vibe
Vibe Code Orchestrator (VCO) is a governed runtime entry that freezes requirements, bounds execution, and enforces verification and phase cleanup.
58 results
Vibe Code Orchestrator (VCO) is a governed runtime entry that freezes requirements, bounds execution, and enforces verification and phase cleanup.
Chinese-platform last-30-days research skill covering Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, and Toutiao. Includes Markdown, JSON, compact context, and Guizang-inspired Swiss/IKB HTML report output.
Deployment scripts for MisakaNet Workers
Git-style milestone timeline for DeepSeek Harness: hover for metadata, click to jump to any message. 会话里程碑导航条:圆点时间线,定位并跳转到每条提问。
DSH 插件全家桶:浏览器自动化 + MCP Server + GitHub/GitLab 自动评审 + 原生嵌入面板。One install, five modules for DeepSeek Harness: browser automation, an MCP server exposing your agents to any MCP client, GitHub & GitLab automation, and a native in-app panel.
Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness: continuable children, durable session recovery, per-role product permissions, delegation with a permission ceiling, and a declarative role library.
DeepSeek Harness UX walkthrough plugin: persona-driven source-code UX review for React (TypeScript/JavaScript) and Vue 3 projects, with change-triggered automatic walkthroughs
OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.
Global skill hub for dsh: aggregates Claude Code, project, and .skill-package skills into ~/.dsh/skills with reference/copy import and slash-menu usage
Solo-style isolated brainstorm branches and Handoffs for DeepSeek Harness
Portable Agent Skill for developing and auditing DeepSeek Harness plugins, with an optional DSH bundle adapter.
GitHub-installable DeepSeek Harness bundle that mounts the zhihu-search Skill
RMB/USD token-billing plugin for DSH web: official-policy auto pricing (incl. peak/off-peak), full coding-plan billing by provider routing, Settings→Cost summary page, per-message ledger, account balance, locale-driven currency display
DSH (DeepSeek Harness) plugin packaging of the Project Blueprint skill — one-command AI coding conventions (AGENTS.md, docs skeleton, CI/CD, git rules, testing policy) with an autonomous discovery engine (7 languages, 15 frameworks, 70+ components, web fallback).
DSH 消息撤回插件:在用户消息气泡旁加「撤回」按钮,把项目文件(独立影子 git 仓库快照)与对话历史(官方 fork)一并回退到该消息发送之前。
Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Doubao Web by default (zero cost, no API key), Antigravity IDE quota (flash/pro), Gemini API, or Cockpit proxy — model-invokable vision tool, wrapper adapters, evidence memory, and a bilingual client panel.
DSH Web 多主题引擎:完整支持 opencode TUI 全部 34 个主题(33 内置 + system)。数据驱动三层管线:主题 JSON → 颜色解析 → DSH 适配注入。
顶部栏「IDE」按钮:自动检测本机已安装的 IDE(VS Code / JetBrains / Cursor / Windsurf / Zed / Trae / VSCodium / Android Studio / Sublime Text 等),设默认后单击直达、点 ▾ 或右键可选其它,一键用其打开当前工作区目录;自定义 IDE 与默认 IDE 会持久化,界面文案支持中英文。
VS Code-style workspace keyword search tab for the dsh web GUI, registered into dsh-better-sidebar
Wanjiqi (6657 live room) meme Skill for DeepSeek Harness (DSH): 22,771 real barrage memes distilled into an AI skill - wanjiqi-style barrage memes, CS x DOTA cross-memes, player roasting and casting banter. / 玩机器(6657直播间)烂梗 Skill:22771 条真实弹幕烂梗蒸馏成 AI 技能——玩机器式弹幕烂梗、CS×DOTA 双料梗、选手锐评与解说吐槽。
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
Harness Pet is an unofficial community project. Not affiliated with, endorsed by, or maintained by DeepSeek. A tiny whale for DeepSeek Harness.
散户研究心法:把模糊问题变锋利、枚举可能性、只对承重主张取真实证据、做非对称审计,交付证据标注的可读报告,并沉淀可更新的认知锚。何时用:用户问题材真伪、要可能性地图/承重主张审计/定价对照、说「更新锚」时。默认原生工具循环,零强制脚本。
Server-development mode for DeepSeek Harness: remote agent tools (ssh_list / ssh_exec / ssh_ls / ssh_read / ssh_write) backed by a persistent ssh2 engine, so the DSH coding agent's working environment is a remote Linux server. Works with the `remote` agent preset.