@hawk2048/oh-my-dsh

Oh My Dsh

oh-my-dsh：DeepSeek Harness 多智能体编排层——OMC 风格的工作流技能、斜杠命令和智能体预设。

目标 Profile

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:hawk2048/oh-my-dsh#1ea0fd2ad824abdac0730f60c838954c34610910

兼容性与来源证明

Oh My Dsh 以 @hawk2048/oh-my-dsh 发布，当前版本为 0.3.0。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: 2026/9/16

版本

0.3.0stable

2026/9/16

0.2.1stable

2026/9/7

0.2.0stable

2026/9/6

README

oh-my-dsh

A multi-agent orchestration layer for DeepSeek Harness (DSH) — ports oh-my-claudecode's orchestration modes onto DSH's native primitives (workflow / subagent / ralph / goal).

Two ways to trigger: natural language (30 skills, auto-loaded by the agent) + slash commands (13 /omd-* commands). Start a session, orchestration is ready.

中文

Quick Start

One command installs all 30 skills + 13 /omd-* commands (the OMC plugin-marketplace equivalent):

dsh plugin --profile web add github:hawk2048/oh-my-dsh

Or from npm (the npm i -g equivalent):

dsh plugin --profile web add @hawk2048/oh-my-dsh

Restart the profile, type /omd to see command candidates, or use natural language ("plan this", "autopilot, build a REST API").

Requirements

DeepSeek Harness (dsh CLI)
pnpm — dsh plugin forwards to pnpm

Why oh-my-dsh

Zero configuration — one dsh plugin add installs everything; the bundle self-registers, no setup wizard.
Team-first orchestration — Team is the canonical staged pipeline (team-plan → team-prd → team-exec → team-verify → team-fix), built on DSH's native workflow.
Natural language interface — describe what you want; the 30 omd-* skills auto-load, nothing to memorize.
Automatic parallelization — complex tasks fan out across parallel subagents.
Persistent execution — Ralph / Autopilot / Ultragoal keep going until verified complete (native ralph loops + goal cross-turn objectives).
Zero runtime overhead — adds no new host tools or runtime, just skills over DSH's native primitives, so you keep DSH's own model routing and sandbox.
Learn from experience — omd-skillify extracts reusable skills; omd-remember persists durable notes across sessions.
Real-time visibility — the inline HUD renders live dsh-ui progress dashboards.

OMC correspondence

Aligned to OMC v5.3.0 (the plan → execute → review → verify pipeline + retained modes):

OMC workflow	oh-my-dsh skill	DSH primitive
Plan	`omd-plan`	read-only exploration + parallel `subagent`
Execute	`omd-execute`	parallel `subagent` + `todo_write`
Review	`omd-review`	`subagent_fork` independent review
Verify	`omd-verify`	`pwsh`/`bash` tests + `subagent` re-check
Team	`omd-team`	`workflow` + `subagent`
Autopilot	`omd-autopilot`	`goal` + `todo` + `subagent`
Ralph	`omd-ralph`	`ralph` + `goal` verify loop
Deep Interview	`omd-deep-interview`	`ask_user_question`
Ralplan

Prompt-trigger + utility skills (natural-language only, no slash command):

OMC trigger	oh-my-dsh skill	DSH primitive
tdd	`omd-tdd`	`pwsh`/`bash` tests + red-green-refactor
deepsearch	`omd-deepsearch`	`grep`/`glob`/`read` local lookup
deep-analyze	`omd-deep-analyze`	parallel `subagent` multi-angle
ultrathink	`omd-ultrathink`	pure reasoning (no tools first)
ai-slop-cleaner	`omd-ai-slop-cleaner`	`review`/`edit` tightening
omc-doctor	`omd-doctor`	install/mount diagnostics
debug	`omd-debug`	reproduce→isolate→fix→regress
release	`omd-release`	git + tests + changelog + tag
remember

New in this plugin (no OMC counterpart):

Capability	oh-my-dsh skill	DSH primitive
Pyramid structured expression (conclusion-first + MECE)	`omd-pyramid`	pure expression discipline + `dsh-ui` hierarchy mapping (genui)

ultrawork is retired — OMC removed it in 5.0.0 (along with ultraqa/swarm/pipeline); oh-my-dsh removed it too, folding its "maximum parallel fan-out" into execute/team/ralph.

