Skip to content
dsh.fish

Browse

15 results

Bundle

dsh-eval-harness

DSH 插件回归评测门禁:yaml 用例 + headless 驱动 + trace 断言 + baseline 门禁(eval_run / eval_gate)

BiBoyang14
Bundle

dsh-ecc-skills

ECC (227k-star operator system) skills for DeepSeek Harness — progressive port of 274 curated single-file skills (agentic engineering, evaluation, testing, patterns, vertical domains, docs). Adapted from affaan-m/ECC (MIT)

gongyijie856
Bundle

auto-pwa

AI-driven partial wave analysis for DeepSeek Harness: physics-gated config editing, ctpwa fit execution, numeric evaluation, and goal-driven iterative convergence. Physics knowledge (PDG-2026) as pure functions; DSH integration as a thin pwa_* tool plugin.

BHXiang3
Bundle

dsh-profile-lab

Reproducible local experiment matrices for DSH profiles

young-tim3
Bundle

dsh-self-evolution

Benchmark-driven self-evolution plugin for DeepSeek Harness: evaluate, optimize, snapshot, accept or roll back.

Lhy7233
Bundle

dsh-skill-eval

Skill-trigger evaluation: an LLM judge recreates the DSH skill catalog and measures how reliably a skill description routes matching queries.

renjianguojinqianfan2
Bundle

dsh-eval-regression

Deterministic, CI-safe golden-output evaluation for DeepSeek Harness

aryswisnu1
Bundle

@trapstreet/dsh-trapstreet

Check which DeepSeek Harness plugins actually loaded, and look up public evaluation boards on trapstreet.run

trapstreet1
Bundle

dao-zang-skill

Installable bundle contributing the DaoZang offline retrieval & original-text extraction skill to DeepSeek Harness (v2.0: launcher + self-check + workspace setup)

Godners-Code1
Bundle

@evegoodevening/dsh-llmwiki

Local-first, source-linked Markdown wiki storage and retrieval plugin for DeepSeek Harness

EveGoodEvening1
Bundle

dsh-northstar

A local DeepSeek Harness north-star guard with explicit AI indicator evaluation and task alignment context.

xDylanLong1
Bundle

dsh-skill-optimization

把技能当可训练参数:像训练神经网络一样训练 agent 技能(epochs/batchsize/learning rate/验证门禁,但不碰模型权重)——rollout→reflect→aggregate→select→update→evaluate 循环、候选编辑仅在严格改善 held-out 验证分时接受、文本学习率预算、零推理时模型调用、部署紧凑 best_skill.md。受 microsoft/SkillOpt(MIT)启发。

satan9394
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
Bundle

dsh-plugin-abtest

Paired experiments and promotion gates for DSH plugins.

Morriaty-The-Murderer