From kitchen-sink
Triages plan complexity to avoid heavyweight execution for trivial changes
npx claudepluginhub oalders/kitchen-sink --plugin kitchen-sinkThis skill uses the workspace's default tool permissions.
**After planning but before execution, evaluate whether the implementation is trivial enough to execute directly rather than using heavyweight processes.**
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
After planning but before execution, evaluate whether the implementation is trivial enough to execute directly rather than using heavyweight processes.
Core principle: Match execution process to implementation complexity. Don't launch 33 subagents to add items to arrays.
Use this skill:
Always check complexity before heavyweight execution.
Ask these questions:
Trivial Implementation Indicators:
If 3+ indicators are TRUE -> This is trivial
For Trivial Implementation:
Plan complete. Checking execution complexity...
Changes required:
- [List specific changes from plan]
This is trivial implementation (adding items to lists/updating data).
I'll implement directly rather than using subagent-driven development.
This will:
- Save time (10 min vs hours)
- Use fewer credits (1 agent vs 33)
- Produce the same quality result
Proceeding with direct implementation.
For Complex Implementation:
Plan complete. Checking execution complexity...
Changes required:
- [List specific changes from plan]
This is complex implementation requiring:
- New business logic / algorithms
- Multi-file coordination
- Database migrations / API changes
I'll use subagent-driven development for:
- Fresh context per task
- Thorough review cycles
- Quality verification
Proceeding with subagent-driven development.
Trivial -> Direct implementation:
Complex -> Heavyweight process:
Plan says:
Triage:
Decision: TRIVIAL -> Implement directly
Avoided: 33 subagent invocations (11 implementers + 11 spec reviewers + 11 code reviewers)
Plan says:
Triage:
Decision: COMPLEX -> Use subagent-driven development
Plan says:
Triage:
Decision: TRIVIAL -> Implement directly (simple bug fix)
Never:
Always:
Trivial implementation executed with heavyweight process:
Complex implementation executed directly:
Match the process to the task.
You're using this skill correctly when:
Always Trivial:
Always Complex:
Context-Dependent:
After superpowers:writing-plans:
-> Run over-engineer-no-more
-> Then either direct implementation OR superpowers:subagent-driven-development
After superpowers:brainstorming:
-> If implementation is clear, run over-engineer-no-more
-> Then either direct implementation OR superpowers:writing-plans -> triage -> execution
User says "fix #123": -> Read issue, understand scope -> Run over-engineer-no-more -> Execute accordingly