skill-candidates/media-workbench-desktop-ops/SKILL.md
Operate the STARFRAME Media Workbench desktop app and its local 9040 worker as one restart-safe local contract. Use when fixing or validating the Electron shell, source staging flow, prompt-head automation, queue submission, live telemetry, output preview, or desktop startup acceptance for the private media app.
npx skillsauth add grtninja/skill-arbiter media-workbench-desktop-opsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill for the local STARFRAME Media Workbench app surface, not just the raw render lanes behind it.
media_workbench mode before touching the app.9040 worker as one owned contract.http://127.0.0.1:9040/healthhttp://127.0.0.1:9040/readyhttp://127.0.0.1:9040/v1/media-agent/status<media-workbench-output-root>\work_itemsBackend lifecycle:
powershell -ExecutionPolicy Bypass -File `
<media-workbench-root>\tools\start_media_workbench_agent.ps1
powershell -ExecutionPolicy Bypass -File `
<media-workbench-root>\tools\stop_media_workbench_agent.ps1
powershell -ExecutionPolicy Bypass -File `
<media-workbench-root>\tools\get_media_workbench_agent_status.ps1
Desktop lifecycle:
powershell -ExecutionPolicy Bypass -File `
<media-workbench-root>\tools\start_media_workbench_desktop.ps1
Health checks:
curl http://127.0.0.1:9040/health
curl http://127.0.0.1:9040/ready
curl http://127.0.0.1:9040/v1/media-agent/status
curl <prompt-head-lane>/health
curl <prompt-head-lane>/v1/models
Prefer these surfaces as the source of truth:
apps/media-workbench-desktop/ui/apps/media-workbench-desktop/electron/tools/media_workbench_agent.pyevidence/agent_runtime/media_workbench_agent_state.jsonevidence/agent_runtime/jobs/evidence/agent_runtime/submissions/<media-workbench-output-root>\work_itemsAt minimum, require:
9040 is healthy and readyUse this skill for the Media Workbench app shell, worker contract, and operator flow.
Do not use this skill for:
references/ops-checklist.mdreferences/runtime-surfaces.mdtools
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.
development
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.
documentation
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.
development
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.