Skip to content
Agentmart
Submit a tool

dasheng-sop-orchestrator

Use when running, resuming, or auditing the full Dasheng 8-stage media workflow with strict stage contracts and delivery outputs.

Skill by leecyno1

IndexedMIT★ 5
Write a review

Chalk Labs

Need help deploying dasheng-sop-orchestrator?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/leecyno1-dasheng-sop-orchestrator

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when running, resuming, or auditing the full Dasheng 8-stage media workflow with strict stage contracts and delivery outputs.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/dasheng-sop-orchestrator

What's inside

Skill name
dasheng-sop-orchestrator
Description
Use when running, resuming, or auditing the full Dasheng 8-stage media workflow with strict stage contracts and delivery outputs.
License
MIT
Instructions
87 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • openai.yaml · agents/
  • stage-contract.md · references/

SKILL.md (first lines)

# Dasheng SOP Orchestrator

## 目的

统一调度 8 阶段创作流,防止越级、混稿、漏交付。

## 默认路径

- `DASHENG_WORKSPACE=${DASHENG_WORKSPACE:-${DASHENG_PROJECT_ROOT}}`

## 固定主链

`intake -> brief -> draft -> material -> rewrite -> publish -> distribute -> postmortem`

## 执行规则

1. 先识别当前阶段(用户说”继续/开始某阶段”时不得猜错阶段)。
2. 只调用当前阶段技能,不提前产出下游正式交付。
3. 每阶段必须产出文档 + manifest。
4. 多选题必须分题独立目录,禁止混稿。

## 阶段路由

- `intake` -> `dasheng-stage-intake-brief-draft` (intake 环节)
- `brief` -> **`dasheng-stage-brief-ai`** (AI 驱动选题生成,替代旧的规则系统)
- `draft` -> `dasheng-stage-intake-brief-draft` (draft 环节)
- `material` -> `dasheng-stage-material-refill`
- `rewrite` -> `dasheng-stage-rewrite` (已集成框架和策略)
- `publish` -> `dasheng-stage-publish-video` (视频补充生成)
- `distribute` -> **`dasheng-stage-distribute`** (多平台分发:微信/小红书/抖音/微博/X)
- `postmortem` -> 按项目复盘约定执行(可沿用现有复盘脚本)

### Distribute 阶段说明

**新增阶段(在 publish 和 postmortem 之间)**:`dasheng-stage-distribute`
- ✅ 读取 rewrite_manifest.json 自动路由内容到各平台
- ✅ 生成平台适配内容(微博摘要/X 推文串/抖音字幕)
- ✅ 调用现有 OpenClaw 平台 skill 执行发布
- ✅ 支持微信/小红书/抖音/微博/X 五大平台
- ⚠️ 微信仅保存草稿,需后台手动发布
- ⚠️ 微博需飞书审批后执行
- ⚠️ X 需用户在浏览器中手动确认

**调用的外部 Skills**:
```
wechat-multi-publisher  → 微信公众号
weibo-manager           → 微博(审批流)
baoyu-post-to-x         → X (Twitter)
xiaohongshu-auto        → 小红书
douyin-upload-skill     → 抖音
```

### Brief 环节升级说明

**新系统(推荐)**:`dasheng-stage-brief-ai`
- ✅ AI 理解事件因果关系
- ✅ 生成自然语言标题(不是模板拼接)
- ✅ 推荐写作框架和内容增强策略
- ✅ 提供完整的论证和证据需求
- ✅ 候选选题数量:10-15 个(vs 旧系统的 5 个)

**旧系统(备份)**:`phase2_rebuilder.py`
- 保留作为回退方案
- 仅在 AI 系统失败时使用

**使用方式**:
```bash
# 通过 Claude Code 或 OpenClaw 调用
# 输入:产物/01_内容采集/{run_id}/
# 输出:产物/02_Brief/{run_id}/selected_topics.json
```

## 入口校验

执行前先检查:

- `${DASHENG_WORKSPACE}/引擎/03_全链路SOP工作流/STAGE_INTERFACES.md`
- `${DASHENG_WORKSPACE}/skills/dasheng-media-sop/SKILL.md`

## 每日首跑自检(强制)

首次运行当天任务前,先执行一次最小自检并记录:

- 自检提示词:`SMOKE_PROMPTS.md` 的“全链路最小自检”
- 交付:`smoke_report.md`(仅状态、风险、阻塞,不产出正式稿件)

From leecyno1/newma-media-studio, MIT.

More from leecyno1/newma-media-studio

Signals

Stars
5
Forks
1
Open issues
0
Last commit (this folder)
Aug 3, 2026 (3 months ago)
Last release
Aug 3, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from leecyno1

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get dasheng-sop-orchestrator running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying dasheng-sop-orchestrator?

CallGet help
Cite this page

dasheng-sop-orchestrator skill. Agent Mart. https://agentmart.dev/skills/leecyno1-dasheng-sop-orchestrator (last updated 2026-10-24)