grtninja/qwen-training-desktop-ops
skill-candidates/qwen-training-desktop-ops/SKILL.md
Operate the local Qwen Training Workbench desktop shell and its `9041` worker as one restart-safe local contract. Use when fixing or validating the Electron shell, launcher path, local dashboard load, queue or campaign controls, job visibility, or desktop startup acceptance for the private training app.
$ install --global
skillsauthnpx skillsauth add grtninja/skill-arbiter qwen-training-desktop-opsInstall 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 5, 2026, 2:32 PM366.9s4 files scanned
SKILL.md
- name:
- qwen-training-desktop-ops
- description:
- Operate the local Qwen Training Workbench desktop shell and its `9041` worker as one restart-safe local contract. Use when fixing or validating the Electron shell, launcher path, local dashboard load, queue or campaign controls, job visibility, or desktop startup acceptance for the private training app.
Qwen Training Desktop Ops
Use this skill for the local Qwen Training Workbench desktop surface, not just the long-running training lane behind it.
Workflow
- Treat the desktop shell and the
9041worker as one owned local contract. - Validate the backend first:
http://127.0.0.1:9041/healthhttp://127.0.0.1:9041/readyhttp://127.0.0.1:9041/v1/training-agent/status
- Launch only through the canonical repo-owned desktop entrypoint.
- Confirm the shell loads the worker UI from
http://127.0.0.1:9041/instead of drifting to a packaged or remote surface. - Prefer worker truth over renderer assumptions for queue, campaigns, jobs, and submissions.
- Keep the operator flow explicit:
- desktop start
- worker readiness
- campaign or job submission
- active and queued job visibility
- artifact and runtime inspection
- Restart the desktop after Electron-shell changes. Do not claim UI fixes without a real relaunch.
Canonical Commands
Desktop launch:
powershell -ExecutionPolicy Bypass -File `
<training-workbench-root>\tools\start_qwen_training_workbench_desktop.ps1
Worker lifecycle:
powershell -ExecutionPolicy Bypass -File `
<training-workbench-root>\tools\start_qwen_training_workbench_agent.ps1
powershell -ExecutionPolicy Bypass -File `
<training-workbench-root>\tools\stop_qwen_training_workbench_agent.ps1
powershell -ExecutionPolicy Bypass -File `
<training-workbench-root>\tools\get_qwen_training_workbench_agent_status.ps1
Health checks:
curl http://127.0.0.1:9041/health
curl http://127.0.0.1:9041/ready
curl http://127.0.0.1:9041/v1/training-agent/status
curl http://127.0.0.1:9041/v1/training-agent/jobs
curl http://127.0.0.1:9041/v1/training-agent/campaigns
Runtime Truth
Prefer these surfaces as the source of truth:
apps/qwen-training-desktop/apps/local_dashboard/tools/qwen_training_workbench_agent.pyevidence/agent_runtime/qwen_training_workbench_agent_state.jsonevidence/agent_runtime/jobs/evidence/agent_runtime/submissions/
Scope Boundary
Use this skill for the training desktop shell, launcher, worker coupling, and operator-facing runtime views.
Do not use this skill for:
- dataset-factory or continuation-batch decision making without the desktop/operator context
- generic Electron packaging work outside this app
- docs-only wording cleanup
References
references/ops-checklist.mdreferences/runtime-surfaces.md
Related Skills
grtninja/white-hat
tools
VerifiedTrustedCommunity
Run a defender-first security sweep on code, configs, prompts, model/tooling surfaces, or third-party contribution lanes. Use when a request involves safe bug, leak, zero-day-class, exploit, or hack hunting for protection, when contributing to outside repositories and you want a focused security pass, or when touching auth, secrets, permissions, network exposure, prompt/tool boundaries, data flow, or update/build surfaces. This skill is defensive only and must never be used for weaponization or unauthorized access.
2SKILL.mdUpdated Apr 22, 2026
grtninja/vrm-sandbox-startup-acceptance
development
VerifiedTrustedCommunity
Validate and repair VRM Sandbox startup acceptance with shim-first local model authority, frontend/backend bring-up, and avatar-runtime launch proof. Use when launch behavior, chat handoff, voice fallback, or runtime bridge acceptance must be verified end to end.
2SKILL.mdUpdated Apr 22, 2026
grtninja/voice-catalog-runtime-alignment
documentation
VerifiedTrustedCommunity
Align documented voice-command catalogs, endpoint action allowances, and live runtime handlers so operator-visible voice surfaces match what the stack can actually execute. Use when voice command docs, parser matrices, endpoint permissions, or runtime action routing drift apart.
2SKILL.mdUpdated Apr 22, 2026
grtninja/skillhub-trend-radar
development
VerifiedTrustedCommunity
Track SkillHub trend and topic drift, maintain a bounded rewrite watchlist, and surface emerging gaps worth turning into repo-owned skills. Use when the marketplace query set shows new families or when the current shortlist has gone stale.
2SKILL.mdUpdated Apr 22, 2026