adversarial-review
claudeTwo independent adversarial approvals for a digest-checked task result.
1 skill
2
claude
research-loop
Metric-driven experiments with holdouts, immutable evidence, and replay-safe recovery.
/
Plugin research-loop from marketplace emlembow-skills in Emlembow/skills. Commands read from the repo's manifest — 1 month ago.
What it installs
Skills (1)
research-loopRun autonomous, metric-driven experiments on a version-controlled implementation against a fixed trusted evaluation harness. Use when the user asks to improve eval pass rate, benchmark score, prompt or policy quality, performance, cost, or another measurable outcome through repeated hypothesis, chan
More from Emlembow/skills
All 3 plugins →divisible-work
claudeVerified GPT-6.1 Sol or GPT-6 Luna work, preferring permitted Codex chats with native subagent fallback and durable task state.
1 skill
2
Maintain research-loop?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.
claude & codex plugins3 plugins