Key difference: OMC's HUD is a CLI status line, while oh-my-dsh's HUD is an inline dsh-ui dashboard in the reply (stat/progress/timeline/table), because DSH's Web GUI already renders structured UI.

Directory structure

oh-my-dsh/
├── package.json              # dsh.bundle manifest (bundle install entry)
├── cordis.patch.yml          # bundle patch layer (global commands + skills)
├── index.js                  # bundle module entry
├── agent.cordis.yml          # agent preset composition (= standard + persona + skills + commands)
├── preset.yml                # preset display metadata
├── install.ps1 / install.sh  # preset manual install scripts
├── LICENSE
├── commands/
│   └── omd-commands.mjs      # slash-command producer (ESM plugin)
├── skills/
│   ├── omd-plan/SKILL.md
│   ├── omd-execute/SKILL.md
│   ├── omd-review/SKILL.md
│   ├── omd-verify/SKILL.md
│   ├── omd-team/SKILL.md
│   ├── omd-autopilot/SKILL.md
│   ├── omd-ralph/SKILL.md
│   ├── omd-deep-interview/SKILL.md
│   ├── omd-ralplan/SKILL.md
│   ├── omd-research/SKILL.md
│   ├── omd-autoresearch/SKILL.md
│   ├── omd-ultragoal/SKILL.md
│   ├── omd-pyramid/SKILL.md
│   ├── omd-tdd/SKILL.md
│   ├── omd-deepsearch/SKILL.md
│   ├── omd-deep-analyze/SKILL.md
│   ├── omd-ultrathink/SKILL.md
│   ├── omd-ai-slop-cleaner/SKILL.md
│   ├── omd-doctor/SKILL.md
│   ├── omd-debug/SKILL.md
│   ├── omd-release/SKILL.md
│   ├── omd-remember/SKILL.md
│   ├── omd-cancel/SKILL.md
│   ├── omd-minimal-code-discipline/SKILL.md
│   ├── omd-external-context/SKILL.md
│   ├── omd-visual-verdict/SKILL.md
│   ├── omd-skillify/SKILL.md
│   ├── omd-wiki/SKILL.md
│   ├── omd-help/SKILL.md
│   └── omd-hud/SKILL.md
└── docs/
    ├── ARCHITECTURE.md
    └── RELEASE.md

Install / usage

Two forms — pick one (bundle for global, preset for per-session).

Form A: bundle (primary, the OMC plugin-marketplace equivalent) — installs the 13 /omd-* commands and 30 skills globally, visible to every session in the profile:

# git source (pure JS/Markdown, zero build, no allowBuilds needed; pin with @<tag>)
dsh plugin --profile web add github:hawk2048/oh-my-dsh

# or npm (the npm i -g equivalent)
dsh plugin --profile web add @hawk2048/oh-my-dsh

Restart the profile. One command, pulled by pnpm — no manual tarball download.

Form B: agent preset (optional, per-session) — full session with persona and the orchestration toolkit:

# Windows
.\install.ps1
# macOS / Linux
./install.sh

The installer is non-destructive: it never deletes the preset directory, keeps skills you added locally, and backs up any local edit it would overwrite as <name>.bak-<timestamp>. Re-running is safe and reversible.

Then create a session and pick the "oh-my-dsh 编排" preset (or set it as agent-presets.default). See docs/RELEASE.md.

Usage (in-session)

Two equivalent ways:

Way 1: natural language (the agent auto-loads the matching skill)

plan how to implement X → omd-plan
execute the plan → omd-execute
review my changes → omd-review
verify — tests must pass → omd-verify
team, build a task-management app → omd-team
autopilot: build a REST API → omd-autopilot
ralph the auth refactor until green → omd-ralph
deep interview me — I want to build X → omd-deep-interview
ralplan this architecture decision → omd-ralplan
research X best practices, with sources → omd-research
autoresearch this report to passing → omd-autoresearch
ultragoal: break this long goal into subgoals → omd-ultragoal
structure this as a pyramid / conclusion first / MECE → omd-pyramid
tdd: failing test first → omd-tdd
deepsearch: who calls this function → omd-deepsearch
deep-analyze this architecture → omd-deep-analyze
ultrathink before acting → omd-ultrathink
strip the AI slop → omd-ai-slop-cleaner
self-check the install → omd-doctor
debug this error → omd-debug
release v1.2 with changelog → omd-release
remember this decision → omd-remember
stop the running autopilot → omd-cancel
minimal change, no over-engineering → omd-minimal-code-discipline
read this issue/link → omd-external-context
compare these screenshots → omd-visual-verdict
turn this flow into a skill → omd-skillify
write this to the wiki → omd-wiki

