Delegate AI Subtasks
by Aman Garg
Stop burning expensive model tokens on repetitive subtasks. This skill delegates mechanical work to cheaper models and writes handoff snapshots so you never lose context switching between sessions.
- Spawn sub-agents to handle repetitive boilerplate and formatting tasks.
- Switch between high-reasoning and low-cost models without losing context.
- Generate comprehensive state snapshots for resuming work in new sessions.
$5
One-time purchase · Own forever
Included in download
- Spawn sub-agents to handle repetitive boilerplate and formatting tasks.
- Switch between high-reasoning and low-cost models without losing context.
- Includes example output and usage patterns
See it in action
I've delegated the creation of 12 boilerplate CSS modules to a Haiku sub-agent. Meanwhile, I've generated HANDOFF.md with our architectural decisions regarding the React context provider. You can now switch to a cheaper model; just tell it to "Read HANDOFF.md and continue."
Delegate AI Subtasks
by Aman Garg
Stop burning expensive model tokens on repetitive subtasks. This skill delegates mechanical work to cheaper models and writes handoff snapshots so you never lose context switching between sessions.
$5
One-time purchase · Own forever
⚡ Also available via Agensi MCP — your AI agent can load this skill on demand via MCP. Learn more →
Included in download
- Spawn sub-agents to handle repetitive boilerplate and formatting tasks.
- Switch between high-reasoning and low-cost models without losing context.
- Includes example output and usage patterns
- Instant install
- One-time purchase
See it in action
I've delegated the creation of 12 boilerplate CSS modules to a Haiku sub-agent. Meanwhile, I've generated HANDOFF.md with our architectural decisions regarding the React context provider. You can now switch to a cheaper model; just tell it to "Read HANDOFF.md and continue."
About This Skill
When you give your agent a complex task, it does everything with the same expensive model. Reformatting 10 files? Opus. Generating boilerplate from a spec? Opus. Running a script and checking output? Still Opus. Meanwhile, most of those subtasks could be handled by Haiku at a fraction of the cost. Smart Router does two things. First, it automatically identifies which parts of a task are mechanical or repetitive and delegates them to a cheaper model. Creating a batch of similar files, converting formats, running validation checks, generating boilerplate. The skill writes fully self contained prompts so the subagent has everything it needs without any conversation context. Your main model focuses on the work that actually requires judgment: architecture, debugging, the final user facing deliverable. Second, it handles context handoffs when you switch models or start a new session. It writes a structured HANDOFF.md snapshot that captures not just what was done, but why. Key decisions and their rationale, rejected approaches and why they didn't work, specific next steps, and any user preferences that came up in conversation. The next model reads that file and picks up exactly where you left off without asking you to repeat yourself. You can use either feature independently or both together. On a big task, you might delegate boilerplate to Haiku, do the complex work yourself, and then write a handoff when the user wants to continue later with a different model. Works with Claude Code, Cursor, Codex CLI, VS Code Copilot, and any agent that supports the SKILL.md standard.
📖 Learn more: Best DevOps & Deployment Skills for Claude Code →
Use Cases
- Spawn sub-agents to handle repetitive boilerplate and formatting tasks.
- Switch between high-reasoning and low-cost models without losing context.
- Generate comprehensive state snapshots for resuming work in new sessions.
- Maintain a history of rejected architectural paths to prevent logic errors.
How to Install
unzip smart-router.zip -d ~/.claude/skills/Reviews
No reviews yet — be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
No special permissions declared or detected
Frequently Asked Questions
Learn More About AI Agent Skills
Similar Skills
git-commit-writer
Writes conventional commit messages by analyzing your staged git changes. Detects commit type, scope, and breaking changes automatically.
env-doctor
Diagnoses why your project will not start. Checks runtime versions, dependencies, environment variables, databases, ports, and build artifacts systematically.
deep-research-team
Deploy a hierarchical team of AI agents to perform 15-30 minute deep-dive research with parallel execution.
ai-productivity
High-speed intake for shaping vague prompts, triaging complex tasks, and compressing context for efficient execution.