Results for “tiered-model”

Proposal pricing workflow producing defensible line-item, tiered, or value-based pricing with calibration and sanity checks. Use when the user needs a quote, estimate, tier packages, pricing strategy, rate calibration, or discount modeling for a proposal brief. Triggers: 'price this proposal', 'build tiered pricing', 'line-item estimate', 'value-based price', 'calibrate rates', 'sanity check this quote'.

Use to design VIP or tiered support programmes and to test whether higher tiers actually deliver better outcomes. Trigger for "VIP support programme", "service tiering", queue priority for premium customers, entitlement vs priority, tier inflation, or "does our enterprise tier get faster support".

Trains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Multi-tiered memory management (HOT/WARM/COLD) for context compaction. Invoke ONLY for explicit compaction events: post-`/compact` cleanup, MEMORY.md tier promotion, archive batch, or "trim my context". NOT for general recall (use deep-recall) or routine memory writes (use storage-router). Triggers: "compact memory", "promote to durable", "archive old context", "tier this".

Plan which model tier handles which work BEFORE execution begins — a high-cognition model deeply understands the problem, lays the foundations, then emits a modular plan assigning each module the cheapest tier that can safely execute it, with escalation tripwires and one-way-door protection. Advisory only: it announces "next module → tier X / model Y" at each boundary and the HUMAN switches models — harnesses like Cursor cannot switch mid-run. Load when the user asks which model to use, wants a model plan, model tiers, model-tier routing, assign models to tasks or modules, says "cheap model got stuck", "which model for this task", "cost-efficient model choice", or when implementation-plan / problem-to-plan need a model: tier column. NOT dynamic-routing (plan-path selection after failure) — this skill assigns cognition tiers to work.

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

Complete Pump protocol fee system — tiered protocol fees based on market cap, creator fee collection across two programs, basis point arithmetic, and ceiling division for dust-safe calculations.

The layers trade timeliness against definitiveness.

Tier vocabulary from a text or topic into everyday, academic, and technical categories with teaching priorities. Use when pre-teaching vocabulary or identifying language barriers in a text.

v5.6.0 joint multi-TF model: single model per symbol with broadcast 1Hour context replaces dual 15Min/1Hour models. Trigger: (1) replacing weighted-voting model aggregation, (2) adding broadcast features to vectorized env, (3) limited training data + worried about overfitting from doubling obs_dim, (4) backtest builder mismatch with newer feature counts.

Transforms scattered competitor data into a decision-ready product strategy report with positioning maps, feature matrices, pricing analysis, and opportunity windows.

Performs STRIDE-A threat model analysis of repositories and systems, producing architecture overviews, DFD diagrams, prioritized findings, and executive assessments. Supports both single analysis and incremental updates with change tracking.

Train, evaluate, distill, quantize, export, and run inference for PyTorch-based TAO image classification models with support for multiple backbones.

Train, evaluate, distill, quantize, export, and run inference for RT-DETR object detection models using NVIDIA TAO.

Train, evaluate, export, quantize, and run inference for a Deformable DETR 2D object detection model using TAO, with deformable attention for efficient multi-scale feature processing.

DEPRECATED in v5.6.0 — see joint-multi-tf-v560 skill. Documents the v5.2.0 dual-model approach (train separate 15Min/1Hour models, combine via weighted voting). Still relevant for: (1) loading legacy v5.5.0 dual models, (2) understanding the historical aggregation layer, (3) resampling pattern via origin='start'.

Design and evaluate paid-ad experiments with hypotheses, randomization, sample-size calculations, guardrails, and decision rules for A/B and split tests.

Recommend the right AI model for a task by scoring candidates across six dimensions (Reasoning, Engineering, Speed, Breadth, Reliability, Governance) and displaying a spider-chart profile.

Pricing models, tier packaging, and willingness-to-pay research. Use when the user requests 'pricing tiers', 'freemium', 'value metric', 'pricing page', 'willing to pay', or 'van Westendorp'.

STRIDE Threat Model

Creates and manages design tokens with a three-layer architecture (primitive, semantic, component), generates CSS variables and component specifications, and produces brand-compliant slide presentations with Chart.js integration.

TRAK: Attributing Model Behavior at Scale

Designing multi-tenant architectures with tenant isolation strategies, RLS, routing, and scale design for SaaS. Use when designing multi-tenant SaaS systems or tenant isolation.

Models cascading what-if scenarios across all business functions to prepare for compound adversity, using a structured six-step framework that maps variables, domain impacts, cascade effects, severity levels, early warning signals, and hedging strategies.

Patterns for H5AD-backed Shiny apps with Excel fallback, groovy data in .uns, scVI QC validation, Leiden clustering merge, per-donor tissue extraction

Layer 0 of the keyword research pipeline. Builds a topic-graph snapshot for the brand's category before any seed work, approximated from Semrush phrase_related + phrase_questions on the category seeds plus the brand's own ranking footprint (domain_organic_unique). Idempotent on brand-config hash; never blocks the pipeline; cheap.

Generates award-level UI with GSAP motion, bento grids, and Python-driven randomization for layout variety.

Builds and governs design systems with a three-layer token architecture, component specs, and design-to-code handoff, including slide generation.

Design user flows and screen structure using UX patterns like progressive disclosure, hub-and-spoke navigation, and information pyramids to create coherent user journeys before building screens.

Evaluates text-to-image models on spatial relationship accuracy using the VISOR metric, separating object detection from spatial correctness to reveal biases like object priority and merging.

Evaluates prospective partnerships by classifying partner tier, designing a 90-day joint GTM plan, modeling revshare economics, and surfacing kill criteria for under-performing partnerships.

Deploy a trained model to serving with versioning, shadow or canary rollout, and a tested rollback path.

Selects pricing models (subscription, usage-based, value-based, freemium, hybrid), analyzes willingness-to-pay survey data with Van Westendorp PSM, and designs Good/Better/Best packaging tiers with anti-pattern detection.