bojak83318
- 12 skills
- 0 followers
- 7 hours ago last updated
- ▌ Sub Mini · bojak83318Use this skill when implementing work from `/home/rocm/clawcontrol/implementation.md` with a small delegated coding model, especially when the user wants execution driven by `gpt-5.1-codex-mini` and task progress tracked in `/home/rocm/clawcontrol/TASK.md`.
- ▌ Main Loop · bojak83318Use this skill for PRD-driven execution loops where one main agent orchestrates bounded sub-agents, keeps trying viable paths, logs what worked and what failed, and stops only when the PRD acceptance criteria pass or all PRD paths are exhausted.
- ▌ Kasm Manager · bojak83318 bundleManage, troubleshoot, and develop for Kasm Workspaces. Use for restarting services, checking container health, using the Kasm Public API, or building custom images.
- ▌ Vsrail Win11 · bojak83318End-to-end guide for installing, configuring, and cloning Windows 11 on the VSRail/Incus platform. Includes TPM bypass, driver loading, RDP setup, and Sysprep procedures.
- ▌ Dn577 Network Map · bojak83318Provides the current Tailscale network map for the dn577 project. Use this skill to retrieve IPs for the host, dockge-lxc, kasm-vm, ffmpeg-service, and vsrail-novnc.
- ▌ Win11 Vsrail Setup · bojak83318Canonical setup and maintenance guide for the win11-vsrail Virtual Machine on the VSRail platform. Includes hardware specs, ISO mappings, and boot-recovery parameters.
- ▌ Browser T3 Scenarios · bojak83318Use this skill when implementing, extending, or validating the T3 end-to-end browser scenarios in `/home/rocm/clawcontrol/browser`, especially the shared scenario runner in `browser/src/end_to_end.py`, the fake-data T3 suite in `browser/tests/test_end_to_end_scenarios.py`, and related evidence, routing, PageAgent, or anti-bot scenario work.
- ▌ Proxima Verification · bojak83318Re-run OWASP-based security verification for Proxima-Secure-Remediated versus Zen4-bit/Proxima after repo revisions. Use when Codex needs to compare the current remediated repo to upstream, reconstruct or refresh Proxima findings, update a PRD or verification report in Research/, or produce diff-backed evidence with minimal context so the work can be done reliably on gpt-5.4-mini.
- ▌ Arc Pro B70 Extraction · bojak83318 bundleUse this skill to extract data from Level1Techs forum threads and maintain agentic primitives in the level1techs-forums repository.
- ▌ Windows 11 Ralph Retry · bojak83318Use this skill when recovering a VSRail Windows 11 VM that fails to boot the installer ISO correctly, especially when `win11-vsrail` shows `0xc000000d`, BCD-style boot errors, stale UEFI behavior, helper-ISO boot confusion, or a suspect Windows installer ISO. It enforces three ordered Ralph loops, uses a 10-minute action plus 5-minute research cadence, and stops after one hour unless the user resets the task.
- ▌ Openclaw Qwen3 K3s Runbook · bojak83318Use this skill when running or recovering OpenClaw Qwen3-30B-A3B MoE training on a k3s node with Unsloth, especially for shard-load OOM, disk pressure, containerd bloat, PVC placement, or stalled startup behavior.
- ▌ Re Prd · bojak83318Use this skill when the user wants rough technical notes, chats, proposals, or brainstorms transformed into a formal engineering PRD with Background, Requirements, Milestones, Acceptance Criteria, and Rollout or Exit Decision sections.