Parallel sub-tasks within skills and across skill families should produce parallel outputs for legibility.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• A skill's output length should match task complexity—short tasks produce short reports, long tasks produce structured hierarchical reports.claim0.821
• Skills should interconnect with each other rather than operate independently; output of one feeds another.claim0.820
• A skill should do its work and stop, avoiding performative complexity and multi-stage flows when single-pass suffices.claim0.804
• Parallel programming needn't be terribly difficult, but 'thinking in simultaneities' as in message-passing is calculated to make it difficult.claim0.798
  Asserts that Linda's uncoupled style reduces cognitive load.
• Pure functional languages cannot be the whole story for parallel programming because they fail to provide needed expressivity.claim0.793
  Argument that recursion equations are inappropriate for many important parallel programs.
• For a given task, the number of all sequences which work is tiny by comparison with the huge number of all possible sequences; less than a trillionth of all 6 × 10^23 possible sequences actually work well enough.claim0.792
  A combinatorial argument that good sequences are astronomically rare, emphasizing the difficulty of discovery.
• A skill works at multiple reinforcing scales: individual command, skill invocation, and user project.claim0.786
• Training identical architectures on the same data with different objective functions should produce systematically different internal evaluative representations, detectable through interpretability tools, even when final task performance is matchedhypothesis0.777
  Second falsifiable prediction linking objective function structure to valence profile