Automated summary
This skill describes how to split several independent failures across multiple Claude agents running concurrently, each confined to a narrow file scope, and then how to merge their results.
Strengths
- Lays out a clear four-step process: identify independent problem domains, write agent tasks, dispatch them simultaneously, then consolidate results.
- The agent prompt template enforces scope, goal, constraints, and expected output, which keeps agents from wandering outside their area.
- A pitfalls table (scope too broad, missing context, undefined constraints, vague deliverables) pairs each problem with a concrete fix.
- Includes a demonstrated run (6 failures across 3 agents, zero conflicts) to show the time savings in practice.
Limitations
- Assumes access to Claude Code's Task tool and does not explain how to adapt the pattern to other environments.
- Does not cover file conflicts or coordination when scopes overlap despite the stated constraints.
- The claimed ~3x speedup comes from a single demonstration and is not reproducible measurement.
Use it when you face three or more distinct failures in separate files or subsystems that can be investigated without shared state.
Avoid it when failures are interconnected or when an agent needs whole-system context to diagnose the problem correctly.
Security analysis
CautionThe skill instructs dispatching parallel agents via Task and allows Bash, which are powerful capabilities but used for a legitimate workflow of investigating and fixing independent failures. No destructive, exfiltration, or obfuscation patterns are present. Risk is primarily operational, stemming from concurrent code modifications if constraints are ignored.
- •Uses Task to dispatch multiple subagents capable of modifying code, which could lead to unintended changes if scope constraints are not strictly followed.
- •Declares Bash as an allowed tool, though the skill itself does not include explicit shell commands.
Examples
I have failing tests in auth.test.js (JWT validation), api.test.js (routing errors), and db.test.js (connection timeouts). These look unrelated. Dispatch parallel agents to investigate and fix each one in its own scope, then summarize the root cause, the fix, and the test result for each.Three independent modules fail to build: the payment service, the notification worker, and the file upload handler. Split them into separate agent tasks with restricted file scopes and run them concurrently, then report the merged results.We have separate bugs reported in src/auth/, src/api/, and src/db/. They don't share state. Create one agent task per area with a clear goal, allowed files, and constraints, dispatch them in parallel, and give me a consolidated report.name: dispatching-parallel-agents description: Use when facing 3+ independent failures that can be investigated without shared state or dependencies. Dispatches multiple Claude agents to investigate and fix independent problems concurrently. allowed-tools: Read, Glob, Grep, Task, Bash license: MIT metadata: author: obra/superpowers version: "1.0"
Dispatching Parallel Agents
여러 독립적인 문제를 병렬 에이전트로 동시에 해결하는 스킬입니다.
Core Principle
"Dispatch one agent per independent problem domain. Let them work concurrently."
When to Use
✅ 적합한 상황
- 3개 이상의 독립적 실패
- 각 문제가 서로 관련 없음
- 공유 상태 없이 조사 가능
- 서로 다른 파일/서브시스템에서 발생
❌ 피해야 할 상황
- 실패들이 연결되어 있음 (하나 해결 시 다른 것도 해결)
- 전체 시스템 컨텍스트가 필요
- 에이전트들이 공유 리소스에 간섭
Execution Pattern
1. 독립적 문제 도메인 식별
## 실패 분석
| 파일/영역 | 문제 | 독립성 |
|-----------|------|--------|
| auth.test.js | JWT 검증 실패 | ✅ 독립 |
| api.test.js | 라우팅 오류 | ✅ 독립 |
| db.test.js | 연결 타임아웃 | ✅ 독립 |
2. 에이전트 태스크 생성
## Agent 1: Auth Module
Scope: src/auth/, tests/auth/
Goal: JWT 검증 실패 원인 찾기
Constraint: auth 관련 파일만 수정
## Agent 2: API Routes
Scope: src/api/, tests/api/
Goal: 라우팅 오류 해결
Constraint: api 관련 파일만 수정
## Agent 3: Database
Scope: src/db/, tests/db/
Goal: 연결 타임아웃 해결
Constraint: db 관련 파일만 수정
3. 동시 디스패치
Task(Agent 1) || Task(Agent 2) || Task(Agent 3)
4. 결과 통합
## Results
### Agent 1 (Auth)
- 문제: 만료 시간 계산 오류
- 수정: auth/jwt.js:45
- 테스트: ✅ 통과
### Agent 2 (API)
- 문제: 미들웨어 순서
- 수정: api/routes.js:12
- 테스트: ✅ 통과
### Agent 3 (DB)
- 문제: 커넥션 풀 설정
- 수정: db/config.js:8
- 테스트: ✅ 통과
Agent Prompt Template
## Task
[구체적인 문제 설명]
## Scope
- 파일: [제한된 파일 목록]
- 관련 테스트: [테스트 파일]
## Goal
[명확한 목표]
## Constraints
- 다른 영역 코드 수정 금지
- 프로덕션 코드 최소 변경
- 테스트 통과 필수
## Expected Output
1. 근본 원인 분석
2. 수정 내용 요약
3. 테스트 결과
Common Pitfalls
| 문제 | 해결책 | |------|--------| | 범위가 너무 넓음 | 구체적인 파일/디렉토리 지정 | | 컨텍스트 누락 | 필요한 배경 정보 포함 | | 제약 미정의 | "~하지 마세요" 명시 | | 출력 불명확 | 정확한 deliverable 지정 |
Demonstrated Results
6개 실패, 3개 파일
→ 3개 병렬 에이전트
→ 동시 완료
→ 충돌 0건
→ 순차 대비 ~3배 속도
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/dispatching-parallel-agents-mmlj2oa2/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/dispatching-parallel-agents-mmlj2oa2' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/dispatching-parallel-agents-mmlj2oa2/download' --output '.skill-downloads/dispatching-parallel-agents-mmlj2oa2/SKILL.md.part' && mv '.skill-downloads/dispatching-parallel-agents-mmlj2oa2/SKILL.md.part' '.skill-downloads/dispatching-parallel-agents-mmlj2oa2/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Glob, Grep, Task, Bash
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/dispatching-parallel-agents-mmlj2oa2/SKILL.md' && test -s '.skill-downloads/dispatching-parallel-agents-mmlj2oa2/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/dispatching-parallel-agents' && cp -R '.skill-downloads/dispatching-parallel-agents-mmlj2oa2' '.claude/skills/dispatching-parallel-agents'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/dispatching-parallel-agents-mmlj2oa2'openskills read 'dispatching-parallel-agents-mmlj2oa2'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/dispatching-parallel-agents-mmlj2oa2/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.