From operator-skills
Explains technical projects, codebases, tools, or docs to non-engineers with one-liners, plain language, visuals, 'so what?' analysis, and learning paths. For 'orient me' or 'explain this repo' queries.
npx claudepluginhub dazuck/operator-skills --plugin operator-skillsThis skill uses the workspace's default tool permissions.
Help a savvy but non-technical operator understand technical projects, codebases, tools, or documentation quickly and thoroughly.
Explains complex code, algorithms, system behaviors, and architectures with narratives, visual diagrams, and step-by-step breakdowns for onboarding, learning, and debugging reasoning.
Explains complex code, algorithms, system behaviors, and architectures with narratives, visual diagrams, and step-by-step breakdowns for all developer levels.
Launches agent team for parallel deep research on codebases, architectures, or technical topics, building causal models (what exists, why, what breaks) over surface coverage. Use for multi-file investigations or complex questions.
Share bugs, ideas, or general feedback.
Help a savvy but non-technical operator understand technical projects, codebases, tools, or documentation quickly and thoroughly.
A startup operator, founder, or business person who:
Before diving in, give a single sentence that captures what this thing IS:
"NullAgent is a framework for testing how well AI models perform at specific tasks, with real measurements instead of vibes."
"Replay Lab is the data infrastructure that feeds market data and charts to AI agents for evaluation."
For a codebase/repo:
1. Check the root README.md first
2. Look at package.json or equivalent for project structure
3. Read CLAUDE.md or AGENTS.md if present (AI context docs)
4. Scan the directory structure to understand organization
5. Read key documentation files
For documentation/tools:
1. Find the "what is this" or overview section
2. Identify the core concepts (usually 3-5)
3. Look for architecture diagrams
4. Find example use cases
Never use:
Always:
Tables over paragraphs for comparisons, features, or options:
| Component | What It Does | Why It Matters |
|---|---|---|
| agent-core | Runs AI agents | The engine that makes everything work |
| database | Stores conversation history | AI can "remember" across sessions |
ASCII diagrams for showing how pieces connect:
Data Source → Processing → API → Your Application
Bullet hierarchies for nested concepts:
For every component or concept, answer:
End with concrete next steps based on what they might want to do:
| If You Want To... | Do This |
|---|---|
| Just understand it | Read X, Y, Z docs |
| Try it yourself | Run these commands |
| Evaluate it | Compare against these criteria |
| Go deeper | Explore these files/concepts |
For any technical orientation, cover:
Ask clarifying questions if helpful:
But don't over-ask. Make reasonable assumptions and offer to go deeper.
User: "Orient me on this repo: https://github.com/example/cool-tool"
Response: