grtninja/media-workbench-worker-contracts
skill-candidates/media-workbench-worker-contracts/SKILL.md
Guard the STARFRAME Media Workbench worker ownership contract, queue/work-item lifecycle, and desktop-to-worker status surfaces. Use when changes touch `9040`, job payloads, resumable work items, operator snapshots, or worker-facing docs/tests.
$ install --global
skillsauthnpx skillsauth add grtninja/skill-arbiter media-workbench-worker-contractsInstall 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 22, 2026, 8:20 PM69.7s3 files scanned
SKILL.md
- name:
- media-workbench-worker-contracts
- description:
- Guard the STARFRAME Media Workbench worker ownership contract, queue/work-item lifecycle, and desktop-to-worker status surfaces. Use when changes touch `9040`, job payloads, resumable work items, operator snapshots, or worker-facing docs/tests.
Media Workbench Worker Contracts
Use this skill when the Media Workbench 9040 worker contract changes and the desktop shell, queue lifecycle, and operator-visible state all need to stay aligned.
Workflow
- Read the target repo
AGENTS.mdand the operator app contract first. - Treat the repo as the sole owner of the
9040worker contract, local dashboard, and thin desktop shell. - Inspect these worker surfaces together:
/health/ready/v1/media-agent/status/v1/media-agent/jobs/v1/media-agent/summary
- Preserve operator-visible workflow state:
active_job_id- queue depth and tracked jobs
- resumable work item target
- draft state continuity
- output/artifact visibility
- Validate desktop-to-worker coupling:
- healthy worker reuse when already up
- repo-owned bootstrap when down
- queue, cancel, retry, and resume-latest routes stay consistent
- runtime snapshot and operator snapshot still describe the same active systems
- When job payloads or status fields change, update Electron IPC, docs, and tests in the same pass.
Required Evidence
- worker health and ready proof
- current status or summary payload
- queue or work-item lifecycle proof for the changed path
- note of any operator-visible field that changed
- exact docs/tests updated with the contract change
Guardrails
- Sister repos may submit work through the worker, but they do not redefine the contract.
- Do not hide or silently reset active job, draft, or resume state.
- Keep source-by-reference behavior intact; do not duplicate the source library to satisfy the UI.
- If worker health, queue lifecycle, or resume semantics are ambiguous, fail closed and report the contract as unresolved.
Best-Fit Companion Skills
$media-workbench-desktop-ops$local-compute-usage$docs-alignment-lock$skill-common-sense-engineering
Scope Boundary
Use this skill only for the Media Workbench worker contract and its desktop/operator coupling.
Do not use it for:
- generic Comfy workflow tuning without contract changes
- full training-workbench tasks
- VRM or avatar runtime work
References
references/worker-contract-checklist.md
Loopback
If this lane is unresolved, blocked, or ambiguous:
- capture the failing worker route or status field
- route back through
$skill-hubfor chain recalculation - resume only after the updated chain returns a deterministic contract fix path
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