Fis Architecture
Skill by muselinn
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/muselinn/fis-architectureFIS (Federal Intelligence System) Architecture Skill
Version: 3.2.6
Name: Federal Intelligence System (联邦智能系统)
Description: File-based multi-agent workflow framework. Core: JSON tickets + Markdown knowledge (no Python required). Optional: Python helpers inlib/for badge generation. Integrates with OpenClaw QMD for semantic search.Security: See SECURITY.md for subprocess usage, resource permissions, and sandboxing guidelines.
Note: Legacy FIS 3.1 components (memory_manager, skill_registry, etc.) are preserved in GitHub repo history but not included in this release. See repo for historical reference.
Status: ✅ Stable — Simplified architecture with QMD integration
Before You Install
Core workflow: Pure file-based (JSON tickets, Markdown). No Python required for basic use.
Optional components (review before use):
lib/*.py— Badge generation helpers (requirepip install Pillow qrcode)lib/fis_lifecycle.py— CLI helpers for ticket management
Required: mcporter CLI (included with OpenClaw), openclaw CLI
Security: Review SECURITY.md before running Python scripts or granting ticket resources permissions.
Core Principle: FIS Manages Workflow, QMD Manages Content
FIS 3.2 is a radical simplification of FIS 3.1. We removed components that overlapped with QMD (Query Model Direct) semantic search capabilities:
| Component | FIS 3.1 | FIS 3.2 | Reason |
|---|---|---|---|
| Task Management | Python classes + memory_manager | Ticket files (JSON) | Simpler, audit-friendly |
| Memory/Retrieval | memory_manager.py | QMD | QMD has native semantic search |
| Skill Discovery | skill_registry.py | SKILL.md + QMD | QMD indexes SKILL.md files |
| Knowledge Graph | experimental/kg/ | QMD | QMD covers knowledge discovery |
| Deadlock Detection | deadlock_detector.py | Simple conventions | Rarely needed in practice |
What's Kept: Only the unique workflow capabilities that FIS provides.
What's New in 3.2.0
Simplified Architecture
- Core workflow: File-based (JSON tickets, Markdown knowledge) — no Python required
- Optional helpers: Python scripts in
lib/for badge generation (auditable, optional) - Official integration: Uses OpenClaw QMD for semantic search — see https://docs.openclaw.ai/concepts/memory
- Badge generator: Visual identity for subagents (requires Pillow, optional)
Directory Structure
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-muselinn-fis-architecture": {
"enabled": true,
"auto_update": true
}
}
}