dsh-multi-cloud
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
131 results
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
DSH plugin: model reasoning levels plus CLI request mimic, with a unified Daily Optimization settings section.
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
DeepSeek Harness plugin: aggressive token optimization without affecting task quality. Trims tool results, manages context window pressure, optional LLM-summary compaction, stable prompt-cache layout.
vLLM-Ascend Profiler Analyzer — a DeepSeek Harness plugin that ingests vLLM-Ascend / Ascend NPU profiling artifacts, renders a standalone Host+Device swimlane / cost-share / optimization-advice surface, and exports Markdown or PDF reports.
DSH Prompt Optimization plugin: one-click prompt optimization in the composer input, with an optional dedicated optimizer model in Settings
DSH 对抗多智能体三层失效的防御插件:读取台账去重度量(read-ledger)、免疫压缩规则区+完成机械门禁(immutable-core+completion-gate)、低成本审查lane(role-router)。零外部依赖,注入即用。
DSH Effort Router(模型分流):按每一轮请求的难度自动选择模型与思考强度——简单问题走便宜快模型,难题才叫强模型。规则判定零 token,灰区交给一次小模型裁定,图片档强度随难度升降(low/high/max)。每轮请求级覆盖,不改你的会话选择与默认模型。
DSH 提示词锻炉:零配置流式优化(复用会话模型)+ 轻量词库(JSON 文件)+ 一键存技能。Prompt Forge: zero-config streaming optimization + file-based prompt library + one-click skills.
Multi-Agent collaborative skill forging system for DeepSeek Harness — distill conversational experience into verifiable, reusable skills with evolutionary optimization.