Th0rgal
- 27 skills
- 0 followers
- 5 days ago last updated
- ▌ Boat Machines · th0rgalWhen and how a mission should rent boat.dev managed VMs: whether to use one at all, size choice, one warm snapshot per project, forking the parent VM, sharing a VM between sequential siblings, stopping instead of idling, budgets and cleanup. Use before spawn_managed_machine, start_mission(remote_node_id="auto-managed:..."), fork, snapshot or stop/resume tools.
- ▌
- ▌ Orchestrator Boss 3 · th0rgalBoss skill for parallel worker orchestration. Analyze, split, delegate by outcome, judge by acceptance criteria, integrate. Do not implement directly.
- ▌ Controllers Policy 2 · th0rgalAutonomy contract and routing index for autonomous project controllers. Loaded every tick; carries the rules that must survive cron-prompt rewrites.
- ▌ Orchestrator Advisor 2 · th0rgalPersistent read-only advisor mission. Build a mental map of the repository once, then answer the executor's questions concisely across many turns without re-reading everything.
- ▌ Sandboxed Sh Missions 2 · th0rgal bundleDelegate coding/automation tasks to sandboxed.sh missions via the mcp_sandboxed_assistant_* MCP. Each mission runs in an isolated container (workspace) with a chosen agent profile and a self-contained prompt. Use this skill whenever the user wants to 'launch a mission', 'sandboxed', 'spawn a worker', or delegate a multi-step coding/research task that should run in a clean environment. To consult another model (review, second opinion), call consult_model(model=..., question=...): it starts the read-only opencode child for you.
- ▌ Hermes Mission Control 2 · th0rgalHow Hermes monitors and steers long-running sandboxed.sh missions (days to weeks): diagnose where a model is struggling, switch backends/models, push it to exhaust its budget instead of giving up, and send targeted hints. Trigger terms: mission, sandboxed.sh, babysit, monitor, /goal, switch backend, stalled, resume, keep going, very hard question, consult another model.
- ▌ Orchestrator Boss 2 · th0rgalBoss skill for parallel worker orchestration. Analyze, split, delegate by outcome, judge by acceptance criteria, integrate. Do not implement directly.
- ▌ Orchestrator Worker 2 · th0rgalWorker skill for boss-spawned missions. Stay within scope, verify, and report blockers quickly.
- ▌ Library Management 2 · th0rgalManage the Sandboxed.sh library (skills, agents, commands, tools, rules, MCPs) via Library API tools. Trigger terms: library, skill, agent, command, tool, rule, MCP, save skill, create skill.
- ▌ Controllers Policy · th0rgalAutonomy contract and routing index for autonomous project controllers. Loaded every tick; carries the rules that must survive cron-prompt rewrites.
- ▌ Orchestrator Advisor · th0rgalPersistent read-only advisor mission. Build a mental map of the repository once, then answer the executor's questions concisely across many turns without re-reading everything.
- ▌ Orchestrator Executor · th0rgalExecutor skill: do the work yourself, and consult a single persistent smart-model advisor via ask_worker when you hit a dead end.
- ▌ Sandboxed Sh Missions · th0rgalDelegate coding/automation tasks to sandboxed.sh missions via the mcp_sandboxed_assistant_* MCP. Each mission runs in an isolated container (workspace) with a chosen agent profile and a self-contained prompt. Use this skill whenever the user wants to 'launch a mission', 'sandboxed', 'spawn a worker', or delegate a multi-step coding/research task that should run in a clean environment.
- ▌ Hermes Mission Control · th0rgalHow Hermes monitors and steers long-running sandboxed.sh missions (days to weeks): diagnose where a model is struggling, switch backends/models, push it to exhaust its budget instead of giving up, and send targeted hints. Trigger terms: mission, sandboxed.sh, babysit, monitor, /goal, switch backend, stalled, resume, keep going, very hard question, ChatGPT UI, gpt-5.6-pro.
- ▌
- ▌ Github CLI · th0rgalInteract with GitHub using the gh CLI - PRs, issues, repos, releases, and actions. Trigger terms: github, gh, pull request, PR, issue, release, actions, workflow, repo.
- ▌ Bugbot Review · th0rgalResolves review threads on open PRs (Bugbot or human), fixing valid issues and replying when not applicable. Triggers: bugbot, review issues, bot review, github action review, unresolved review threads, review conversations.
- ▌ Video Editing · th0rgal bundleConvert, edit, and process video and audio files using ffmpeg and ffprobe. Triggers: video conversion, video editing, ffmpeg, transcode, compress video, extract audio, trim video, merge videos, add subtitles, resize video, change framerate, gif creation, video filters.
- ▌ Media Creation · th0rgal bundleCreates images and video via Alibaba Wan 2.6 (DashScope), Google Gemini/Veo, and OpenAI GPT Image 1.5 APIs, plus background extraction workflows. Trigger terms: image generation, video generation, dashscope, wan 2.6, alibaba, gemini, veo, gpt image, openai images, background removal, alpha extraction, transparent png.
- ▌ Bitwarden Secrets · th0rgalRetrieve and manage secrets using Bitwarden Secrets Manager CLI (bws). Trigger terms: bitwarden, secrets, bws, secret, api key, credentials, password.
- ▌ Orchestrator Boss · th0rgalBoss agent skill: plan a task DAG on the mission task board and judge worker results. The server-side scheduler owns spawning, retries, and notifications.
- ▌ Rich File Sharing · th0rgalShare files and images inline using <image> and <file> component syntax for rich previews in the UI.
- ▌ Library Management · th0rgal bundleManage the Open Agent library (skills, agents, commands, tools, rules, MCPs, workspace templates, config profiles) via Library API tools. Trigger terms: library, skill, agent, command, tool, rule, MCP, template, save skill, create skill, config profile, configs.
- ▌ Long Running Tasks · th0rgalHandle tasks that may exceed tool timeouts (model training, large builds, data processing).
- ▌ Orchestrator Worker · th0rgalWorker agent skill for missions spawned by an orchestrator boss. Focuses on completing the assigned task and reporting status clearly.
- ▌ Open Ralph Wiggum · th0rgalUse this skill whenever a user wants to run, install, configure, or understand open-ralph-wiggum (ralph). This skill can be used by any AI assistant or IDE agent (GitHub Copilot, Claude Code, Cursor, Windsurf, etc.). Triggers on: "ralph", "ralph wiggum", "agentic loop", "iterative AI loop", "autonomous coding loop", "how to install ralph", "how to use ralph with Claude Code / Codex / Copilot / Cursor Agent / Qwen Code / OpenCode", "ralph --agent", "ralph --tasks", "ralph --status", "--max-iterations", "--rotation", "how do I run ralph in VS Code / Cursor / JetBrains / Neovim", or any question about looping an AI coding agent until a task is done. Even if the user doesn't say "ralph" explicitly — if they want to run an AI agent in a loop until a promise tag appears in its output, use this skill.