メニュー
Audit Cybertron remote-host readiness, repo parity, WinRM auth-state, MeshGPT host-terminal bootstrap, canonical model-matrix validation, Starframe/Cybertron offload checks, and VRM display readiness.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | cybertron-fabric-host-ops |
| description | Audit Cybertron remote-host readiness, repo parity, WinRM auth-state, MeshGPT host-terminal bootstrap, canonical model-matrix validation, Starframe/Cybertron offload checks, and VRM display readiness. |
Use this skill for Cybertron host governance when remote management, repo parity, model placement, or VRM display readiness need to be validated as one bounded lane.
skill-hub and skills-cross-repo-radar first so the Cybertron lane is isolated from unrelated repo work.<external-candidate-root> against any paired $env:USERPROFILE\... clonemultitask-orchestrator only when the parity, model, and host-readiness lanes can run independently.skill-auditor, then pass admission through skill-arbiter-lockdown-admission and skill-enforcer.skill-trust-ledger if the skill is materially updated again.Run from <external-candidate-root>\skill-arbiter:
python skill-candidates/cybertron-fabric-host-ops/scripts/cybertron_repo_parity.py --left <external-candidate-root>\skill-arbiter --right $env:USERPROFILE\...\skill-arbiter --json-out .tmp/cybertron-repo-parity.json
python skill-candidates/cybertron-fabric-host-ops/scripts/cybertron_model_matrix_check.py --json-out .tmp/cybertron-model-matrix.json
python skill-candidates/cybertron-fabric-host-ops/scripts/cybertron_host_readiness.py --host CYBERTRON_CORE --ports 5985 3389 9000 2337 8892 --json-out .tmp/cybertron-host-readiness.json
python skill-candidates/cybertron-fabric-host-ops/scripts/cybertron_fabric_host_audit.py --skill-root skill-candidates/cybertron-fabric-host-ops --json-out .tmp/cybertron-fabric-host-audit.json
Model-plane note:
:9000 and :2337 as authoritative model lanes.:1234 only as a non-authoritative operator surface if it is inspected at all.Use this skill only for Cybertron fabric host operations and the admission evidence needed to support them.
Do not use it for general desktop bring-up or unrelated repo work; route those through $skill-hub and the most specific matching skill.
references/host-readiness.mdreferences/repo-parity.mdreferences/model-matrix.mdreferences/admission-workflow.mdIf the lane is unresolved, blocked, or ambiguous:
$skill-hub for chain recalculation.Run the local NullClaw host security app for skill governance, curated-source discovery, guarded threat suppression, and self-governance on Windows hosts.
Sweep one or more local repositories for implementation gaps and produce deterministic, evidence-backed remediation lanes. Use when you need cross-repo detection of missing tests, docs lockstep drift, risky TODO/FIXME additions, and release-hygiene misses.
Build and query bounded metadata-only repository indexes without rg process churn. Use when working in very large repos and you need deterministic file discovery by path, extension, language, scope, or freshness.
Detect recent cross-repo work and produce deterministic JSON evidence for skill curation and routing decisions. Use when workflows span multiple repos and you need a bounded view of recent commits, touched files, and policy/contract-sensitive changes.
Enforce hardware-first diagnosis and fixes in <PRIVATE_REPO_B>. Use for runtime probe, telemetry, inference, and integration failures where strict real-hardware behavior, no new stubs, deterministic diagnostics, and no unrequested driver/runtime mutation are required.
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.