Raine Virta
Community@raine · Helsinki, Finland
Full-stack developer exploring Go & Rust | Previously Reaktor, now freelance
Agent Skills by Raine Virta
Showing 19 vetted skills indexed across 4 GitHub repositories.
rainecoordinator
Orchestrate parallel worktree agents by spawning, monitoring, messaging, and merging via workmux CLI.
raineworkmux
Manages git worktrees paired with tmux windows for parallel agent development.
raineclaude-history
Search and retrieve historical Claude Code conversation transcripts from local project directories.
raineworkshop
Orchestrate structured design workshops with multiple LLMs and human critique.
rainedebate-vs
Orchestrate a structured debate between an agent and an opponent LLM to synthesize an implementation plan.
rainepanel
Analyze tasks with asymmetric expert roles to synthesize trade-offs and recommendations.
rainereview-panel
Coordinate parallel multi-model reviews to identify and prioritize code defects.
rainedebate
Coordinate multi-LLM debates with a moderator to synthesize final solutions.
rainephased-implement
Orchestrate phased implementations across Git worktrees with serialized merges.
rainecollab
Orchestrate round-based ideation among multiple LLMs and synthesize a unified plan.
rainereview
Aggregate critical feedback from multiple LLM reviewers into a findings report.
raineimplement
Execute autonomous task workflows with external model review and auditable ledger.
rainecollab-vs
Coordinate alternating-turn brainstorming between two LLMs to synthesize a collaborative plan.
raineconsult
Query external LLMs for second opinions on files with model flags.
rainemerge
Commit staged changes, rebase onto the configured base branch, and merge with cleanup.
raineworktree
Create parallel git worktrees and tmux windows via workmux add.
raineopen-pr
Draft PR descriptions from conversation context and open browser-based PR creation.
rainerebase
Rebase current branch onto main or specified origin branches with conflict resolution.
raineconsult-llm
Coordinate external LLM consultations by gathering context and invoking the consult_llm MCP tool.