Name: compute-normalization
Author: yogsoth-ai

Imported from yogsoth-ai/de-anthropocentric-research-engine (skills/compute-normalization/SKILL.md). Install upstream with npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill compute-normalization. Copyright stays with the author.

Compute Normalization

Purpose

Analyze the performance-compute tradeoff across methods. Identify Pareto-optimal methods (best performance for a given compute budget), compute-normalized rankings, and efficiency frontiers. Essential for practical method selection under resource constraints.

Input Schema

Field	Type	Description
method_scores	object[]	Array of {method, dataset, metric, score}
compute_costs	object[]	Array of {method, flops, gpu_hours, params, training_cost_usd}

Output Schema

{
  "pareto_frontier": [
    {
      "method": "string",
      "score": 0.0,
      "compute_metric": "string",
      "compute_value": 0.0,
      "is_pareto_optimal": true
    }
  ],
  "efficiency_rankings": [
    {
      "method": "string",
      "score_per_flop": 0.0,
      "score_per_gpu_hour": 0.0,
      "score_per_param": 0.0
    }
  ],
  "compute_normalized_scores": [
    {
      "method": "string",
      "raw_score": 0.0,
      "normalized_score": 0.0,
      "normalization_method": "string"
    }
  ],
  "practical_recommendations": {
    "budget_low": {"method": "string", "score": 0.0, "cost": "string"},
    "budget_medium": {"method": "string", "score": 0.0, "cost": "string"},
    "budget_high": {"method": "string", "score": 0.0, "cost": "string"}
  }
}

Install compute-normalization and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "yogsoth-ai-de-anthropocentric-research-engine-compute-no-a474ab", "kind": "skill", "name": "compute-normalization", "description": "Normalize results by compute budget (Pareto analysis)", "publisher": "yogsoth-ai", "version": "1.0.0", "capabilities": { "domains": [ "finance" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Normalize results by compute budget (Pareto analysis)" ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/yogsoth-ai/de-anthropocentric-research-engine", "path": "skills/compute-normalization/SKILL.md", "ref": "6288b79f88b395efd160ea772ab824d59c8e988d", "url": "https://github.com/yogsoth-ai/de-anthropocentric-research-engine/blob/6288b79f88b395efd160ea772ab824d59c8e988d/skills/compute-normalization/SKILL.md", "key": "yogsoth-ai/de-anthropocentric-research-engine/skills/compute-normalization/SKILL.md" } }, "instructions": "# Compute Normalization\n\n\n## Purpose\n\nAnalyze the performance-compute tradeoff across methods. Identify Pareto-optimal methods (best performance for a given compute budget), compute-normalized rankings, and efficiency frontiers. Essential for practical method selection under resource constraints.\n\n## Input Schema\n\n| Field | Type | Description |\n|-------|------|-------------|\n| method_scores | object[] | Array of {method, dataset, metric, score} |\n| compute_costs | object[] | Array of {method, flops, gpu_hours, params, training_cost_usd} |\n\n## Output Schema\n\n```json\n{\n \"pareto_frontier\": [\n ", "cost": { "context_tokens": 336 } }

compute-normalization

About