Запуск параллельных агентов
Раздаёт две и более независимые задачи параллельным агентам, когда у задач нет общего состояния и последовательных зависимостей.
Ставится на компьютере
С телефона скилл не поставить: Claude Code работает на Windows, macOS и Linux. Отправьте ссылку себе и откройте её на компьютере.
Способ установки
Откройте Терминал и вставьте команду:
curl -fsSL https:/ / claudeskills.ru/ install/ dispatching-parallel-agents | bashСкилл ляжет в папку ~/.claude/skills/dispatching-parallel-agents/. Если Claude Code уже открыт, а папки skills раньше не было, наберите в нём /reload-skills. Посмотреть скрипт
Карточка
dispatching-parallel-agents- obra
- на английском, задачу ставите по-русски
- SKILL.md
Похожие скиллы
- РазработкаРазработка через субагентов Claude
Для выполнения планов с независимыми задачами в текущей сессии
subagent-driven-development· obra - РазработкаGit worktrees: параллельные ветки
Для изоляции новой функции от основной работы или перед запуском реализации
using-git-worktrees· obra - РазработкаРеализация спеки командой агентов
Claude реализует всю спеку: тикеты идут параллельно в отдельных worktree и сливаются в одну ветку.
implement-spec· mattpocock - РазработкаПередача контекста агенту
Claude сжимает текущий диалог в документ, по которому новый агент продолжит работу.
handoff· mattpocock - РазработкаРетро сессии агента
Разбор прошедшей сессии Claude: что поменять в окружении, чтобы следующие запуски шли лучше.
retro· mattpocock - РазработкаКонтекстная инженерия для агентов
Коллекция навыков агентов для контекстной инженерии, мультиагентных систем и промышленных решений
context-engineering-collection· muratcankoylan
Статьи по теме
- Лучшие скиллы для Claude Code: топ-15 по скачиваниям с примерамиТоп-15 скиллов для Claude Code по скачиваниям за 90 дней: что делает каждый, пример запроса и команда установки. Код, тесты, ревью, планы.
- Что такое Claude Skills и зачем они нужныClaude Skills — модульные навыки для ИИ-ассистента Claude. Узнайте, что это, как установить, создать свой skill и использовать в Claude Code. Примеры и инструкции.
- Настройка скиллов Claude: как устроен SKILL.md и где хранить скиллыНастройка скиллов Claude: из чего состоит SKILL.md, куда класть папку, как написать description и проверить, что скилл срабатывает. CLAUDE.md — отдельно.
Текст инструкции · SKILL.md
Оригинал инструкции (англ.)
Это оригинал автора на английском. Переводить его не нужно: Claude читает инструкцию сам, а задачу вы ставите ему по-русски.
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"];
}
Use when:
- 3+ test files failing with different root causes
- Multiple subsystems broken independently
- Each problem can be understood without context from others
- No shared state between investigations
Don't use when:
- Failures are related (fix one might fix others)
- Need to understand full system state
- Agents would interfere with each other
The Pattern
1. Identify Independent Domains
Group failures by what's broken:
- File A tests: Tool approval flow
- File B tests: Batch completion behavior
- File C tests: Abort functionality
Each domain is independent - fixing tool approval doesn't affect abort tests.
2. Create Focused Agent Tasks
Each agent gets:
- Specific scope: One test file or subsystem
- Clear goal: Make these tests pass
- Constraints: Don't change other code
- Expected output: Summary of what you found and fixed
3. Dispatch in Parallel
Issue all three subagent dispatches in the same response — they run in parallel:
Subagent (general-purpose): "Fix agent-tool-abort.test.ts failures"
Subagent (general-purpose): "Fix batch-completion-behavior.test.ts failures"
Subagent (general-purpose): "Fix tool-approval-race-conditions.test.ts failures"
# All three run concurrently.
Multiple dispatch calls in one response = parallel execution. One per response = sequential.
4. Review and Integrate
When agents return:
- Read each summary
- Verify fixes don't conflict
- Run full test suite
- Integrate all changes
Agent Prompt Structure
Good agent prompts are:
- Focused - One clear problem domain
- Self-contained - All context needed to understand the problem
- Specific about output - What should the agent return?
Fix the 3 failing tests in src/agents/agent-tool-abort.test.ts:
1. "should abort tool with partial output capture" - expects 'interrupted at' in message
2. "should handle mixed completed and aborted tools" - fast tool aborted instead of completed
3. "should properly track pendingToolCount" - expects 3 results but gets 0
These are timing/race condition issues. Your task:
1. Read the test file and understand what each test verifies
2. Identify root cause - timing issues or actual bugs?
3. Fix by:
- Replacing arbitrary timeouts with event-based waiting
- Fixing bugs in abort implementation if found
- Adjusting test expectations if testing changed behavior
Do NOT just increase timeouts - find the real issue.
Return: Summary of what you found and what you fixed.
Common Mistakes
❌ Too broad: "Fix all the tests" - agent gets lost ✅ Specific: "Fix agent-tool-abort.test.ts" - focused scope
❌ No context: "Fix the race condition" - agent doesn't know where ✅ Context: Paste the error messages and test names
❌ No constraints: Agent might refactor everything ✅ Constraints: "Do NOT change production code" or "Fix tests only"
❌ Vague output: "Fix it" - you don't know what changed ✅ Specific: "Return summary of root cause and changes"
When NOT to Use
Related failures: Fixing one might fix others - investigate together first Need full context: Understanding requires seeing entire system Exploratory debugging: You don't know what's broken yet Shared state: Agents would interfere (editing same files, using same resources)
Real Example from Session
Scenario: 6 test failures across 3 files after major refactoring
Failures:
- agent-tool-abort.test.ts: 3 failures (timing issues)
- batch-completion-behavior.test.ts: 2 failures (tools not executing)
- tool-approval-race-conditions.test.ts: 1 failure (execution count = 0)
Decision: Independent domains - abort logic separate from batch completion separate from race conditions
Dispatch:
Agent 1 → Fix agent-tool-abort.test.ts
Agent 2 → Fix batch-completion-behavior.test.ts
Agent 3 → Fix tool-approval-race-conditions.test.ts
Results:
- Agent 1: Replaced timeouts with event-based waiting
- Agent 2: Fixed event structure bug (threadId in wrong place)
- Agent 3: Added wait for async tool execution to complete
Integration: All fixes independent, no conflicts, full suite green
Verification
After agents return:
- Review each summary - Understand what changed
- Check for conflicts - Did agents edit same code?
- Run full suite - Verify all fixes work together
- Spot check - Agents can make systematic errors