community
active
leiden_hybrid_concepts
label: sonnet
community:leiden_hybrid_concepts-run2-c35AI skill design principles
Heuristics for composing modular, scale-aware LLM skill architectures
7 members. Each node is clickable.
Loading graph…
Drawn from 1 source
The papers/notes whose extracted claims & findings make up this cluster.
- agent-harness-design.md7 members
Bridges (2)
Other communities that share members with this one — cross-cutting threads or papers that sit at the seam between two themes.
Claims (7)
- 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.
- Parallel sub-tasks within skills and across skill families should produce parallel outputs for legibility.
- 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.