Loading...
Loading...
Found 32 Skills
Use when you have specifications or requirements for multi-step tasks before touching code
Create, manage, and execute agent tools (claude, codex) inside Docker sandboxes for isolated code execution. Use when running agent loops, spawning tool subprocesses, or any task requiring process isolation. Triggers on "sandbox", "isolated execution", "docker sandbox", "safe agent execution", or when working on agent loop infrastructure.
Manage background coding agents in tmux sessions. Spawn Claude Code or other agents, check progress, get results.
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
Requirement planning to wave-based CSV execution pipeline. Decomposes requirement into dependency-sorted CSV tasks, computes execution waves, runs wave-by-wave via spawn_agents_on_csv with cross-wave context propagation.
Implement approved OpenSpec proposal using DAG-scheduled multi-agent parallel execution
Operate the external task-management CLI (tk) as source of truth for agent execution tracking. Invoke when any SPEC comes up for implementation, when the user asks to track tasks, check what to work on next, see task status, manage work dependencies, or close/abandon tasks. For coordination-tier artifacts (EPIC, VISION, JOURNEY), swain-design must decompose into child SPECs first — this skill tracks the children, not the container.
Create and run durable workflows with steps, streaming, and agent execution. Covers starting, resuming, and persisting workflow results.
Create install.md files optimized for AI agent execution. Use for ANY question about install.md files or request to create/review installation documentation for autonomous agent use.
Converts a Refound/Lenny Skill into a high-density, agent-executable Skill Pack (Agent Skills standard). Output must be in English.
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
Unified command interface for the autonomous idea intake workflow system