obsidian-hybrid-search: Skill for Claude Code

Dispatching Parallel Agents

Do not use for implementation plan tasks

This skill is for independent investigations: diagnosing unrelated test failures, read-only code investigation, documentation lookups, or analysis of independent subsystems , anything with no shared mutable state and no overlapping file changes. It is not for implementing tasks from one implementation plan in a shared working tree; running implementers in parallel there produces file conflicts. Use skill:subagent-driven-development for that , it dispatches one implementer at a time, with a review gate between tasks. Parallel implementation is only safe with per-task worktree isolation and a dedicated integration workflow, neither of which this skill provides.

Overview

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history , you construct exactly what they need. This also preserves your own context for coordination work.

When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

Core principle: Dispatch one agent per independent problem domain. Let them work concurrently.

When to Use

digraph when_to_use {
    "Multiple failures?" [shape=diamond];
    "Are they independent?" [shape=diamond];
    "Single agent investigates all" [shape=box];
    "One agent per problem domain" [shape=box];
    "Can they work in parallel?" [shape=diamond];
    "Sequential agents" [shape=box];
    "Parallel dispatch" [shape=box];

    "Multiple failures?" -> "Are they independent?" [label="yes"];
    "Are they independent?" -> "Single agent investigates all" [label="no - related"];
    "Are they independent?" -> "Can they work in parallel?" [label="yes"];
    "Can they work in parallel?" -> "Parallel dispatch" [label="yes"];
    "Can they work in parallel?" -> "Sequential agents" [label="no - shared state"];
}