Workflow & Automation

`dsh-workflow-designer` 是面向 DeepSeek Harness 的提示词优先工作流设计插件。它收集当前 Agent 可见的本地 Skill、原生 Tool 与 MCP Tool，提供必要的可视化编排和约束编辑能力，并导出稳定的 YAML 中间表示。后续可由大模型及对应框架把 YAML 生成 Python、`workflow.mjs` 或其他代码工作流。

DeepSeek Harness plugin: per-day token usage statistics — 13-week heatmap, stacked daily chart, /token-usage command

Maintains reusable named subagent profiles for DeepSeek Harness and runs them with per-profile model, reasoning effort, and agent-preset settings.

Task Runner mode for DeepSeek Harness: the main agent decomposes large tasks into independent subtasks, dispatches them to subagents (default local model) in fresh short contexts, and synthesizes results; concurrency and worker/orchestrator models are configurable in the settings panel.

Jimu (积木): domain-based orchestration plugin for DeepSeek Harness — domain_plan confirmation, per-domain sub-agents with hand-off, and automatic LLM audit.

✨ One-click prompt polisher for the DSH composer — an agent refines your rough draft in a side chat over multiple turns, and you copy the result back when you're happy.

Turns a product or UI request into an implementation-ready design spec with /ui-workflow and /ui-rerun. Analysts run through a read-only ui_analyst tool, and the lead agent writes docs/ui-workflow reports.

Intercepts turn-stopping to force one critique-and-improve round after each completed turn before the agent stops.

Multi-agent isolated debate for DeepSeek Harness: debaters of different temperaments research independently (no herding), then cross-examine, then judges converge to a conclusion. Runs as a background job with per-agent progress, token accounting, wave-parallel execution, and session-referenced resume.

Plan-and-execute orchestration over ReactLoopAgent — turns a goal into reviewable steps with a web UI plan card.

Claude Code style /init command and tool that writes a minimal CLAUDE.md and symlinks AGENTS.md to it.

Captures every plan the agent presents through exit_plan_mode as markdown under <workspace>/.dsh/plans, opens a review window, and keeps a Plans history tab recording the outcome of each plan.

Preset workflow template library: 12 reusable orchestration script templates with wf_template_list / wf_template_search / wf_template_run / wf_template_validate tools and static template validation.

Git Ship Done (opengsd-core) reimplemented as host-plane Cordis plugins: replaces the default agent loop with a spec/discuss/plan/execute/verify/ship phase loop.

An agent preset that turns a one-line idea into requirements, tech plan and maintenance baseline — every step is restated and confirmed by you before proceeding. No scenario presets: 73 atomic skills (6 master skills + a verify dispatcher + 66 sub-skills) load by context.

Roadmap ideation for DeepSeek Harness — generate and compare distinct roadmap options via headless agent runs, pick one, export as goal.md

Routine taskboard for DSH: a dedicated registry of long-lived scheduled infrastructure placards (windows tasks / cron / ai sessions) with dual-source health lamps and artifact freshness, plus a lightweight claimable work-order board.

DeepSeek Harness plugin: background file/command monitors that wake the owning session on new output and show a live monitor list in the Web session header over a dedicated WebSocket. Host core + Web client half, no build step.

DSH plugin: an unattended AI software team. Feed it a bare Linux server, a set of secrets (env-var references only) and a git remote, and the plugin-driven AI team drives the whole project lifecycle — environment bootstrap, scaffolding, task decomposition

Danus-native DSH plugin suite: verifier-gated mathematical proof-search orchestration (fact graph, role-gated tools, cold-start verifier, worker swarm, orchestration tools, heartbeats).

Roadmap ideation for DeepSeek Harness — generate and compare distinct roadmap options via headless agent runs, pick one, export as goal.md

A cron-based scheduled task plugin for DeepSeek Harness (dsh) desktop: create / edit / delete / fire-now tasks from the settings panel, with cross-session agent follow-up and multi-level notifications. Zero LLM tools — purely human-driven scheduling.

DeepSeek Harness 无人值守任务队列插件：丢 .md 进收件箱 → AI 自动执行 → 产出报告