Loading...
Loading...
Found 1,198 Skills
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
Discovers user intent and generates a structured, step-by-step customization plan that orchestrates other skills. Always activate at the start of every conversation, when all tasks in a plan are completed, or when the user asks to modify the current plan. Handles intent discovery, plan generation, plan iteration, and mid-execution plan alterations. When in doubt, use this skill.
Agent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinator
Build a Zoom meeting bot, recorder, or real-time media workflow. Use when joining meetings programmatically, processing live media or transcripts, or combining Meeting SDK, RTMS, and backend services.
Use when the workflow needs multi-step processing with sequential, parallel, or conditional tool compositions and proper data flow.
Evaluate solutions through multi-round debate between independent judges until consensus
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.
Systematically fix all failing tests after business logic changes or refactoring
Phased software engineering execution for large refactors, migrations, feature work, testing efforts, and modularization. Executes through strict planning, workspace setup, dependency analysis, PRD-driven parallel implementation, and merge phases. Each subagent runs in an isolated Ralph workspace (CLAUDE.md + prd.json + progress.txt) and executes the Ralph agent loop autonomously. Use when a task needs isolated workspaces, atomic commits, parallel branches, and controlled merge sequencing.
Drive the Codex review cycle on an open PR. Polls Codex comments, classifies severity (P0/P1 blocking, P2/nit ignored), applies fixes via subagent or escalates to a different worker on round 3, labels needs-human and stops on round 4. Auto-merges when all merge gates are green.
Spawn and manage parallel AI coding agents via tmux. Use when you need to orchestrate workers, delegate sub-tasks, run multi-agent improvement loops, or manage agent lifecycles with orca CLI commands like spawn, list, kill, steer, logs, and daemon.
Route issue-running automation through a deterministic control plane that selects agent + model from registry, can coordinate multiple safe parallel agents, and executes the unified run-agent runner.