Welcome to Unit 4 of Skills — Extending Claude's Capabilities! Throughout this course, we explored the Skills system's fundamentals, created practical Skills from scratch, and mastered advanced design patterns. Now for the final piece: designing Skills that work together.

In this lesson, we will work through a realistic scenario: analyzing sales_data.csv, generating publication-quality charts, and producing a professional PDF report. Along the way, you will discover how to design Skills with compatible inputs and outputs, avoid conflicts when multiple Skills might apply, and know when workflows need advanced techniques.

Let's explore the power of multi-skill workflows!

In previous lessons, we saw individual Skills solve focused problems: extracting PDF tables, generating visualizations, or creating API tests. Real-world tasks, however, often require multiple specialized capabilities working together:

• Analyze data, then visualize results, then generate a report.
• Read documentation, extract patterns, then generate code following those patterns.
• Test an API, analyze failures, then suggest fixes.

When tackling complex workflows, you might use multiple Skills. Each Skill handles its specialized part. The key is designing Skills that complement each other - producing outputs compatible with what other Skills expect as inputs.

Let's work through a realistic business scenario where we:

1. Analyze trends in sales_data.csv.
2. Create publication-quality visualizations.
3. Generate a professional PDF report with findings.

This workflow spans multiple domains: data analysis, visualization, and document generation. Let's see how different capabilities work together.

We make our request:

Phase 1: Data Analysis

Claude starts by analyzing the data using general capabilities (we're assuming the csv-analyzer skill from Unit 2 doesn't exist in this scenario - though it could certainly be used if available):

Basic data analysis can be handled with general knowledge, but a dedicated skill like the csv-analyzer from Unit 2 would provide more structured, consistent analysis.

Phase 2: Visualization

For publication-quality charts, Claude automatically selects the sci-viz skill:

The skill ensures charts follow publication standards: 300 DPI resolution, colorblind-safe palettes, proper labels, vector formats. Here's the chart code it produces:

Notice the publication standards: high resolution, proper sizing, clear labels, both raster and vector formats.

Phase 3: PDF Report

Finally, Claude generates the report using general knowledge:

Claude matches your request to skill descriptions. When you said "create publication-quality charts," this matched the sci-viz skill's description: "Create publication-ready matplotlib visualizations."

Design tip: Use specific keywords in descriptions that match how people naturally phrase requests.

If your request could match multiple skills, Claude uses the description to determine the best match. To avoid conflicts:

• Make each skill's description unique.
• Use specific keywords for each domain.
• Define clear boundaries between skills.
• Test your skills together to verify they work well.

We can improve this workflow by creating a dedicated pdf-report skill:

Notice how these skills work well together:

• sci-viz creates 300 DPI images
• pdf-report expects 300 DPI images

This isn't accidental - it's good design! When creating related skills, think about:

• What outputs does one skill produce?
• What inputs does another skill need?
• Are there shared standards (like resolution)?

Design skills to be compatible, and complex workflows become possible.

For very complex workflows, the Task tool (covered in the Advanced Features course) can:

• Launch subagents with separate context windows
• Work in parallel on different parts
• Handle tasks that would overflow main context

Example use cases:

• Analyzing 50+ files simultaneously
• Complex code refactoring across entire codebase
• Generating extensive documentation

For this course, focus on skills for most workflows. Subagents are an advanced technique for exceptional cases.

Skills not activating when expected:

• Review skill descriptions; are they specific enough?
• Check "When to Use" bullets; do they match how you phrase requests?
• Verify the skill file is in .claude/skills/ and properly formatted.

Wrong skill activating:

• Look for description overlaps between skills.
• Make descriptions more distinct using unique terminology.

Skills producing incompatible output:

• Ensure shared standards (like image resolution) are consistent.
• Document expected input/output formats in each skill.
• Test skills together, not just individually.

Workflow stalling between phases:

• Check that each skill produces outputs the next phase expects.
• Verify tool permissions (allowed-tools) include what is needed.
• Ensure intermediate results are written to files or clearly summarized.

In this lesson, we explored multi-skill workflows and how to design Skills that work well together. We worked through a realistic workflow: analyzing sales data, creating publication-quality visualizations with the sci-viz skill, and generating professional PDF reports.

The key insight: Well-designed Skills naturally complement each other by sharing standards and producing compatible artifacts. Publication-quality charts (300 DPI) from sci-viz work perfectly in reports expecting high-resolution images. This compatibility emerges from thoughtful skill design.

You now understand the complete Skills system: from creating individual Skills, through advanced patterns, to designing coordinated Skills for sophisticated workflows. The practice exercises ahead will challenge you to design complementary Skills, debug workflow issues, and make strategic decisions about skill boundaries. Let's apply everything you have learned!