novel-writer
Multi-Core Collaborative Novel Writing — a DeepSeek Harness (DSH) preset plugin that installs a multi-agent novel-writing mode: one conductor plus five specialized subagents (多核协同写作模式).
5989 results
Multi-Core Collaborative Novel Writing — a DeepSeek Harness (DSH) preset plugin that installs a multi-agent novel-writing mode: one conductor plus five specialized subagents (多核协同写作模式).
FormatForge for DeepSeek Harness: forge any file format (pdf/docx/xlsx/pptx/eml/toml/...) into AI-readable structured data. v1.0.0 (PRODUCTION-READY, protocol frozen): 协议冻结(v1.x 向后兼容)+ v0.14.0 全部 7 项 P0+P1 + 5 项 audit 修复(4 bug + 1 性能)。测试基线 567 passed。Thin
DSH plugin health checker: scan plugin repos for manifest protocol / patch format / build pitfalls / hub registration, zero-dependency read-only diagnostics
Claude Code-style focus view for the dsh web GUI: the conversation's condensed reading surface — tool calls folded into expandable metric summaries, chat 1:1 row chrome, and streaming think rows
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, 95 component entries, web fallback).
Session-state notification plugin for the dsh web GUI: session completed/failed, question-asked, and permission-requested alerts with configurable built-in or custom sounds and browser notifications, plus a Notifications settings section
Four-source migration wizard: copy Claude Code, Codex, OpenCode and Hermes sessions, memories, skills, instructions and slash commands into DeepSeek Harness as resumable sessions — copy-only, approval-gated, idempotent
Self-contained browser runtime plugin for DeepSeek Harness (scoped @anweat) — bundles Playwright (chromium) and OpenCLI as plugin-local dependencies (with global-reuse fallback), exposes a `browser` service and interactive browser tools.
DSH Web 多主题引擎:完整支持 opencode 全部 38 个主题(37 内置:33 TUI + 4 桌面 2.0 + system)。数据驱动三层管线:主题 JSON → 颜色解析 → DSH 适配注入。
dsh-qa QA Workbench: a local software testing workbench plugin for DeepSeek Harness. Project/iteration dual-mode, full-flow requirements / test cases / defects / milestones / reports, native QA preset, themes, kanban and calendar.
OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.
DSH plugin (scoped package @smanx/dsh-proxy, matching the repository): LAN reverse proxy with native Basic Auth and a settings page. Source lives in this repo's dsh-proxy/ subdirectory; this root package makes the plugin installable from the repository itself (git/github: specs install the root).
DeepSeek Harness 插件:对话式游戏本地化,把 tav2(TranslateAgent v2)翻译流水线接入 dsh。引擎适配器架构,首发支持 Ren'Py。
Google Antigravity / Cloud Code Assist model provider for DeepSeek Harness
Project-scoped one-shot users for DSH: project/user dual workspaces with symlink isolation, cwd session bucketing, soft guard, and a built-in admin UI. Best-effort isolation (honnet gens) — not a hard security boundary.
DeepSeek Harness 的统一智能体画布:需求时间轴 + 多智能体团队层级编排一图呈现,成员立绘、按说话者编织的对话链、任务依赖 DAG,团队数据自有化存储。
DSH 插件透明排行与推荐:每日自动抓取 dsh-plugin 话题生态 + 公开评分模型 + rank/recommend/search 工具 + 设置页排行标签
DSH lorebook-driven fiction writer plugin: import Tavern/SillyTavern character cards & world books, save local Markdown lore documents, and generate novel prose with the world settings as reference.
MuseAI tavern for the dsh web GUI: a MuseAI conversation-view tab (right of Trajectory) with background / chat / adventure / bond / settings pages ported from MuseAI, running entirely on models configured in DeepSeek Harness (no separate API config)
AI-native Kanban companion for DeepSeek Harness
Long-term memory for DeepSeek Harness: multi-channel retrieval and an evolving memory store.
Minimal Root-Orchestrator PTES pentesting plugin for DeepSeek Harness
DSH plugin: one shell tool that runs commands through PowerShell, Git Bash, or WSL on Windows, with a user-chosen default terminal in the Web UI settings.
A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 75 models from one credential: a BlockRun API key, or a wallet paying per call over x402.