21 results
AI4Scholar for DeepSeek Harness (dsh): 38 native academic tools — Semantic Scholar, PubMed, Google Scholar, arXiv, bioRxiv/medRxiv, DOI resolution, PDF full text, auto-cite, scientific figures, credit balance — with an API-key card in the Web UI settings. Powered by ai4scholar.net.
DSH Web GUI right sidebar: VS Code-style file explorer plus source control (git status, stage/unstage/discard, commit, diff, commit graph, sync fetch/pull/push, branch/remote management, git init, multi-repo switch, color-coded file status, file-type icons, image preview) with an editable full-file diff view (hunk stage/revert), a syntax-highlighted editor (15 languages), file operations (new/move/copy/delete), a collapsible icon rail, a multi-tab bottom terminal (ConPTY), AI-generated commit messages from a host-configured model, and save.
Persistent project memory for dsh agents: index docs (PDF/Markdown/text) and code symbols into a searchable per-workspace store, recall them with cited sources, and keep experience entries (problems -> solutions) searchable on demand.
Display images read by the read_image tool inside the DeepSeek Harness Web GUI: a dedicated Read image row with a default-expanded message-style image card (PS-style transparency checkerboard), merged read-N-images rows with side-by-side frames for multi-image requests, and an in-page full-resolution lightbox (zoom buttons, mouse wheel, 1:1 original size). 在 Web GUI 对话流中展示 read_image 读到的图片：默认展开的消息图片卡（透明棋盘格）+ 多图合并并排行（读取了 N 张图片）+ 页面内全精度放大层。
Self-contained Trellis workflow trigger for DeepSeek Harness: per-turn breadcrumb injection via agent/pre-step, a bundled skill provider, and DSH-native task/phase state resolution. No Trellis AGPL code is vendored; workflow semantics are rewritten and licensed MIT.
Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall of past solutions + LLM-driven capability matching + auto-persisted lessons. Zero keys, zero hard-coded paths.
Engineering-discipline skill pack for DeepSeek Harness — code review, simplification, plan-then-execute, test-first, and conflict resolution, delivered as a bundled skill provider plugin.
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.
Craft Mermaid skill + DeepSeek Harness bundle: deterministic high-resolution Mermaid PNG rendering with Craft light/dark palettes and visual review.
DSH AI tabletop / GM plugin for DeepSeek Harness: dice rolls, check resolution, world books, character cards, and DiceFrame content-pack import. Play solo in DSH, play with friends in DiceFrame.
GitHub research assistant for DeepSeek Harness: model-facing tools to search repositories, read READMEs/source, and clone candidates, so the agent can prospect open-source solutions for an idea and synthesize an implementation plan.
Deterministic chemistry math for DeepSeek Harness (dsh): formula parsing with molar mass (nested parens, hydrates, ionic charges), mass/mole/particle conversions, solution concentration (molarity, dilution, percent) and pH/pOH/buffer math — zero runtime dependencies
DSH 冲突管家（P2M）：自动拦截会让 DSH 闪退的同名服务注册/版本漂移等冲突，按用时排序、隔离肇事插件。Plugin Conflict Manager for DeepSeek Harness (DSH/Cordis).
Local OpenAI-compatible model-server discovery + tiered reasoning-metadata resolution for DeepSeek Harness (dsh).
订阅 turn/end 对本轮完整对话做 LLM 蒸馏（被否决方案/踩坑记录/工程约束），打 type:rejected_solution 标签写入 MemOS；编码任务时对 rejected_solution 记忆做检索权重提升。复用 MemOS 向量检索、归档淘汰、生命周期能力。
Explicit minimal-solution coding guidance for DeepSeek Harness. Registers six load-on-request Ponytail skills and a localized Settings page.
DeepSeek Harness tools for external opportunity discovery, unmet-need research, pain-point signals, opportunity mapping and validation experiments.
DSH 视觉增强方案：识图技能（图片理解/OCR/文档解析）+ 幂等宿主补丁，让纯文本模型也能收发图片。
DSH Web GUI plugin: adaptive chat content width — the middle area expands with screen resolution (1080p/2K/4K) when side panels are collapsed (injects CSS overriding --dsh-chat-content-width)
Right-side solution panel for DeepSeek Harness Web: push HTML solutions to a collapsible right drawer with browser-style tabs, resizable width, unread hints, and per-workspace durable persistence. 对话右侧方案面板：HTML 方案展示、多标签页、宽度拖拽、未读提示、按工作区持久化。
DSH skill bundle: competition math (IMO/Putnam/USAMO/AIME) solved with a pure-reasoning pass, an adversarial verifier in a fresh subagent context attacking concrete failure modes, and calibrated confidence output (high / medium / honest "no confident solution"); optional LaTeX→PDF rendering.