@cocofhu/anime-find
DeepSeek Harness 插件:对话内多源搜番,卡片详情、磁力复制与规则流媒体在线播放
97 results
DeepSeek Harness 插件:对话内多源搜番,卡片详情、磁力复制与规则流媒体在线播放
Hanai Worth · 值见 — a local-first A-share value research workbench powered by DeepSeek Harness
Solo-style isolated brainstorm branches and Handoffs for DeepSeek Harness
DSH statistics tool: describe/percentile/frequency/correlation over explicit finite numeric arrays, zero-dependency, deterministic, numerically stable (Neumaier sum + Welford variance + linear-interpolation percentiles + Spearman midrank)
QQ Bot channel bridge for DeepSeek Harness
鲸鱼不废话,少词办大事 — DSH 极简语模式,节省 60-75% 输出 token
一会话,一扇门,一界命数。诸天万界DSH:DeepSeek Harness 上的文字修罗场。十九扇门点封面启程,不助手不提纲只写正文;誊出来的,是你活过的天书。
{{DESCRIPTION}}
Configurable non-public address allowlists for DeepSeek Harness web_fetch
Persistent TypeScript REPL control plane for DeepSeek Harness
Run Pi extensions as agent-scoped DeepSeek Harness plugins
WeCom AI Bot text, image, and file channel bridge for DeepSeek Harness
自主智能多模型协同调度系统 — 主动感知、自主决策、多模型并行、质量反思自愈、经验沉淀进化
FileScope · 文件视界: workspace file-explorer drawer with live file preview for DeepSeek Harness
Structural code MCP server and batch CLI for compact TypeScript/JavaScript reads and hash-bound AST edits.
Zero-signup public plaza for AI agents — speak, read, discover
AgentAstra — a spatial agent-trajectory view for DeepSeek Harness
DSH 插件:/gamemode 1 = 一键切换到内置创造模式(cordis)预设。DSH plugin: /gamemode 1 = switch to the built-in Creative Mode (cordis) agent preset.
DSH 工具箱插件:侧边栏独立页面 + /toolbox 命令 + 配置驱动的 agent 确定性工具。52 个本地工具(文本/编码/数据/安全/提取/转换/网络/效率),数据不出机器。参考 devtoolbox.online 设计。
DSH web plugin: a native Settings panel for visualizing and managing MCP servers, skills and rules, with a modular feature registry so future visualizations slot in without touching the shell.
DSH web 侧边栏搜索索引:标题搜索 ↔ 内容搜索一键切换,内容搜索按会话聚合展示标题与命中片段;自带独立索引(不依赖 DSH 官方全文索引),支持增量同步、非破坏性整理与快照导入导出。
Completion evidence gate for DeepSeek Harness goal-mode subagents
Prompt-cache observability and logical-input diagnostics for DeepSeek Harness
Skill-trigger evaluation: an LLM judge recreates the DSH skill catalog and measures how reliably a skill description routes matching queries.