Unverified50% confidenceBenchmarkExact time
The naturally bloated 9.2KB skill file had an empty-output rate of 50%, averaged 14,766 output tokens, and had a convention hit rate of 2/4; compared with the manually filled 9.5KB file (25% empty-output rate), the naturally bloated file had a higher failure rate.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSkill file size is under a hard budget measured in bytes: below 6KB, zero burnouts across eight runs; 6–9KB, about 25% empty responses; above 9KB, about 50%; one skill file that naturally ballooned to 9.2KB made the weak model return empty responses six times in a row.79% similarUnverifiedIn the experiment, the two size points of 2.8KB and 4.1KB were executed 8 times in total, with empty-output rates of 0% each, average output tokens of 9,096 and 7,913 respectively, and convention hit rates of 4/4 each.74% similarUnverifiedThe UP host estimates that inference speed could improve to 30–40 tokens/s after using a GPU with 50GB of VRAM (not confirmed through actual testing).67% similarUnverifiedThe write rate given in the article's chart is approximately 1,000 sectors/minute, which converts to approximately 0.27 TB/year based on Linux's 512-byte sectors.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062635API
curl https://kongchang.com/api/v1/knowledge/claims/1062635MCP
get_claim(id=1062635)