benchmarking-analyst

Benchmarking study skill for internal, competitive, and best-in-class performance comparison

509 stars

Best use case

benchmarking-analyst is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Benchmarking study skill for internal, competitive, and best-in-class performance comparison

Teams using benchmarking-analyst should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/benchmarking-analyst/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/domains/business/operations/skills/benchmarking-analyst/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/benchmarking-analyst/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How benchmarking-analyst Compares

Feature / Agentbenchmarking-analystStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Benchmarking study skill for internal, competitive, and best-in-class performance comparison

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Benchmarking Analyst

## Overview

The Benchmarking Analyst skill provides comprehensive capabilities for conducting benchmarking studies. It supports internal, competitive, and best-in-class benchmarking, KPI normalization, best practice identification, and adaptation planning.

## Capabilities

- Benchmark partner identification
- KPI selection and normalization
- Data collection methodology
- Performance gap analysis
- Best practice identification
- Adaptation planning
- Progress tracking
- Benchmarking database maintenance

## Used By Processes

- CI-003: Benchmarking Program
- CI-001: Operational Excellence Program Design
- QMS-002: TQM Program Development

## Tools and Libraries

- APQC benchmarking database
- Industry consortiums
- Survey tools
- Data analysis platforms

## Usage

```yaml
skill: benchmarking-analyst
inputs:
  benchmarking_type: "best_in_class"  # internal | competitive | functional | best_in_class
  focus_area: "Order fulfillment cycle time"
  current_performance:
    metric: "order_to_ship_days"
    value: 5
  benchmark_sources:
    - type: "industry_database"
      source: "APQC"
    - type: "consortium"
      source: "Supply Chain Council"
  target_percentile: 90  # aim for top 10%
outputs:
  - benchmark_study
  - performance_gaps
  - best_practices
  - adaptation_plan
  - implementation_roadmap
  - tracking_metrics
```

## Benchmarking Types

| Type | Description | Use Case |
|------|-------------|----------|
| Internal | Compare across own sites/units | Identify internal best practices |
| Competitive | Compare to direct competitors | Understand competitive position |
| Functional | Compare to same function in other industries | Learn from leaders |
| Best-in-Class | Compare to world leaders | Achieve breakthrough performance |

## Benchmarking Process

### Phase 1: Planning
1. Identify what to benchmark
2. Form benchmarking team
3. Identify benchmark partners
4. Determine data collection method

### Phase 2: Analysis
1. Collect performance data
2. Determine performance gaps
3. Identify enablers of superior performance
4. Project future performance

### Phase 3: Integration
1. Communicate findings
2. Establish improvement goals
3. Develop action plans
4. Gain commitment

### Phase 4: Action
1. Implement plans
2. Monitor progress
3. Recalibrate benchmarks
4. Achieve maturity

## KPI Normalization

Normalize metrics for fair comparison:
- Per employee
- Per revenue dollar
- Per unit produced
- Per square foot
- Percent of total

### Example
```
Raw metric: Inventory value = $10M
Normalized: Days of inventory = 45 days
Industry benchmark: 30 days
Gap: 15 days (50% improvement opportunity)
```

## Performance Gap Analysis

| Performance Level | % of Benchmark | Action |
|-------------------|----------------|--------|
| Leading | >110% | Share best practices |
| Parity | 90-110% | Monitor and improve |
| Lagging | 70-90% | Targeted improvement |
| Poor | <70% | Major initiative needed |

## Best Practice Categories

1. **Process Design** - How work flows
2. **Technology** - Tools and systems used
3. **Organization** - Structure and roles
4. **People** - Skills and culture
5. **Metrics** - What is measured

## Integration Points

- Industry databases (APQC, Gartner)
- Consortium networks
- Performance management systems
- Knowledge management platforms

Related Skills

gpu-benchmarking

509
from a5c-ai/babysitter

Expert skill for automated GPU performance benchmarking and regression detection. Design micro-benchmarks, measure kernel execution time with CUDA events, calculate achieved vs theoretical performance, generate comparison reports, detect regressions in CI/CD, and profile power/thermal characteristics.

comp-benchmarking

509
from a5c-ai/babysitter

Analyze market compensation data and establish competitive pay structures

process-builder

509
from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509
from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)

yolo

509
from a5c-ai/babysitter

Run Babysitter autonomously with minimal manual interruption.

user-install

509
from a5c-ai/babysitter

Install the user-level Babysitter Codex setup.

team-install

509
from a5c-ai/babysitter

Install the team-pinned Babysitter Codex workspace setup.

retrospect

509
from a5c-ai/babysitter

Summarize or retrospect on a completed Babysitter run.

resume

509
from a5c-ai/babysitter

Resume an existing Babysitter run from Codex.

project-install

509
from a5c-ai/babysitter

Install the Babysitter Codex workspace integration into the current project.

plan

509
from a5c-ai/babysitter

Plan a Babysitter workflow without executing the run.

observe

509
from a5c-ai/babysitter

Observe, inspect, or monitor a Babysitter run.