Skill-based system design principles

Claims (15)

• There is Strength in Numbers
• Asynchronous communication via out is more efficient and conceptually apt than synchronous procedure calls in parallel contexts.Foundational argument for Linda's design: processes should not block waiting for responses when they can dump results asynchronously.
• Precise specification informs use and implementation without entangling them.
• S suggests practical diagnostics for prompt design, retrieval, and light fine-tuning without additional training infrastructure.Applied contribution.
• Single-process design with coarse-grained task switching eliminates synchronization complexity.
• Task balancing is still an open problem in multi-task learning.Motivation for the proposed method.
• A skill should do its work and stop, avoiding performative complexity and multi-stage flows when single-pass suffices.
• A skill works at multiple reinforcing scales: individual command, skill invocation, and user project.
• A skill's output length should match task complexity—short tasks produce short reports, long tasks produce structured hierarchical reports.
• Every skill should have one unmistakable thing it does; sprawling skills violate the Strong Centers principle.
• Fine-tuning as character formation: what kinds of selves are produced through training is an open research direction.
• Parallel sub-tasks within skills and across skill families should produce parallel outputs for legibility.
• Skill output should contain no filler; every line of a run-summary should carry weight.
• Skills should interconnect with each other rather than operate independently; output of one feeds another.
• Skills that occasionally produce unexpected output may be more useful than perfectly predictable skills.