DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins
D

dreamina-design-plugin

Dreamina Design Plugin

DSH 插件 dreamina-design-plugin

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add github:full-aigc-plugins/dreamina-design-plugin#4a84b7b1c89ed1ea820dca90c18e31bfeeb22c12
README兼容性版本

说明

DSH 插件 dreamina-design-plugin

兼容性与来源证明

Dreamina Design Plugin 以 dreamina-design-plugin 发布,当前版本为 0.8.0。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
any
发布来源
github
Registry 更新时间
2026/10/23

版本

0.8.0stable
2026/10/23

相关插件

正在加载相关插件…

最新版
0.8.0
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
未提供
文件数
未提供
Surface
any
许可证
未声明
发布源
github
GitHub
★ 0
周下载
0
最近提交
2026/10/24
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 ui-customization 分类下经过校验的插件。

Plugin Wallpaper Enginedsh-plugin-wallpaper-engineDSH web GUI 的 Wallpaper Engine 背景:将本地 Wallpaper Engine 壁纸渲染到聊天背景中——通过内置的 WebWallGL 引擎实时渲染 Scene 和 Web,直接播放 Video——配备 iOS 风格的液态玻璃效果,可调节模糊/遮罩/bClaude Designdsh-claude-designDeepSeek Harness 插件:来自 baoyu-design 的 claude-design 技能。智能体将画板画布写入文件,并在本地画布编辑器中打开它们。Claude Slidesdsh-claude-slidesDeepSeek Harness 插件:来自 baoyu-design 的 claude-slides 技能。代理会将可编辑的幻灯片演示文稿写入文件,并在本地幻灯片编辑器中打开。Claude Design Systemdsh-claude-design-systemDeepSeek Harness 插件:来自 baoyu-design 的 claude-design-system skill。代理将设计系统(令牌、字体、组件、资源)写入文件,并在本地 design-system 页面中打开。

README

Dreamina Design

Plugin marketplaces

This plugin belongs to AIGC content creation.

CategoryMarketplacePurpose
Full-stack developmentFull Stack PluginsArchitecture and UI design, code understanding, quality checks, code review, workflow governance, and server operations
AIGC content creationFull AIGC PluginsImage, video, audio, music, 3D, and multimodal content creation

Dreamina Design — create images and videos with control

Create and edit Dreamina images and videos from your coding agent, with a capability snapshot from the live CLI, one explicit approval per paid call, and submissions you can resume by identifier.

English | 简体中文 · Install · Quick start · Skills · MCP tools · Troubleshooting

Positioning

dreamina-design is a strict wrapper around the official Dreamina CLI. It discovers what the installed CLI can actually do, validates each generation request against that snapshot, asks for a native confirmation before any paid call, and queries an uncertain task by its submit_id instead of submitting again. No tool accepts free-form shell input.

Since 0.7.0 the plugin runs a dual rail: paid submit tools default to the Canvas runtime (dreamina-canvas CLI with quote-bound approval), while runtime: "legacy" keeps the frozen dreamina path. The legacy binary stops being maintained after 2026-11, so new work should use the Canvas rail.

Installation

Prerequisites

  • Python 3.13 for the MCP server.
  • The dreamina-canvas CLI, enrolled and trusted with an absolute path and SHA-256 digest. The legacy dreamina CLI is optional and only for the frozen rail.
  • Optional, reference-video project tools only: ffmpeg, ffprobe, a Whisper-compatible ASR runtime, and macOS say.
  • A Dreamina account with credits; generation spend is never included in the plugin.

From the plugin marketplace

codex plugin marketplace add partme-ai/full-aigc-plugins
codex plugin add dreamina-design@full-aigc-plugins

Restart the host and open a new task. Then confirm the server and the CLI trust record:

codex mcp list

Read-only tools run without a prompt; paid and mutating tools raise a native confirmation whose default action is Cancel.

