mikeshu2001/content-factory
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
Markdown-first, human-gated multi-agent editorial workflow with explicit research, planning, writing, and review artifacts.
概要
A Markdown-first, human-gated multi-agent workflow for producing long-form editorial content from source material or research. Content Factory separates research, planning, writing, and whole-document editing into explicit roles. Each machine-produced stage leaves an inspectable file, human approval is explicit in the conversation, and writing cannot begin until that approval is given. this repository contains orchestration specifications, agent instructions, editorial policies, and templates. It is not a hosted application, an autonomous agent runtime, or evidence of unattended production volume. The orchestrator is the main agent context, not another isolated reviewer. It checks the plan, enforces the approval gate, reads the complete draft against the source and examples, and performs the final edit. See the architecture notes for the artifact contract, stop conditions, and design rationale. The included write-* workflows are sequential.
README
以下は原文 README の抜粋です。原文を見る。
Content Factory
A Markdown-first, human-gated multi-agent workflow for producing long-form editorial content from source material or research.
Content Factory separates research, planning, writing, and whole-document editing into explicit roles. Each machine-produced stage leaves an inspectable file, human approval is explicit in the conversation, and writing cannot begin until that approval is given.
Project scope: this repository contains orchestration specifications, agent instructions, editorial policies, and templates. It is not a hosted application, an autonomous agent runtime, or evidence of unattended production volume.
Workflow
source file or topic
|
v
researcher (optional) -> research.md
|
v
planner -> plan.md
|
v
orchestrator review
|
v
HUMAN APPROVAL GATE
|
v
writer, block by block -> draft.md
|
v
orchestrator/editor -> final.md
The orchestrator is the main agent context, not another isolated reviewer. It checks the plan, enforces the approval gate, reads the complete draft against the source and examples, and performs the final edit.
| Role | Responsibility | Reads | Produces |
|---|---|---|---|
researcher |
Collects source-backed facts for topic-led pieces | Topic, project profile, web sources | research.md |
article-researcher |
Revalidates products, prices, capabilities, and limitations | Source list, current web sources | research.md |
planner |
Turns evidence and editorial policy into a block-level structure | Source, research, policy, examples | plan.md |
| Human reviewer | Corrects direction while changes are still cheap | Reviewed plan | Explicit approval or requested changes |
writer |
Writes only assigned blocks from the approved plan | Plan, source, research, existing draft | draft.md |
| Orchestrator/editor | Checks evidence, structure, voice, repetition, and final coherence | All run artifacts | final.md |
See the architecture notes for the artifact contract, stop conditions, and design rationale.
Execution model: sequential by design
The included write-* workflows are sequential. Research must finish before planning; the plan must pass review and human approval before writing; writer calls append blocks in order; final editing starts only after the draft is complete.
Multiple specialist agents do not imply parallel execution here. The repository does not include a parallel scheduler, job queue, retry engine, or observability layer. Independent research branches could be parallelized by a compatible runner, but that behavior is not implemented in this public version.
This constraint is intentional: downstream stages depend on explicit file artifacts, and later writer calls need the current draft to preserve continuity and avoid duplication.
What is included
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add mikeshu2001/content-factory