Way 2: slash commands (type /omd for candidates)

Command	Equivalent skill
`/omd-plan <task>`	`omd-plan`
`/omd-execute <task>`	`omd-execute`
`/omd-review <task>`	`omd-review`
`/omd-verify <task>`	`omd-verify`
`/omd-team <task>`	`omd-team`
`/omd-autopilot <goal>`	`omd-autopilot`
`/omd-ralph <goal>`	`omd-ralph`
`/omd-deep-interview <topic>`	`omd-deep-interview`
`/omd-ralplan <desc>`	`omd-ralplan`
`/omd-research <question>`	`omd-research`
`/omd-autoresearch <task>`	`omd-autoresearch`
`/omd-ultragoal <goal>`	`omd-ultragoal`
`/omd-pyramid <content>`	`omd-pyramid`

The agent loads the matching skill, runs that mode, and reports progress via the HUD.

Why skills + bundle/preset, not new tools

DSH's native multi-agent primitives (workflow pipelines/parallel, subagent fan-out, ralph fresh-agent loops, goal cross-turn objectives) already cover OMC's orchestration semantics. oh-my-dsh therefore adds no new host tools or runtime — it distills "which primitive to use, when, how to orchestrate, and how to close out" into reusable skills.

Distribution reuses DSH's native mechanisms: cordis.patch.yml + the dsh.bundle manifest make dsh plugin add install a bundle (global commands + skills), and agent.cordis.yml makes it an agent preset (per-session persona + commands + skills). The slash-command commands/omd-commands.mjs is an ESM plugin that injects DSH's built-in commands registry — zero runtime risk, survives DSH upgrades.

Extending

Add a mode: add skills/omd-xxx/SKILL.md (YAML frontmatter with name + description).
Add a command: append an entry to the MODES array in commands/omd-commands.mjs.
Change the persona: edit the persona row at the top of agent.cordis.yml.
Make a skill global: use the bundle (dsh plugin add) or copy skills/* to ${DSH_HOME}/skills/.

License

MIT. Inspired by oh-my-claudecode.

README

oh-my-dsh

A multi-agent orchestration layer for DeepSeek Harness (DSH) — ports oh-my-claudecode's orchestration modes onto DSH's native primitives (workflow / subagent / ralph / goal).

Two ways to trigger: natural language (30 skills, auto-loaded by the agent) + slash commands (13 /omd-* commands). Start a session, orchestration is ready.

中文

Quick Start

One command installs all 30 skills + 13 /omd-* commands (the OMC plugin-marketplace equivalent):

dsh plugin --profile web add github:hawk2048/oh-my-dsh

Or from npm (the npm i -g equivalent):

dsh plugin --profile web add @hawk2048/oh-my-dsh

Restart the profile, type /omd to see command candidates, or use natural language ("plan this", "autopilot, build a REST API").

Requirements

DeepSeek Harness (dsh CLI)
pnpm — dsh plugin forwards to pnpm

Why oh-my-dsh

Zero configuration — one dsh plugin add installs everything; the bundle self-registers, no setup wizard.
Team-first orchestration — Team is the canonical staged pipeline (team-plan → team-prd → team-exec → team-verify → team-fix), built on DSH's native workflow.
Natural language interface — describe what you want; the 30 omd-* skills auto-load, nothing to memorize.
Automatic parallelization — complex tasks fan out across parallel subagents.
Persistent execution — Ralph / Autopilot / Ultragoal keep going until verified complete (native ralph loops + goal cross-turn objectives).
Zero runtime overhead — adds no new host tools or runtime, just skills over DSH's native primitives, so you keep DSH's own model routing and sandbox.
Learn from experience — omd-skillify extracts reusable skills; omd-remember persists durable notes across sessions.
Real-time visibility — the inline HUD renders live dsh-ui progress dashboards.

