abdulmateen5251/.agents/skills/qwen-agent
.agents/skills/qwen-agent/SKILL.md
```skill --- name: qwen-agent description: Autonomous Qwen Code agent loop — reads Needs_Action, reasons via Qwen Code CLI, writes drafts to Pending_Approval, and executes approved MCP actions. --- ``` # Qwen Agent The core reasoning brain of the Personal AI Employee. This skill integrates Qwen Code CLI as the autonomous reasoning engine over the Obsidian Vault. ## Architecture ``` Filesystem Watcher / Gmail Watcher ↓ (writes files) Vault/Needs_Action/ ↓ (reads + prompts qw
tools
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add abdulmateen5251/Personal-AI-Employee .agents/skills/qwen-agentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 8:04 PM3.5s5 files scanned
SKILL.md
---
name: qwen-agent
description: Autonomous Qwen Code agent loop — reads Needs_Action, reasons via Qwen Code CLI, writes drafts to Pending_Approval, and executes approved MCP actions.
---
Qwen Agent
The core reasoning brain of the Personal AI Employee. This skill integrates Qwen Code CLI as the autonomous reasoning engine over the Obsidian Vault.
Architecture
Filesystem Watcher / Gmail Watcher
↓ (writes files)
Vault/Needs_Action/
↓ (reads + prompts qwen CLI)
qwen_agent.py
↓ (writes drafts)
Vault/Pending_Approval/
↓ (human approves → moves to Approved/)
qwen_agent.py (detects Approved/)
↓ (calls MCP)
Gmail Send MCP / Social Poster / Odoo MCP
↓
Vault/Done/
Ralph Wiggum Stop Hook
The .qwen/hooks/ralph_stop_hook.py runs after every Qwen Code response.
It checks if Vault/Needs_Action/ has remaining items:
- If YES → injects a "continue" message (exit code 2) → Qwen keeps working
- If NO → exits 0 → Qwen stops
Usage
Start (polling loop):
bash .agents/skills/qwen-agent/scripts/start.sh
Run once (for testing):
.venv/bin/python .agents/skills/qwen-agent/scripts/qwen_agent.py --once
Stop:
bash .agents/skills/qwen-agent/scripts/stop.sh
Verify:
.venv/bin/python .agents/skills/qwen-agent/scripts/verify.py
Manual Qwen Code (Interactive Mode)
To run Qwen Code interactively with the full system prompt:
cd /home/abdul-matten/Desktop/Personal-AI-Employee
qwen
Qwen Code will automatically read QWEN.md as its system instructions and
.qwen/settings.json for the Ralph Wiggum Stop Hook.
Related Skills
abdulmateen5251/.agents/skills/watchdog
data-ai
VerifiedTrustedCommunity
```skill --- name: watchdog description: Monitors and restarts watcher and orchestrator processes. --- ``` # Watchdog Monitors and restarts core background services. ## Start ```bash bash scripts/start.sh ``` ## Stop ```bash bash scripts/stop-all.sh ``` ## Status ```bash bash scripts/status.sh ```
SKILL.mdUpdated Apr 16, 2026
abdulmateen5251/.agents/skills/social-poster
testing
VerifiedTrustedCommunity
```skill --- name: social-poster description: Draft-first Facebook, Instagram, and X posting with approval workflow and posting summaries. --- ``` # Social Poster Creates social post drafts for Facebook, Instagram, and X (Twitter), routes them through `/Pending_Approval`, and processes approved posts with audit logging and summaries. ## Platforms - Facebook - Instagram - Twitter (X) ## Server Lifecycle ### Start ```bash bash scripts/start.sh ``` ### Stop ```bash bash scripts/stop.sh ``` #
SKILL.mdUpdated Apr 16, 2026
abdulmateen5251/.agents/skills/ralph-loop
tools
VerifiedTrustedCommunity
```skill --- name: ralph-loop description: Persistence loop utility that keeps re-running task commands until completion conditions are met. --- ``` # Ralph Loop Implements a persistence pattern for long multi-step tasks by repeatedly running a command until completion criteria are satisfied. ## Usage ```bash python3 scripts/ralph_loop.py \ --command "python3 .agents/skills/orchestrator/scripts/orchestrator.py" \ --done-file "Vault/Done/TASK_COMPLETE.md" \ --max-iterations 10 ``` ## Co
SKILL.mdUpdated Apr 16, 2026
abdulmateen5251/.agents/skills/orchestrator
development
VerifiedTrustedCommunity
```skill --- name: orchestrator description: Coordinates Needs_Action processing, plans, approvals, and dashboard updates. --- ``` # Orchestrator Coordinates Perception → Reasoning → Action for the vault workflow. ## Server Lifecycle ### Start ```bash bash scripts/start.sh ``` ### Stop ```bash bash scripts/stop.sh ``` ### Verify ```bash python3 scripts/verify.py ```
SKILL.mdUpdated Apr 16, 2026