SkillsVote: Lifecycle Governance of Agent Skills — Collection, Recommendation, Evolution (219 HF upvotes)
Memtensor Research Group / IAAR-Shanghai
SkillsVote proposes a lifecycle governance framework for reusable LLM agent skills covering collection (profiling a million-scale open-source corpus), recommendation (agentic library search with instructional skill context), and evidence-gated evolution (admitting only successfully reusable discoveries). It achieves +7.9 pp on Terminal-Bench 2.0 and +2.6 pp on SWE-Bench Pro over frozen base agents without any model updates.
Why it matters
219 HuggingFace upvotes; governed external skill libraries can improve frozen agents without fine-tuning — a modular alternative to model retraining for capability expansion
Importance: 3/5
219 HF upvotes; +7.9 pp Terminal-Bench 2.0 improvement with skill governance alone — no model updates required