kienbui1995/dispatching-parallel-agents
skills/dispatching-parallel-agents/SKILL.md
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
testing
Updated Apr 23, 2026
$ install --global
skillsauthnpx skillsauth add kienbui1995/magic-powers dispatching-parallel-agentsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 12:55 AM22.1s1 file scanned
SKILL.md
- name:
- dispatching-parallel-agents
- description:
- Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Dispatching Parallel Agents
Overview
Delegate tasks to specialized agents with isolated context. Each agent gets precisely crafted instructions — never your session history.
Core principle: One agent per independent problem domain. Let them work concurrently.
When to Use
Use when:
- 2+ independent tasks (different subsystems, different bugs)
- No shared state between tasks
- Each can be understood without context from others
Don't use when:
- Failures are related (fix one might fix others)
- Need to understand full system state
- Agents would interfere with each other (same files)
The Pattern
1. Identify Independent Domains
Group by what's broken:
- Domain A: Authentication flow
- Domain B: Data processing pipeline
- Domain C: UI rendering
Each domain is independent — fixing auth doesn't affect rendering.
2. Create Focused Agent Tasks
Each agent gets:
- Specific problem — one domain only
- Relevant files — only what they need
- Expected outcome — what "fixed" looks like
- Constraints — don't touch other domains
3. Dispatch with Model Routing
| Task Type | Agent | Why | |-----------|-------|-----| | Bug investigation | debugger (Sonnet) | Systematic debugging, full tools | | Code review | reviewer (Haiku) | Fast, cheap, read-only | | Architecture question | architect (Opus) | Deep reasoning | | Implementation | (default subagent) | Sonnet, balanced |
4. Collect and Integrate Results
After all agents complete:
- Review each agent's changes
- Check for conflicts
- Run full test suite
- Use magic-powers:verification-before-completion
Anti-Patterns
| Pattern | Problem | |---------|---------| | Dumping full session context | Agents get confused, waste tokens | | Overlapping file scope | Merge conflicts | | Too many agents at once | Hard to coordinate | | Not reviewing results | Agents can make mistakes |
Integration
- magic-powers:subagent-driven-development — sequential task execution with review
- magic-powers:systematic-debugging — each agent uses this for bug investigation
Related Skills
kienbui1995/xr-interface-design
content-media
VerifiedTrustedCommunity
Use when designing for XR (AR/VR/MR), choosing interaction modes, or adapting 2D UI patterns for spatial computing
SKILL.mdUpdated Apr 24, 2026
kienbui1995/writing-skills
testing
VerifiedTrustedCommunity
Use when creating new skills, editing existing skills, or verifying skills work before deployment
SKILL.mdUpdated Apr 24, 2026
kienbui1995/writing-plans
development
VerifiedTrustedCommunity
Use when you have a spec or requirements for a multi-step task, before touching code
SKILL.mdUpdated Apr 24, 2026
kienbui1995/workflow-templates
development
VerifiedTrustedCommunity
Use when executing a structured workflow — select and run a feature, bugfix, refactor, research, or incident template with correct agent and model assignments per phase.
SKILL.mdUpdated Apr 24, 2026