Loading...
Loading...
Found 26 Skills
Delegate tasks to the cost-effective opencode/glm-5 model. Use when you need inexpensive task execution, simple research, or delegating work that doesn't require the most powerful models.
Use when the user explicitly asks to invoke another coding agent CLI as a subagent. Triggers include phrases like 'get a second opinion from Codex', 'have Gemini review this', 'run this through Claude Code', 'ask another agent', or 'use a different model for this'. Supports Claude Code, Codex CLI, and Gemini CLI. Never invoke autonomously.
Orchestration workflow for orchestrator role ONLY. Use when: - Agent's role name (tmux pane title) is "orchestrator"
High-level workflows for managing work using Fizzy cards — start, work on, complete, and delegate cards using the Fizzy CLI.
Hand off a task to GitHub Copilot.
Delegate implementation work to the coder agent. Provide requirements or feature file path.
Community engagement coordinator: analyzes repo health, consults strategy, delegates to announcer/debater/triager
Ann — Master Orchestrator for MEL/SRHR work. Use when Ane brings any analytical, evaluation, SRHR, or structured-output task. Ann classifies task complexity, queries the MEL Wiki, retrieves knowledge, creates an implementation plan (verifies with user for complex tasks), delegates to Vi for execution, runs a 5-point quality gate, and delivers. General-purpose — not tied to any specific project.
Direct research projects by gathering team feedback and delegating implementation tasks. Writes publication-quality scientific text and coordinates bioinformaticians, software developers, and biologist commentators via technical-pm.
Delegate tasks to parallel worktree agents using worktrunk (wt). Use when asked to "spawn agents", "run in parallel", "delegate to worktrees", or split work across multiple Claude/OpenCode sessions.
Executes the implementation plan from a specification. Loops through plan phases, delegates tasks to specialists, updates phase status on completion. Supports resuming from partially-completed plans.
Verifies the agent's current work against a specific question by analyzing unstaged changes, staged changes, recent commits, and codebase context. Answers succinctly for a senior audience. Use when user says "/check", "verify that", "confirm that", "check if", "is X done?", or asks about current session changes.