All SkillsGet Started Free
Ln 812 Optimization Researcher
Researches competitive benchmarks and generates optimization hypotheses for identified bottlenecks. Use after profiling.
MCP get_skill({ skillId: "ln-812-optimization-researcher-c75e205b" })Use this skill with your agent
Create a free account and connect via MCP
> **Paths:** File paths (`references/`, `../ln-*`) are relative to this skill directory.
# ln-812-optimization-researcher
**Type:** L3 Worker
**Category:** 8XX Optimization
Researches competitive benchmarks, industry standards, and solution approaches for bottlenecks identified by the profiler. Generates prioritized hypotheses for the executor.
---
## Overview
| Aspect | Details |
|--------|---------|
| **Input** | Performance map from profiler (real measurements: baseline metrics, per-step timing, bottleneck classification, optimization hints) |
| **Output** | Industry benchmarks, solution candidates, prioritized hypotheses (H1..H7) |
| **Pattern** | Research-first: competitors → industry → local codebase → solutions → hypotheses |
---
## Workflow
**Phases:** Competitive Analysis → Bottleneck-Specific Research → Local Codebase Check → Hypothesis Generation → Research Report
---
## Phase 1: Competitive Analysis
**MANDATORY READ:** Load `references/research_tool_fallback.md` for MCP tool priority chain.
### Goal
Establish what "good" looks like for this type of operation. Define target metric if user did not provide one.
### Research Queries
| Goal | Query Template | Tool |
|------|---------------|------|
| Industry benchmark | `"{domain} API response time benchmark {year}"` | WebSearch |
| Competitor performance | `"{competitor_type} {operation} latency"` | WebSearch |
| Standard expectations | `"acceptable response time for {operation_type}"` | WebSearch |
| Framework-specific guidance | `"{framework} {operation} performance best practices"` | Context7 / Ref |
### Output
| Field | Description |
|-------|-------------|
| industry_benchmark | Expected performance range for this operation type |
| competitor_approaches | How top systems solve this (2-3 examples) |#agile-workflow#code-review#performance#optimizationweb-search