Yifan Yang ea4ff459d7 docs(sleep): make the results section rigorous (named benchmarks, baseline→after) ...

Label each result with its benchmark, test size, metric, target model, and gate
mode; show absolute baseline→after (not just Δ); state the single shared protocol
once. SearchQA recall-scaling table (1400-item test, SQuAD-EM, GPT-5.5, gated) +
SpreadsheetBench confirmation (280-item, cell-value compare, nano, gate-free) +
the gbrain end-to-end line. Keeps the single-seed / flat-on-noisy caveats.

2026-06-15 16:42:43 +00:00

..

guide

refactor: make EnvAdapter.reflect a shared default (fixes dropped reflect kwargs)

2026-06-15 09:06:00 +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): make the results section rigorous (named benchmarks, baseline→after)

2026-06-15 16:42:43 +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

guideline.html

docs: move SkillOpt-Sleep into the guide; clean docs/sleep; fix guide link

2026-06-15 16:20:50 +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