ContentOS

English | 中文

---

English

An agent-agnostic, self-improving daily content workflow. It scans high-quality sources, turns fresh signals into a briefing, and drafts posts in your voice.

Bring Codex, Claude Code, Cursor, Gemini CLI, OpenCode, or your own agent. ContentOS is a workflow and data contract, not a model, vendor, or CLI-specific application.

Built by @starzq, who uses it every morning for AI, crypto, US equities, space, and solo-business research.

ContentOS reads curated X accounts, newsletters, podcasts, and other sources; filters them through your topic library and positioning; then produces a daily briefing and drafts. On the next run, it learns from your published-post performance and adjusts its recommendations.

It is not another summarizer. The design premise is that summarizing is cheap and judgment is expensive, so the workflow spends most of its effort on freshness, deduplication, source quality, voice, and editorial boundaries.

Video walkthrough

▶ Watch on YouTube: Self-improving Daily Content OS

---

What is in this repository

ContentOS has four portable parts:

• SKILL.md — the complete learn → do → reflect workflow, written as agent instructions.
• Config templates — your sources, topic library, positioning, voice, and red lines.
• Workflow constraints and build-time guards — editorial rules in the instructions, plus Python checks for stale must-reads and missing or duplicate event_id values.
• A local dashboard — a self-contained HTML file with embedded data; no server or database required.

SKILL.md includes tool names from the author's current setup. They are reference adapters, not platform requirements. Map them to equivalent tools in your agent.

Agent compatibility

Any tool-using agent can run ContentOS after mapping its tools to these capabilities:

Capability	Used for	Required?
Read and write local files	Config, memory, archives, and output	Yes
Access fresh web and/or X data	Daily source collection	Yes
Run Python 3	Validation and dashboard data injection	Yes for the full workflow
Read your publishing analytics	Learn what performed well	Optional
Run unattended on a schedule	Daily automation	Optional

MCP is one way to provide these capabilities, but it is not required. Native tools, connectors, APIs, browser automation, or your own scripts work as well.

---

What it produces

Output	Description
ContentOS/daily_brief/daily_briefing_YYYY-MM-DD.md	Market snapshot, must-reads, extended reading, topic candidates, drafts, and system suggestions
ContentOS/daily_brief/daily_data.json	The same result as structured data
ContentOS/daily_brief/daily_briefing.html	A nine-tab, single-file dashboard that opens locally
profile_recent.md	Rolling memory derived from publishing performance when analytics are available

See examples/sample-briefing-2026-08-06.md for a real, redacted output.

Dashboard preview

The generated dashboard keeps the full workflow in one place: fresh signals, topic ideas, drafts, publishing history, source management, and system suggestions.