@dsh-external/dsh-kb-sieve
知识库筛子:把文档(md/txt/docx/pdf)构建成可审计知识包(references + SQLite FTS5),提供确定性检索(kb_query)与原文精读(kb_read)工具,可生成零脚本的 DSH skill 并动态加载。
91 results
知识库筛子:把文档(md/txt/docx/pdf)构建成可审计知识包(references + SQLite FTS5),提供确定性检索(kb_query)与原文精读(kb_read)工具,可生成零脚本的 DSH skill 并动态加载。
dsh bundle: attach any file type in dsh web — text-likes inline, binaries as workspace path references, rasters via the built-in pipeline
Paste/drop non-image files or folders into the DSH chat composer: paste inserts native @path references, drop inserts absolute paths.
Enhanced subagent delegation tools for DeepSeek Harness: per-call model/provider/persona/toolFilter overrides, @preset: references, and provider/model composite ids — zero patches, bundle.
Code reference & reuse-survey plugin for DeepSeek Harness (DSH): search local code + GitHub/npm before building, evaluate reuse vs rewrite, ask the user, architecture-level reuse. 开发前检索本地与开源可复用代码并询问用户的复用调查插件。
DSH 演示文稿技能 + 工具插件:一句话或一篇 Markdown 文档 → 完整演示文稿(独立 HTML 网页放映 + 可编辑 PPTX 导出),内置 5 套视觉主题与页间转场/要点入场动画(motion 可关),可配置默认主题/语言,中英双语,SKILL.md 薄路由 + references 按需装载,跨 harness。
DSH Literature 文献侧窗:在 DeepSeek Harness 侧边栏识别 DOI/arXiv/标题、抓取元数据与全文、写入本地文献库或导出目录,并提供内置 PDF 阅读器(缩放/翻页/目录/搜索/高亮/笔记)。
Complete Git worktree support for DeepSeek Harness: task-scoped isolated worktrees with per-repo manifests, workspace registration, bring-back to main, direct commit, and durable state. Reference: Qoder / Codex / Claude Code worktrees.
Mixture of Agents for DeepSeek Harness: /moa marks a message, multiple reference models assist the main model's summary.
GitHub issue and pull request references for the DeepSeek Harness web GUI: click the GitHub icon at the bottom-right of the input box to search the workspace repository and insert issue/PR references. Data comes from the gh CLI.
Solve the AI goldfish brain: a personal memory layer for DeepSeek Harness — preferences, project conventions, workflows, and error lessons, stored locally as auditable, evidence-backed Markdown/JSON. 解决 AI 金鱼脑:偏好、项目约定、工作方式与纠错教训的本地可审计记忆层。
Registers generate_image and generate_video tools for Agnes AI media models (agnes-image-2.1-flash, agnes-video-2.5-flash) in DeepSeek Harness. Supports multi-image reference via reference_image_urls.
A desktop-style workspace, wallpaper, pet, and file-reference UI 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 Web GUI @-mention workspace file picker: input @ to filter git-tracked files plus files re-included via .aiinclude, like Codex/Claude Code file references.
/fuck — read your Claude Code & Codex conversation history in parallel, analyze your preferences and tool habits, migrate them into DSH as a persisted profile, and keep remembering them.
DeepSeek Harness plugin: drag-and-drop file attachment — paste or drop any local file into the DSH web composer as an @workspace path reference
Caches DSH Web file and session reference indexes for local @ filtering while preserving native mention insertion.
Developer quick-reference toolbox for DeepSeek Harness (DSH): 12 themed categories (195 entries) + zero-dependency dev tools (regex tester, JSON format, timestamp, Base64/URL codec, cron generator, line diff). 开发者速查工具箱。
V0 capability-disclosure scanner for DeepSeek Harness (DSH) cordis plugins: reports which sensitive services (credentials/shell/approval/sandbox/fs/tools...) a plugin declares or references before you trust it.
@-mention context references for DeepSeek Harness: workspace file search and cross-session references from the web composer.
Deterministic context-pruning compaction backend for dsh (DeepSeek Harness) — zero-LLM summaries, /dcp command, works out of the box. Design references Opencode-DCP/opencode-dynamic-context-pruning.
Add an upload-image button beside the composer plus button. Picks local images and feeds them through the conversation draft-image drop path (DataTransfer + synthetic drop event), so describe-image rewrites the send into an image reference.
88API Image Studio for DSH: six Image2, Image 2.5, and Nano Banana models for text-to-image, multi-reference editing, 2K/4K output, and sequential batches.