Quick start

flowchart LR
    A[Intent] --> B[Capability snapshot]
    B --> C[Validated request]
    C --> D{Paid?}
    D -->|no| E[Read-only tool]
    D -->|yes| F[Native confirmation]
    F -->|approved| G[Submit once with submit_id]
    G --> H[Query by submit_id]
    H --> I[Verified download plus receipt]
    F -->|cancelled| J[Stop, nothing spent]
Create a Dreamina image from this brief: a matte ceramic teapot on a linen table,
soft morning light. Show the exact parameters before you spend anything.

Expected observation: a capability snapshot, a validated request, a confirmation dialog listing the exact parameters, then a single submission with a submit_id. Asking to query it downloads the artifact and verifies it on arrival.

What you can build

WorkflowBuilt-in pathVerifiable output
Image generation and editsdreamina-prompt-text2image, dreamina-prompt-image2image, dreamina-submit_imageSubmitted task plus verified image
Video generationdreamina-prompt-text2video, dreamina-prompt-image2video, dreamina-submit_videoSubmitted task plus verified video
Iterate toward a targetdreamina-visual-target, dreamina-vision-judge, dreamina-visual-loopTarget receipt, round receipt, judge verdict
Full video projectdreamina-video-production, dreamina-video-shots, dreamina-video-evaluator, dreamina-video-syncShot analysis, evaluated batches, composed export
Browser-only membersdreamina-opencli-text2image, dreamina-opencli-image2image, dreamina-opencli-text2video, dreamina-opencli-image2videoGenerated artifacts through the Jimeng web session

Skills

SkillWhat it does
dreamina-design-useRoutes an unspecified image or video request to the right entry point.
dreamina-design-harnessInvocation spec: generation families, shot annotation, evaluation and paid submit-once gates.
dreamina-auto-seedanceTurns a validated DCC preview into an approved Seedance video.
dreamina-seedance-resumeResumes a paused 3D job from its ledger state without re-paying.
dreamina-prompt-text2imageWrites and refines image-generation prompts.
dreamina-prompt-image2imageWrites edit prompts for style, background, detail, colour and compositing.
dreamina-prompt-text2videoWrites video prompts with motion and camera direction.
dreamina-prompt-image2videoCovers single-image, first-last frame, storyboard and multimodal reference modes.
dreamina-vision-judgeScores a candidate against a target on composition, lighting, materials and detail, out of ten.
dreamina-visual-targetObtains or synthesizes the target image a visual loop needs.
dreamina-video-productionRuns a complete video project from a local reference video.
dreamina-video-shotsBreaks a finished clip into a measured shot table with deterministic gates.
dreamina-video-syncComposites shot metadata onto the source video so it cuts with the picture.
dreamina-shot-annotatorProduces shot-annotation schema content only.
dreamina-video-evaluatorProduces shot-evaluation schema content only.
dreamina-opencli-text2imageAutomates Jimeng text-to-image for standard members through the browser bridge.
dreamina-opencli-image2imageBrowser-bridge image editing when no CLI is available.
dreamina-opencli-text2videoBrowser-bridge text-to-video for standard members.

Slash commands

CommandWhat it does
/dreaminaEntry point; routes text/image and video families.
/dreamina-setupFirst-run setup: CLI install, authentication and preflight.
/dreamina-text2imageSubmit, poll and troubleshoot image generation.
/dreamina-image2imageLocal edits, stylization and upscale.
/dreamina-text2videoText-to-video including Seedance.
/dreamina-image2videoReference image, video or audio driven generation.
/dreamina-promptPrompt refinement across the four modes.
/dreamina-visual-loopTarget lock → paid generation → independent review → bounded retry.
/dreamina-auto-seedanceValidated preview → one submit → verified download.
/dreamina-seedance-resumeResume a paused Seedance job from the ledger.
/dreamina-video-productionReference video → analysis → prompts → submit → evaluation.

MCP tools

.mcp.json declares one stdio server, dreamina_design, started with python3 -m scripts.dreamina_mcp_server. It exposes 22 typed tools; read-only ones are pre-approved and paid ones always prompt.

