho Inventory API integration for TSH Clients Console. Use when: (1) Creating new API routes that call Zoho endpoints (2) Debugging API errors, token issues, or rate limits (3) Adding new Zoho data fetching functions (4) Understanding OAuth token caching with Upstash Redis (5) Working with products, orders, invoices, payments, or credit notes (6) Troubleshooting "Contact for price" or stock display issues
Break a failing complex AI task into reliable subtasks. Use when your AI works on simple inputs but fails on complex ones, extraction misses items in long documents, accuracy degrades as input grows, AI conflates multiple things at once, results are inconsistent across input types, you need to chunk long text for processing, or you want to split one unreliable AI step into multiple reliable ones.
Builds dashboards, reports, and data-driven interfaces requiring charts, graphs, or visual analytics. Provides systematic framework for selecting appropriate visualizations based on data characteristics and analytical purpose. Includes 24+ visualization types organized by purpose (trends, comparisons, distributions, relationships, flows, hierarchies, geospatial), accessibility patterns (WCAG 2.1 AA compliance), colorblind-safe palettes, and performance optimization strategies. Use when creating visualizations, choosing chart types, displaying data graphically, or designing data interfaces.
Displays progress dashboard showing phase completion, blocked tasks, and remaining work estimate. Provides at-a-glance view of implementation status. Run anytime to check progress.
Help developers integrate Apple MapKit into iOS/macOS apps. Use this skill when users ask to add a map to their app, display maps, show user location on a map, add markers/pins/annotations, implement map clustering, get directions/routing between locations, search for places/points of interest, implement MapKit features, work with MKMapView, SwiftUI Map, MKAnnotation, MKOverlay, MKDirections, MKLocalSearch, or any MapKit-related development task.
Split git changes into context-based micro-commits