agentic-creator-os / hub-generator
CLAUDE.md10 starsChanged 7 months agoApache-2.0View on GitHub
The Creator Hub Generator is a wizard that helps any creator bootstrap their own personalized AI operating system. It captures your identity, workflows, tools, and voice - then generates a complete .creator-hub/ directory with everything you need. This launches the 4-step wizard: 1. Identity Discovery - Who you are and what you create 2. Workflow Mapping - Your regular creative activities 3. Tool Integration - Platforms and tools you use 4. Voice Calibration - Capture your unique writing voice "Every…
We split this CLAUDE.md into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 56
Keep under 100 lines. It's a DIGEST, not an archive.
- Distinctive: line 57
Keep only 3-5 recent decisions
- Distinctive: line 58
Keep only active blockers
- Distinctive: line 62
Every task MUST have built-in verification:
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Creator Hub Generator
Bootstrap your personal AI operating system in 15 minutes
What Is This?
The Creator Hub Generator is a wizard that helps any creator bootstrap their own personalized AI operating system. It captures your identity, workflows, tools, and voice - then generates a complete .creator-hub/ directory with everything you need.
Quick Start
/acos:init-hubThis launches the 4-step wizard:
- Identity Discovery - Who you are and what you create
- Workflow Mapping - Your regular creative activities
- Tool Integration - Platforms and tools you use
- Voice Calibration - Capture your unique writing voice
What Gets Generated
.creator-hub/
├── HUB.md # Creator identity + context
├── STATE.md # Living memory (< 100 lines)
├── VOICE.md # Captured writing voice patterns
├── skills/ # Auto-selected skills
│ ├── content-strategy/
│ ├── social-distribution/
│ └── [selected-skills]/
├── workflows/ # Generated workflows
│ ├── daily-ops.md
│ ├── content-creation.md
│ └── [custom-workflows]/
├── templates/ # Content templates
│ ├── blog-post.md
│ ├── social-post.md
│ └── newsletter.md
└── outputs/ # Generated content
└── [by-date]/Core Patterns (from GSD)
Context Quality Curve
0-30% → Peak performance zone
30-50% → Good quality, watch for degradation
50-70% → Degrading, split tasks to subagents
70%+ → Poor quality, MUST spawn fresh contextSTATE.md Constraint
Keep under 100 lines. It's a DIGEST, not an archive. If it grows too large:
- Keep only 3-5 recent decisions
- Keep only active blockers
- Archive completed context
Task Verification
Every task MUST have built-in verification:
<task type="auto">
<name>Action-oriented name</name>
<files>exact/paths/to/files</files>
<action>What to do, what to avoid, and WHY</action>
<verify>Exact command or check to prove completion</verify>
<done>Binary acceptance criteria</done>
</task>Files in This Directory
| File | Purpose |
init-hub.md | The initialization wizard command |
templates/HUB.md | Template for creator identity file |
templates/STATE.md | Template for living memory |
templates/VOICE.md | Template for voice patterns |
templates/daily-ops.md | Template for daily workflow |
skill-mappings.json | Workflow-to-skill auto-selection |
Philosophy
"Every creator should be able to bootstrap their own AI operating system in 15 minutes."
This generator embodies:
- GSD's rigor - Context engineering, verification, deviation rules
- ACOS's creator focus - Skills, agents, workflows for creators
- Personal Jarvis - AI that knows YOU and serves YOUR vision
Creator Hub Generator - Part of Agentic Creator OS v4
In this repository131 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/commands/monitoring/agents.mdAGENTS.md
- .claude/skills/gstack/AGENTS.mdAGENTS.md
- .claude/agents/CLAUDE.mdCLAUDE.md
- .claude/commands/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .claude/skills/agentic-orchestration/CLAUDE.mdCLAUDE.md
- .claude/skills/cacos/CLAUDE.mdCLAUDE.md
- .claude/skills/CLAUDE.mdCLAUDE.md
- .claude/skills/frankx-daily-execution/CLAUDE.mdCLAUDE.md
- .claude/skills/gstack/CLAUDE.mdCLAUDE.md
- .claude/skills/memory-guardian/CLAUDE.mdCLAUDE.md
- .claude/skills/newsletter/CLAUDE.mdCLAUDE.md
- .claude/skills/oci-services-expert/CLAUDE.mdCLAUDE.md
- .claude/skills/oracle-ai-architect/CLAUDE.mdCLAUDE.md
- .claude/skills/oracle-diagram-generator/CLAUDE.mdCLAUDE.md
- .claude/skills/research/CLAUDE.mdCLAUDE.md
- .claude/skills/swarm-advanced/CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- drafts/CLAUDE.mdCLAUDE.md
- instances/CLAUDE.mdCLAUDE.md
- mcp-servers/CLAUDE.mdCLAUDE.md
- outputs/CLAUDE.mdCLAUDE.md
- scripts/CLAUDE.mdCLAUDE.md
- skills/CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- workflows/CLAUDE.mdCLAUDE.md
- acos-metaSkill
- agentic-jujutsuSkill
- agentic-orchestrationSkill
- AI Architect NewsletterSkill
- ai-architectureSkill
- algorithmic-artSkill
- apod-to-shortSkill
- arxiv-space-paper-to-briefSkill
- book-publishingSkill
- brand-guidelinesSkill
- brand-voiceSkill
- cacosSkill
- canvas-designSkill
- Claude SDK ExpertSkill
- cosmic-mythic-overlaySkill
- creator-productivitySkill
- descript-operatorSkill
- doc-coauthoringSkill
- docxSkill
- excellence-book-writingSkill
- Framer ExpertSkill
- frankx-brandSkill
- FrankX Daily Execution SystemSkill
- frontend-designSkill
- game-developmentSkill
- github-code-reviewSkill
- github-multi-repoSkill
- github-project-managementSkill
- github-release-managementSkill
- github-workflow-automationSkill
- Greek PhilosopherSkill
- grok-harnessSkill
- gstackSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