GroupTools
Read-onlydreamina_capability_snapshot, dreamina_cli_status, dreamina_account, dreamina_query_task, dreamina_list_tasks, dreamina_diagnose, dreamina_quote_video_batch
Paid or mutatingdreamina_submit_image, dreamina_submit_video, dreamina_visual_loop, dreamina_cli_install_or_upgrade, dreamina_auth, dreamina_session
Video projectdreamina_video_project, dreamina_analyze_reference_video, dreamina_validate_shot_analysis, dreamina_create_redesign, dreamina_evaluate_video_batch
Batch and exportdreamina_approve_video_batch, dreamina_execute_video_batch, dreamina_compose_video, dreamina_export_video_project

Failures return a structured envelope with error_type, message, retryable, requires_user_action and a next_action of request_user_action, query_same_submit_id or correct_request.

Configuration

SettingLocationNotes
MCP server.mcp.jsonstdio; 10-second startup timeout, 3600-second tool timeout
Trusted CLI record~/.config/dreamina-design/trusted-cli.jsonMode 0600; stores path and digest, never a credential
State root~/.local/share/dreamina-design/Holds operations/ and approvals/
CLI logs~/.dreamina_cli/logsRead only through the bounded, redacted diagnostic tool

Architecture and security

Codex owns orchestration and approvals; the Dreamina CLI owns authentication and the remote API; this plugin owns validation, approval receipts and the operation ledger. The authors receive no artifact.

  • A paid call requires a native confirmation bound to the session and request; receipts are single-use and expire after five minutes.
  • CLI trust requires an absolute non-symlink path, a trusted owner and mode, and a SHA-256 digest.
  • Approval persistence strips credential-like keys before writing; diagnostics are bounded and redacted.
  • Reference-video uploads are contained: at most 50 MiB per image and 512 MiB per media file.
EvidenceStatus
CLI runtime contract, existing-task recoveryRecorded in docs/verification/dreamina-cli-runtime.md
Paid canarySeparately approved and recorded in docs/verification/paid-canary-2026-09-13.md
Reference-video project chainRegistered, but the ten runtime gate lines are NOT_RUN

Troubleshooting

SymptomCheck firstResolution
Tools are missingcodex mcp listEnable the plugin and open a new task
A paid call is blockedThe confirmation dialogConfirm explicitly; the default is Cancel
The CLI is not trustedThe trust recordRe-enrol the CLI and confirm the digest
A task looks stuckThe task stateQuery by submit_id; never submit again
A video mode is refusedWeb-side prerequisitesComplete the prerequisite on the web; the plugin will not bypass it
A reference-video tool does nothingThe runtime gate recordThose gate lines are NOT_RUN until they pass

Upgrade

codex plugin marketplace upgrade full-aigc-plugins
codex plugin add dreamina-design@full-aigc-plugins

Re-run the capability snapshot after upgrading: model parameters and command help come from the installed CLI, not from this repository. If you still call runtime: "legacy", plan the move to the Canvas rail before the 2026-11 sunset.

Current packaged version: 0.8.1+codex.20261018 (development preview).

Contributing and support

Open functional issues at https://github.com/full-aigc-plugins/dreamina-design-plugin/issues. State the CLI version you verified against, whether the change alters the approval envelope or the receipt format, and include the affected gate output.

License

Apache-2.0 — see LICENSE, NOTICE and THIRD_PARTY_NOTICES.md.

dreamina-opencli-image2video
Browser-bridge image animation with manual reference upload.
dreamina-cli-text2imageFrozen legacy CLI route; only for explicit legacy recovery.
dreamina-cli-image2imageFrozen legacy CLI route for image edits.
dreamina-cli-text2videoFrozen legacy CLI route for text-to-video.
dreamina-cli-image2videoFrozen legacy CLI route for image-to-video.
dreamina-cliFrozen compatibility entry; new tasks move to the Canvas successor.