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

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

• Parallel sub-tasks within skills and across skill families should produce parallel outputs for legibility.claim0.821
• 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.claim0.790
  A combinatorial argument that good sequences are astronomically rare, emphasizing the difficulty of discovery.
• A skill should do its work and stop, avoiding performative complexity and multi-stage flows when single-pass suffices.claim0.779
• A skill works at multiple reinforcing scales: individual command, skill invocation, and user project.claim0.771
• Skill output should contain no filler; every line of a run-summary should carry weight.claim0.763
• Skills should interconnect with each other rather than operate independently; output of one feeds another.claim0.761
• Scale is sufficient but not necessarily efficient to reach high levels of intelligence; different methods can scale with different efficiency levelsclaim0.758
  Implication of PRH for 'scale is all you need' argument
• Task difficulty moderates whether CoT is performative or genuine: easy recall questions show performative CoT, difficult multihop questions show genuine reasoningclaim0.752
  Task difficulty as the key variable distinguishing the two modes of CoT identified in the paper