Yifan Yang acf4545c00 docs(sleep): full 4/4 gbrain parity — quick-answerer 0->1.00 via real tool loop ...

quick-answerer (judge: tool_called=search) reaches 0.00 -> 1.00 with Sonnet
optimizer -> Haiku target: the optimizer wrote an OVERRIDE of the "never use
tools" instruction and the Haiku target genuinely invoked the ./search shim.
All 4 gbrain skillopt-v1 seeds now at 0->1.00, matching gbrain's own headline.

Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>

2026-06-08 14:31:51 +00:00

..

guide

docs: align API reference and Add-a-Benchmark guide with real EnvAdapter ABC

2026-06-01 20:14:54 +00:00

reference

docs: align API reference and Add-a-Benchmark guide with real EnvAdapter ABC

2026-06-01 20:14:54 +00:00

sleep

docs(sleep): full 4/4 gbrain parity — quick-answerer 0->1.00 via real tool loop

2026-06-08 14:31:51 +00:00

superpowers/specs

docs: add SkillOpt-Sleep Claude Code plugin design

2026-06-08 14:31:51 +00:00

contributing.md

SkillOpt v0.1.0: initial release

2026-05-21 17:22:04 +00:00

index.md

refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update

2026-05-24 19:15:10 +00:00