OMC correspondence

Aligned to OMC v5.3.0 (the plan → execute → review → verify pipeline + retained modes):

OMC workflow	oh-my-dsh skill	DSH primitive
Plan	`omd-plan`	read-only exploration + parallel `subagent`
Execute	`omd-execute`	parallel `subagent` + `todo_write`
Review	`omd-review`	`subagent_fork` independent review
Verify	`omd-verify`	`pwsh`/`bash` tests + `subagent` re-check
Team	`omd-team`	`workflow` + `subagent`
Autopilot	`omd-autopilot`	`goal` + `todo` + `subagent`
Ralph	`omd-ralph`	`ralph` + `goal` verify loop
Deep Interview	`omd-deep-interview`	`ask_user_question`
Ralplan

Prompt-trigger + utility skills (natural-language only, no slash command):

OMC trigger	oh-my-dsh skill	DSH primitive
tdd	`omd-tdd`	`pwsh`/`bash` tests + red-green-refactor
deepsearch	`omd-deepsearch`	`grep`/`glob`/`read` local lookup
deep-analyze	`omd-deep-analyze`	parallel `subagent` multi-angle
ultrathink	`omd-ultrathink`	pure reasoning (no tools first)
ai-slop-cleaner	`omd-ai-slop-cleaner`	`review`/`edit` tightening
omc-doctor	`omd-doctor`	install/mount diagnostics
debug	`omd-debug`	reproduce→isolate→fix→regress
release	`omd-release`	git + tests + changelog + tag
remember

New in this plugin (no OMC counterpart):

Capability	oh-my-dsh skill	DSH primitive
Pyramid structured expression (conclusion-first + MECE)	`omd-pyramid`	pure expression discipline + `dsh-ui` hierarchy mapping (genui)

ultrawork is retired — OMC removed it in 5.0.0 (along with ultraqa/swarm/pipeline); oh-my-dsh removed it too, folding its "maximum parallel fan-out" into execute/team/ralph.

Directory structure

oh-my-dsh/
├── package.json              # dsh.bundle manifest (bundle install entry)
├── cordis.patch.yml          # bundle patch layer (global commands + skills)
├── index.js                  # bundle module entry
├── agent.cordis.yml          # agent preset composition (= standard + persona + skills + commands)
├── preset.yml                # preset display metadata
├── install.ps1 / install.sh  # preset manual install scripts
├── LICENSE
├── commands/
│   └── omd-commands.mjs      # slash-command producer (ESM plugin)
├── skills/
│   ├── omd-plan/SKILL.md
│   ├── omd-execute/SKILL.md
│   ├── omd-review/SKILL.md
│   ├── omd-verify/SKILL.md
│   ├── omd-team/SKILL.md
│   ├── omd-autopilot/SKILL.md
│   ├── omd-ralph/SKILL.md
│   ├── omd-deep-interview/SKILL.md
│   ├── omd-ralplan/SKILL.md
│   ├── omd-research/SKILL.md
│   ├── omd-autoresearch/SKILL.md
│   ├── omd-ultragoal/SKILL.md
│   ├── omd-pyramid/SKILL.md
│   ├── omd-tdd/SKILL.md
│   ├── omd-deepsearch/SKILL.md
│   ├── omd-deep-analyze/SKILL.md
│   ├── omd-ultrathink/SKILL.md
│   ├── omd-ai-slop-cleaner/SKILL.md
│   ├── omd-doctor/SKILL.md
│   ├── omd-debug/SKILL.md
│   ├── omd-release/SKILL.md
│   ├── omd-remember/SKILL.md
│   ├── omd-cancel/SKILL.md
│   ├── omd-minimal-code-discipline/SKILL.md
│   ├── omd-external-context/SKILL.md
│   ├── omd-visual-verdict/SKILL.md
│   ├── omd-skillify/SKILL.md
│   ├── omd-wiki/SKILL.md
│   ├── omd-help/SKILL.md
│   └── omd-hud/SKILL.md
└── docs/
    ├── ARCHITECTURE.md
    └── RELEASE.md

Install / usage

Two forms — pick one (bundle for global, preset for per-session).

