Skip to main content
skill CX Codex

gap-analysis — Claude Code skill: what it does, how to install

Compares your current state with the desired one and lists what is missing. Useful before big investments or a roadmap rewrite.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add aj-geddes/useful-ai-prompts --skill gap-analysis -a claude-code
Open on GitHub

What gap-analysis does

The skill works through the distance between where things stand and where you want them. It sorts the difference into categories: business capability, process, technology, skills, data, people and culture, organization, metrics. Each area gets a view of what has to change and what that change costs.

Inside there is a short Python example: a GapAnalysis class holding the category list and an identify_gaps method that matches future capabilities against current ones. The full implementation lives in four guides under references/: a gap identification framework, an analysis template, gap closure planning, and communication and tracking.

The skill advises comparing against a clearly defined future state and pulling stakeholders into the gap hunt. Planning every gap in parallel is a bad idea, because dependencies and resource limits pile up faster than expected. A vague future state turns the whole exercise into a wish list, so pin that down first.

What it helps with

  • compare current team capabilities against target ones
  • spot process gaps before automating anything
  • work out which skills are missing for a new project
  • sort gaps by category and priority
  • build a closure plan that respects dependencies

Example prompts for the agent

  • Run a gap analysis: here is our current state, here is the target — what do we need to close
  • Compare our stack with what the new architecture requires
  • Break the gaps into categories and propose a closure plan

How to install gap-analysis

1Skills CLI (Vercel)

npx skills add aj-geddes/useful-ai-prompts --skill gap-analysis -a claude-code

2Manually: put the files in place

~/.claude/skills/gap-analysis/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/gap-analysis/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about gap-analysis

How do I install gap-analysis in Claude?

Run npx skills add aj-geddes/useful-ai-prompts --skill gap-analysis -a claude-code. The skill lands in ~/.claude/skills/gap-analysis/SKILL.md.

What does gap-analysis do?

It compares the current state with the desired one and surfaces gaps in capabilities, processes, technology, skills, data and structure. You get a list of what to change plus a closure plan.

What files ship with the skill?

The main SKILL.md and four guides under references/: gap identification framework, analysis template, closure planning, and communication and tracking.

Source text

SKILL.md · MIT
---
name: gap-analysis
description: >
  Identify differences between current state and desired future state. Analyze
  gaps in capabilities, processes, skills, and technology to plan improvements
  and investments.
---

# Gap Analysis

## Table of Contents

- [Overview](#overview)
- [When to Use](#when-to-use)
- [Quick Start](#quick-start)
- [Reference Guides](#reference-guides)
- [Best Practices](#best-practices)

## Overview

Gap analysis systematically compares current capabilities with desired future state, revealing what needs to change and what investments are required.

## When to Use

- Strategic planning and goal setting
- Technology modernization assessment
- Process improvement initiatives
- Skills and training planning
- System evaluation and selection
- Organizational change planning
- Capability building programs

## Quick Start

Minimal working example:

```python
# Systematic gap identification

class GapAnalysis:
    GAP_CATEGORIES = {
        'Business Capability': 'Functions organization can perform',
        'Process': 'How work gets done',
        'Technology': 'Tools and systems available',
        'Skills': 'Knowledge and expertise',
        'Data': 'Information available',
        'People/Culture': 'Team composition and mindset',
        'Organization': 'Structure and roles',
        'Metrics': 'Ability to measure performance'
    }

    def identify_gaps(self, current_state, future_state):
        """Compare current vs desired and find gaps"""
        gaps = []

        for capability in future_state['capabilities']:
            current_capability = self.find_capability(
                capability['name'],
                current_state['capabilities']
            )

            if current_capability is None:
// ... (see reference guides for full implementation)
```

## Reference Guides

Detailed implementations in the `references/` directory:

| Guide | Contents |
|---|---|
| [Gap Identification Framework](references/gap-identification-framework.md) | Gap Identification Framework |
| [Gap Analysis Template](references/gap-analysis-template.md) | Gap Analysis Template |
| [Gap Closure Planning](references/gap-closure-planning.md) | Gap Closure Planning |
| [Communication & Tracking](references/communication-tracking.md) | Communication & Tracking |

## Best Practices

### ✅ DO

- Compare current to clearly defined future state
- Include all relevant capability areas
- Involve stakeholders in gap identification
- Prioritize by value and effort
- Create detailed closure plans
- Track progress to closure
- Document gap analysis findings
- Review and update analysis quarterly
- Link gaps to business strategy
- Communicate findings transparently

### ❌ DON'T

- Skip current state assessment
- Create vague future state
- Identify gaps without solutions
- Ignore implementation effort
- Plan all gaps in parallel
- Forget about dependencies
- Ignore resource constraints
- Hide difficult findings
- Plan for 100% effort allocation
- Forget about change management

© aj-geddes · MIT · aj-geddes/useful-ai-prompts

Similar skills

All skills for Notes, tasks and projects →

From the same set143

gcp-cloud-run Guides container deployments to Google Cloud Run with gcloud CLI and Terraform. Useful when releasing stateless HTTP backends. CX Codex +1 535installs Causal Inference A skill that walks your agent through causal effect estimation: propensity scores, instrumental variables, causal graphs. Useful when a randomized experiment isn't an option. CX Codex +1 534installs code-generation-template A skill for generating code from templates: project scaffolding, boilerplate, AST-based generation and template engines. Useful when you need to produce repetitive code fast. CX Codex +1 532installs grpc-service-development This skill walks your agent through gRPC service work: Protocol Buffers contracts, four call patterns, servers in Node.js and Python. CX Codex +1 527installs network-debugging Walks your agent through why requests fail, stall or crawl. Useful when the app is slow and the network is the suspect. CX Codex +1 526installs sql-injection-prevention Enforces parameterized queries, prepared statements, and input validation in database code. Useful when writing API endpoints or auditing legacy queries for security flaws. CX Codex +1 526installs payment-gateway-integration A skill for wiring Stripe, PayPal and Square into your backend: charges, subscriptions, webhooks. Useful when you build billing or a store. CX Codex +1 524installs Anomaly Detection Detect outliers, fraud, and system faults using statistical tests, isolation forests, and deep learning. Generates working Python analysis pipelines. CX Codex +1 523installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor