Unverified50% confidenceBenchmarkExact time
In experiments on the 731 skill library, Skill++ selects all required skills for 76.3% of queries, whereas under the original metadata this proportion is only 36.4%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
UnverifiedSkill-Uni was tested on five skill-related benchmarks, improving on average by 66.59% over Qwen3-4B and by 34.82% on average over LLaMA3.1-8B.73% similarUnverifiedAfter the second round of distilling 3 newly selected skills, all four models reach or exceed the level of the complete skill library, while at this point the size of the complete skill library is at most 11 times that of the skills selected by SGUID.71% similarUnverifiedIn the experiment, the 27B model scored 61.0% on LiveMath when skills were written by the 4B model, whereas it scored 56.3% when it wrote the skills itself67% similarUnverifiedForecall, on 88 tools across 4 servers (Memory, Notion, Playwright, Chrome DevTools), generated 8 single-step requests per tool and tested model selection accuracy with Claude Sonnet 5.5 and GPT-6.1 Sol respectively, with accuracy across all servers ranging from 91% to 99%.63% similarUnverified根据Agent Skills标准，技能名称最多64个字符，描述限制在1024个字符以内63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129278API
curl https://kongchang.com/api/v1/knowledge/claims/1129278MCP
get_claim(id=1129278)