Results for “model-ranking”

Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings.

Queries Hugging Face benchmark leaderboards to find the best AI models for a task, filters by device constraints, and returns a ranked comparison table with scores.

Manage machine learning models in the Agent Platform Model Registry: list, describe, upload, update, and delete models and their versions.

Use the model-recommender skill, Workflow C (Roster Refresh), to research and update the model roster from live benchmarks.

Every metric encodes an opinion about which mistake hurts.

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.

Cross-model benchmark for gstack skills. (gstack)

TRAK: Attributing Model Behavior at Scale

Rank an existing set of context chunks by relevance, diversity, freshness, and utility. Use when retrieval has already produced candidates that must be scored or reranked; use context-retrieval when the source corpus still needs to be searched.

Design and implement evaluation harnesses for models, agents, and code. Use when creating benchmarks, designing eval metrics, or comparing system outputs.

Ranks any list of impediments and their countermeasures using a value-stream scoring model (ROI, Cost to Implement, Ease of Deployment, Risk Factor) and a fixed prioritization formula.

Fine-tune open models or Gemini models using Agent Platform infrastructure, from environment setup through data preparation, job configuration, monitoring, and deployment.

Rank a backlog of feature ideas by impact, effort, risk, and strategic alignment to identify the top 5 to pursue.

Filters and ranks trending Hugging Face models, datasets, and spaces by novelty and significance, providing a 'why notable' explanation for each pick.

Prioritize product work with explicit criteria, scoring, tradeoffs, and decision rationale.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

The layers trade timeliness against definitiveness.

Pricing model design, competitive positioning, value metric selection, price testing, and pricing page optimization. Use when the user asks about pricing strategy, pricing models, price testing, value-based pricing, or competitive pricing analysis.

Research latest Claude models and update selection guide — run when new models drop or periodically to stay current

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.

Provides a single 0-100 cycle score blending VIX, SPY IV Rank, Put/Call ratio, and valuation percentile to determine offense vs. defense posture, based on Howard Marks' market cycle framework.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session.

Compare a product against alternatives by positioning, capabilities, gaps, and strategic moves.

Recommend model families and validation strategy based on data, constraints, and objective. Use when: (1) choosing algorithms, (2) balancing bias/variance, (3) planning benchmark baselines. NOT for: final legal/compliance sign-off.

Rank a topic's user-flow branches by proof priority (value × risk × frequency) right after user-flow-map, ordering the branches, gating variation breadth, and promoting or pruning flows so state-model and ux-variations grow the tree in proof order — writes only existing flow-tree ordering fields, no schema change.

Scores competitors across nine weighted dimensions with explicit 1–5 rubrics and a tension plot, producing comparable profile cards for competitive analysis.

Cardinality and model family jointly determine the encoding.

LoRA: Low-Rank Adaptation of Large Language Models

Compute TAM/SAM/SOM with top-down and bottoms-up methods, plan survey sample sizes with per-segment minimums, and score candidate segments against Kotler's five criteria.

Pick the right business-model canvas (Lean Canvas, Business Model Canvas, or Value Proposition Canvas) for the stage and fill it with specifics — one segment, one primary canvas, top-3 assumptions, no fluff in the moat or channel boxes. Load when the user asks to fill a business model canvas, lean canvas, value proposition canvas, model this business, map the business model, says "fill the BMC", "make a Lean Canvas", "Value Proposition Canvas for this", "model this idea", "what's the business model", "design the business model". Sub-skill of `venture-exploration`. Hard-bans "everyone" segments, generic channels ("SEO/social/content/ads"), and "unfair advantage = AI/data/network effects" with no concrete asset. Does NOT score viability — for that use `idea-evaluation`.

Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpoint recommendations for overfitting.

`task-agent`/`review-agent`: use when CPU, memory, I/O, database, network, rendering, or cost needs measured bottleneck evidence; skip without a profiling need.