@zseven-w/dsh-openpencil
Preview, inspect, and edit real .op OpenPencil design documents inside DSH conversations — headless rendering, a read-only canvas, and a managed editor.
41 results
Preview, inspect, and edit real .op OpenPencil design documents inside DSH conversations — headless rendering, a read-only canvas, and a managed editor.
Task-specific React apps for DeepSeek Harness with state carried into the next Agent turn
Design I/O for coding agents: controllable UI generation via declarations (spec/domain/craft/design/components/template) and contracts (skill/evaluator). Use for product UI—console, dashboard, agent-ops, CJK-first apps.
MCP visual manager plugin for DeepSeek Harness: inspect installed/enabled MCP servers, add/remove, enable/disable and view live connection status from the web GUI.
Browser element annotation bridge for DeepSeek Harness
Conversational Grafana operations for DeepSeek Harness: inspect live observability data and make safe, reviewable dashboard changes
Verified plugin marketplace for DeepSeek Harness: discover, inspect, install, and remove DSH plugins from the Web UI
DSH 外部插件:模型在对话流中流式生成 SVG/HTML Widget(```svg/```html 围栏逐 token 渲染于沙箱 iframe)与结构化图表(visualize 工具的 ChartSpec -> echarts)。复用已有 assistant/chunk + tool/result 事件,不改 DSH 源码。
Click any UI element in your running dev page to jump to its Vue / React / Svelte / Angular source in the DSH chat. A click-to-source inspector for DeepSeek Harness, compatible with dsh-better-sidebar.
Spec-driven development loop for DeepSeek Harness: a /spec command family drives propose → approve → implement → verify → archive with OpenSpec-compatible change directories, a durable session projection, and a change card in the composer dock.
DeepSeek Harness plugin that browses, previews, edits, and saves OpenSpec change Markdown files in the Web UI.
OpenCode Go subscription key rotator for DeepSeek Harness (dsh): per-request active-key routing, 429/quota cooldown rotation, cost accounting, dashboard quota scraping, and a web GUI settings section. Self-contained data dir under the plugin install folder — no machine-specific paths.
DSH plugin: Sisyphus agent orchestration — star topology, single-line blocking, 7 specialist sub-agents (Hermes/Explore/Librarian/Looker/Hephaestus/Prometheus/Oracle) with per-type model binding, go_work/continue/need_help/forward communication tools, Web UI tree panel and settings.
DeepSeek Harness plugin that turns UI screenshots into implementation-grade web specs using OCR, deterministic geometry, scene graphs, assets, and render comparison.
A stateful, Agent-controllable Jupyter workspace for DeepSeek Harness: a persistent ipykernel runtime the DSH agent can read, edit, execute, and inspect, with VS Code-aligned cell UI and .ipynb save/load.
Control YesPlayMusic TUI from dsh-TUI with /music, artwork, seeking, and a live spectrum bar
Maglev for DSH: 面向 DeepSeek Harness 的研发对齐插件(29 技能 + spec 工具 + 结晶事件 + Maglev GUI)
Matt Pocock's skill workflow pipeline for DeepSeek Harness: registers the matt skill set and adds a visual pipeline panel (Idea > Triage > Grill > Spec > Tickets > Implement > Review) to the better-sidebar, one click dispatching the official /<skill> gesture to the active session.
A Genshin Impact Columbina (哥伦比娅) themed plugin for DeepSeek Harness Web: preset/custom background images with a translucent mask, per light/dark scheme palettes, and a special glow for the active conversation title.
Spike: channel-grouped session view for DeepSeek Harness — sidebar tab injection + session-projection data path (RFC dsh-channel-spec)
ResearchCraft as a DeepSeek Harness profile: DSH web UI and agent, scientific skills, lab notebook, specialist subagents.
Background jobs panel for dsh-TUI: /jobs lists, watches, inspects and cancels background jobs (bash, subagent, …) via the ctx.jobs registry.
Trellis × DSH workspace dashboard: a conversation-view tab showing the current task + progress (prd.md acceptance checklist), spec/skill usage, and workspace session summary.
Model-facing describe_image + extract_text tools for the DeepSeek Harness web GUI: gives a text-only model reliable image understanding and OCR through an OpenAI-compatible vision endpoint, with critical-inspection prompts, auto-preprocessing, retries, and a persistent answer cache.