dsh-skillopt
Microsoft SkillOpt-Sleep integration for DeepSeek Harness: give your dsh agent a nightly sleep cycle that harvests past sessions, replays recurring tasks, and consolidates validated skills behind a held-out gate.
318 results
Microsoft SkillOpt-Sleep integration for DeepSeek Harness: give your dsh agent a nightly sleep cycle that harvests past sessions, replays recurring tasks, and consolidates validated skills behind a held-out gate.
AgentAstra — a spatial agent-trajectory view for DeepSeek Harness
Native Windows toast + taskbar flash for DeepSeek Harness when a task finishes or your input is needed.
dsh-auto-paste — a DeepSeek Harness plugin (tool template, extended with a web client paste listener): 在输入框粘贴大段文本时自动保存为附件文件。
A-share + US stock trading toolkit for DeepSeek Harness agents: A股/美股行情查询 (EastMoney, no key), ADX regime signals (trend/oscillating/noise), and simple backtest previews. Read-only, no order placement.
DeepSeek Harness plugin for SecurStack security scans, policy checks, doctor diagnostics, and JSON CLI results.
Remote multi-server GPU status board for DeepSeek Harness Web: read-only nvidia-smi over SSH with ControlMaster-muxed connections, a host-side cached snapshot, per-server selection, and gpu_overview / gpu_refresh agent tools.
Cite what matters in DeepSeek Harness: @ a past session, quote earlier messages with comments, and open the files this turn just wrote.
Paste/drop non-image files or folders into the DSH chat composer: paste inserts native @path references, drop inserts absolute paths.
DSH (DeepSeek Harness) data-insight skill plugin: turn raw data (CSV / pasted table / SQL results / DuckDB) into a structured Markdown report with business conclusions, metrics and charts.
深海事务所 (Abyss) — an operations console for DeepSeek Harness agent fleets: every agent is a character at a desk, every line comes from the durable session log, and any past case replays and reports from disk
DeepSeek Harness web plugin: paste files into the composer, store under session workspace/inbox/, read via read_inbox / list_inbox tools.
Recursive Self-Improvement (RSI) engine for DeepSeek Harness: a bounded perceive → integrate → verify → repair → propose loop that keeps a downstream desktop app in sync with the fast-moving upstream harness. AI for AI — DSH maintains DSH.
DeepSeek Harness achievement & gamification plugin: cross-session badges for turns, tool calls, sessions and daily streaks, with a badge panel, unlock toasts and a ctx.achievements service. Zero core changes.
DeepSeek Harness 喜马拉雅播客插件:Host 端代理喜马拉雅搜索/专辑/曲目/收藏声音/订阅专辑/关注主播接口并解析播放地址(免费曲直链 + 登录态 baseInfo 解锁已购/VIP 内容),支持订阅/收藏/关注云端写回(与手机 App 同步),浏览器侧提供播放条与搜索/专辑/主播/我的面板,并注册 ximalaya_play 模型工具
DSH 大会话性能插件:零拷贝 fork + fast initFor + 投影分片预热 + fork 缓存回填 + 分片 materialize + 冷会话 LRU 裁剪 + heap 检测(DeepSeek Harness / DSH)
Read-only market quotes, OHLCV history, fundamentals, news, search, and health checks for DeepSeek Harness
Session KB for DeepSeek Harness: full-text search across all past sessions and recall them as @references. 会话库:全文搜索历史会话,一键以 @引用 召回给 AI(session search / recall / knowledge base).
DSH 任务提醒插件:任务结束/审批/提问/出错时网页 toast + 跨窗口系统弹窗 + 通知中心;设置页内置配置预设,可自定义弹窗位置、样式、主题、宽度与系统级提醒开关
Codex themes (light + dark) for the DSH web GUI as a configurable appearance plugin: maps codex-theme-v1 knobs onto the DSH --dsw-* token system and adds a Codex appearance settings section (colors, contrast, diff/skill semantic colors, UI/code fonts) persisted to settings.yaml.
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
DeepSeek Harness plugin: auto-detect secrets pasted into the composer, store them in the official credentials seam, and send [secret:REF] placeholders to the model instead of the value.
Paste images / drag any files into the DSH composer -> saved into the session workspace as files -> images read by modlens, other files read by the model by path
Plug-and-play image reading for text-only models: admits pasted images, projects them as [Image #N], and provides a first-class read_image tool backed by a configurable vision model, with a 读图 settings page (设置 → 读图) bridged over typert Remote.