Form A: bundle (primary, the OMC plugin-marketplace equivalent) — installs the 13 /omd-* commands and 30 skills globally, visible to every session in the profile:

# git source (pure JS/Markdown, zero build, no allowBuilds needed; pin with @<tag>)
dsh plugin --profile web add github:hawk2048/oh-my-dsh

# or npm (the npm i -g equivalent)
dsh plugin --profile web add @hawk2048/oh-my-dsh

Restart the profile. One command, pulled by pnpm — no manual tarball download.

Form B: agent preset (optional, per-session) — full session with persona and the orchestration toolkit:

# Windows
.\install.ps1
# macOS / Linux
./install.sh

Then create a session and pick the "oh-my-dsh 编排" preset (or set it as agent-presets.default). See docs/RELEASE.md.

Usage (in-session)

Two equivalent ways:

Way 1: natural language (the agent auto-loads the matching skill)

plan how to implement X → omd-plan
execute the plan → omd-execute
review my changes → omd-review
verify — tests must pass → omd-verify
team, build a task-management app → omd-team
autopilot: build a REST API → omd-autopilot
ralph the auth refactor until green → omd-ralph
deep interview me — I want to build X → omd-deep-interview
ralplan this architecture decision → omd-ralplan
research X best practices, with sources → omd-research
autoresearch this report to passing → omd-autoresearch
ultragoal: break this long goal into subgoals → omd-ultragoal
structure this as a pyramid / conclusion first / MECE → omd-pyramid
tdd: failing test first → omd-tdd
deepsearch: who calls this function → omd-deepsearch
deep-analyze this architecture → omd-deep-analyze
ultrathink before acting → omd-ultrathink
strip the AI slop → omd-ai-slop-cleaner
self-check the install → omd-doctor
debug this error → omd-debug
release v1.2 with changelog → omd-release
remember this decision → omd-remember
stop the running autopilot → omd-cancel
minimal change, no over-engineering → omd-minimal-code-discipline
read this issue/link → omd-external-context
compare these screenshots → omd-visual-verdict
turn this flow into a skill → omd-skillify
write this to the wiki → omd-wiki

Way 2: slash commands (type /omd for candidates)

Command	Equivalent skill
`/omd-plan <task>`	`omd-plan`
`/omd-execute <task>`	`omd-execute`
`/omd-review <task>`	`omd-review`
`/omd-verify <task>`	`omd-verify`
`/omd-team <task>`	`omd-team`
`/omd-autopilot <goal>`	`omd-autopilot`
`/omd-ralph <goal>`	`omd-ralph`
`/omd-deep-interview <topic>`	`omd-deep-interview`
`/omd-ralplan <desc>`	`omd-ralplan`
`/omd-research <question>`	`omd-research`
`/omd-autoresearch <task>`	`omd-autoresearch`
`/omd-ultragoal <goal>`	`omd-ultragoal`
`/omd-pyramid <content>`	`omd-pyramid`

The agent loads the matching skill, runs that mode, and reports progress via the HUD.

Why skills + bundle/preset, not new tools

Extending

Add a mode: add skills/omd-xxx/SKILL.md (YAML frontmatter with name + description).
Add a command: append an entry to the MODES array in commands/omd-commands.mjs.
Change the persona: edit the persona row at the top of agent.cordis.yml.
Make a skill global: use the bundle (dsh plugin add) or copy skills/* to ${DSH_HOME}/skills/.

License

MIT. Inspired by oh-my-claudecode.

Oh My Dsh

兼容性与来源证明

版本

相关插件

Oh My Dsh

README

oh-my-dsh

Quick Start

Requirements

Why oh-my-dsh

OMC correspondence

Directory structure

Install / usage

Usage (in-session)

Why skills + bundle/preset, not new tools

Extending

License

兼容性与来源证明

版本

相关插件

相关插件

相关插件

README

oh-my-dsh

Quick Start

Requirements

Why oh-my-dsh

OMC correspondence

Directory structure

Install / usage

Usage (in-session)

Why skills + bundle/preset, not new tools

Extending

License