Bundle
dsh-design-qa
让 DeepSeek Harness 里任何纯文本模型都能读图。识图是按需调用的 tool —— 图片不进主模型上下文，不看就不花钱；附 23 处缺陷的评测集，换模型可自测。
sunxin-ai43
Browse
12 results
Bundle
oh-my-knowledge
OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.
lizhiyao17
Bundle
dsh-blind-arena
A blind, fair, local Agent arena inside DSH Web: same task, same commit, isolated worktrees, shared verification, judge before you reveal.
changer-changer2
Bundle
@webwalkerhq/dsh-replay-lab
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
tbxy092
Bundle
@chenjie1129/dsh-reliability-governor-plugin
Two-stage intent and evidence review, deterministic completion gates, and bounded repair for DeepSeek Harness agents
chenjie11292
Bundle
dsh-dual-model-eval
Compare multiple coding models side by side in DeepSeek Harness with isolated Git worktrees
huangdaxianer1
Bundle
deepseek-harness-flow
Community visual workflow and multi-model evaluation plugin for DeepSeek Harness
alison-xx1
Bundle
dsh-plugin-abtest
Paired experiments and promotion gates for DSH plugins.
Morriaty-The-Murderer
Bundle
@tbxy09/dsh-replay-lab
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
tbxy09
Bundle
dsh-learning-bundle
A proof-carrying correction loop for DSH: explicit adoption, scoped recall, and reconstructable delivery.
B1lli
Bundle
dsh-plugin-compare
Controlled A/B comparisons and evidence-backed reports for DeepSeek Harness plugins and presets.
yminghua
Bundle
dsh-llm-eval
LLM 评估：输出质量评估、幻觉检测、基准测试、回归守护。受 wshobson/agents（38k★ MIT）启发。
satan9394