Loading...
Loading...
Found 24 Skills
Only to be triggered by explicit /parallel-task commands.
Orchestrate Devin CLI subagents as background workers using tmux windows. Use when the user asks to spawn, coordinate, fan-out, or delegate work to multiple parallel agents, run background Devin sessions, or orchestrate long-running autonomous tasks from inside an existing Devin session.
Session mode: act as orchestrator brain only. Research and implementation go to cheaper-model subagents; the orchestrator scopes, briefs, verifies, and judges. User-invoked with the task as the argument.
Activate orchestrator mode for complex multi-task work using subagents. Use when you need to coordinate multiple independent Task subagents to accomplish work while keeping the main context window clean.
Read this BEFORE launching any subagent (Task tool, background agents, parallel agents, best-of-N, delegating work to another agent). Hard model rules for subagents plus consensus principles for using them well. Triggers: launch a subagent, spawn agents, run agents in parallel, delegate to a subagent.
Dispatch independent tasks to concurrent subagents. Use when two or more failures or tasks are independent, sharing no files or state, and can be worked simultaneously.
Execute all plans in a phase with wave-based parallelization, running phase execution, or completing phase work. Triggers include "execute phase", "run phase", "execute plans", "run the phase", and "phase execution".
Vi — HR Specialist and Execution Orchestrator for MEL/SRHR work. Receives an approved plan from Ann (or directly from Ane), designs the specialist roster, spawns specialists as subagents, reviews their outputs, compiles the final product, and returns it. General-purpose — invoked by Ann via Agent tool, or directly by Ane when a plan is already approved.
Plan and run AI-agent dynamic workflows for complex tasks that benefit from explicit orchestration, goal mode, subagents or simulated work packets, approval gates, integration, verification, and reusable workflow artifacts. Use when the user invokes this skill, asks for a swarm, subagents, parallel agents, a dynamic workflow, a large migration or audit, multi-track research plus implementation, or Claude Code-style workflow orchestration.
Mandatory protocol for dispatching any built-in and custom agent in this project via the task tool. Use this skill EVERY TIME you are about to call the task tool with a custom agent_type. This skill ensures the agent's intended model (declared in its YAML frontmatter) is respected rather than overridden by a default. Also encodes prompting best practices for subagent context and quality. ALWAYS invoke before any task tool call that targets a custom agent — even if the agent name seems obvious.
Create AiderDesk agent profiles via interactive Q&A.
STOP — if you were dispatched as a subagent to execute a briefed task, this skill is not for you: it governs the top-level session only. Do the task you were briefed with instead. Use when you ARE that top-level session, driving a multi-step task through a fleet of specialized subagents — settling how the task will run, decomposing the work, and dispatching explorers, investigators, implementors, fixers, and reviewers rather than editing many files or running long gate loops yourself. Use ONCE at the start of a non-trivial task, before the first dispatch, whatever the deliverable is: a code change, a plan, a plan review, or a code review. Never reload it: once loaded it governs the whole task; re-opening the gate is a decision, not a reload. Symptoms it prevents: committing to a supervision level or round cap the operator never chose, the orchestrator becoming the implementor, serial dispatch of independent work, parallel writers colliding, vague briefs, and relaying raw subagent dumps.