# Accelerate

> Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.

- **Type:** Skill
- **Install:** `agentstack add skill-sharpdeveye-maestro-accelerate`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [sharpdeveye](https://agentstack.voostack.com/s/sharpdeveye)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [sharpdeveye](https://github.com/sharpdeveye)
- **Source:** https://github.com/sharpdeveye/maestro/tree/main/source/skills/accelerate
- **Website:** https://maestroskills.dev

## Install

```sh
agentstack add skill-sharpdeveye-maestro-accelerate
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## MANDATORY PREPARATION

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first.
Consult the context-management reference in the agent-workflow skill for window optimization and budget strategies.

---

Make the workflow faster and cheaper without sacrificing quality. Measure before and after.

### Performance Audit

Measure current performance:

```text
Current metrics:
  Latency (p50): ___ms
  Latency (p95): ___ms
  Cost per request: $___
  Token usage (avg): ___ input / ___ output
  Error rate: ___%
```

### Acceleration Strategies

**Reduce Token Usage**

- Shorten system prompts (remove redundant instructions)
- Compress few-shot examples to minimum viable length
- Use structured output schemas instead of verbose text
- Summarize context instead of passing raw documents
- Reduce output length requirements

**Model Cascading**

- Route simple tasks to cheaper/faster models
- Escalate only complex tasks to capable models
- Use classification to determine complexity

**Caching**

- Cache responses for identical or near-identical inputs
- Cache tool results with appropriate TTL
- Cache embeddings for frequently-queried documents
- Use semantic caching for similar (not identical) queries

**Parallelization**

- Run independent tool calls in parallel
- Run independent agent steps in parallel
- Use streaming to start processing before full response

**Context Optimization**

- Retrieve less, retrieve better (improve retrieval precision)
- Use context compression techniques
- Implement sliding window for long conversations

### Acceleration Report

For each optimization:

1. **What changed**: Specific modification
2. **Before**: Latency/cost/tokens before
3. **After**: Latency/cost/tokens after
4. **Quality impact**: Any quality change (verify with golden tests)
5. **Trade-off**: What was sacrificed for the improvement

### Acceleration Checklist

- [ ] Baseline metrics recorded before any changes
- [ ] Each optimization measured with before/after comparison
- [ ] Quality impact verified (golden tests still pass)
- [ ] Trade-offs documented for each change
- [ ] Cost/latency improvements quantified

### Recommended Next Step

After optimization, run `/evaluate` to verify quality didn't degrade, or `/iterate` to set up continuous monitoring.

**NEVER**:

- Optimize without measuring first (you need a baseline)
- Sacrifice quality for speed without explicit user approval
- Cache outputs that depend on real-time data
- Skip the quality check after optimization
- Optimize prematurely (make it correct first, then make it fast)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [sharpdeveye](https://github.com/sharpdeveye)
- **Source:** [sharpdeveye/maestro](https://github.com/sharpdeveye/maestro)
- **License:** MIT
- **Homepage:** https://maestroskills.dev

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-sharpdeveye-maestro-accelerate
- Seller: https://agentstack.voostack.com/s/sharpdeveye
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.