All authors
Th0rgal avatar

Claude Skills by Th0rgal

github.com/Th0rgal
9 skillsA× 7F× 20 installs1 views
Open Ralph WiggumF

Use 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-ite...

developmentgoshell
0
1,733
Library ManagementA

Manage 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.

ai-agentstypescriptbash
0
493
Orchestrator BossA

Boss skill for parallel worker orchestration. Analyze, split, delegate, monitor, integrate. Do not implement directly.

ai-agentsrustgo
0
493
Orchestrator WorkerA

Worker skill for boss-spawned missions. Stay within scope, verify, and report blockers quickly.

ai-agents
0
493
Controllers PolicyA

Autonomy contract and routing index for autonomous project controllers. Loaded every tick; carries the rules that must survive cron-prompt rewrites.

ai-agentsgobash
0
493
Hermes Mission ControlA

How 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.

ai-agentsrustgo
0
493
Orchestrator AdvisorA

Persistent 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.

ai-agentsgit
0
493
Orchestrator ExecutorA

Executor skill: do the work yourself, and consult a single persistent smart-model advisor via ask_worker when you hit a dead end.

ai-agentsbackend
0
493
Sandboxed Sh MissionsF

Delegate 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.

ai-agentspythonrust
0
493