A skill's output length should match task complexity—short tasks produce short reports, long tasks produce structured hierarchical reports.

{
  "doc": "/Users/antonborzov/Documents/Research.nosync/alexander/applied/agent-harness-design.md",
  "claim": "A skill's output length should match task complexity—short tasks produce short reports, long tasks produce structured hierarchical reports.",
  "vector": "alexander-s-15-properties-in-digital-conscious-space",
  "section": "Property-by-property sketch: 6. Good Shape",
  "extracted_at": 1778899491,
  "extracted_by": "haiku-4-5",
  "supporting_refs": [
    "concise-over-elaborate principle"
  ]
}