Automated summary
Explains data flows, features, and code paths within a codebase by tracing entry points and providing visual ASCII diagrams and step-by-step breakdowns.
Strengths
- Produces clear ASCII diagrams for visualizing data flow.
- Provides detailed step-by-step explanations with file:line references.
- Covers multiple types of explanations (data flows, features, components, integrations).
- Traces complete end-to-end paths from entry to output.
Limitations
- ASCII diagrams can become complex for very large flows.
- Requires the agent to have read access to all relevant files.
- Explanations are only as accurate as the code and the agent's ability to parse it.
Use when you need a deep understanding of how a specific part of the system works, especially for onboarding or debugging.
Avoid for simple questions that can be answered with a quick overview, as the full breakdown may be overkill.
Security analysis
SafeThe skill only describes a process for analyzing and explaining codebases using standard development tools (Glob, Grep, Read, LSP). It does not instruct the AI to execute any code, modify files, access external services, or handle sensitive data. There are no destructive or exfiltrating actions.
No concerns found
How this analysis is madeExamples
How do forecasts get from Windguru to the frontend?How does the favorites system work?How does the spot data flow from JSON to API response?name: explain description: Explain data flows, features, and code paths in the varun.surf application with visual diagrams and step-by-step breakdowns
Explain Skill
Explain how data flows through the system, how features work, and trace code paths with clear visualizations and step-by-step breakdowns.
Instructions
When the user asks to explain something (a feature, data flow, or component), follow this process:
1. Identify What to Explain
Parse the user's request to determine:
- Data flow: How data moves from source to destination (e.g., "explain how forecasts get to the frontend")
- Feature: How a specific feature works end-to-end (e.g., "explain favorites system")
- Component: How a specific service or class works internally (e.g., "explain AggregatorService")
- Integration: How external APIs are integrated (e.g., "explain Windguru integration")
2. Gather Context
Use the following tools to understand the code:
Globto find relevant filesGrepto search for specific patterns, method calls, and referencesReadto examine source codeLSPfor finding definitions, references, and call hierarchies
3. Trace the Flow
For data flows and features, trace the complete path:
Entry Point → Processing Steps → Output
Identify:
- Entry points (API endpoints, scheduled tasks, user actions)
- Service layer processing
- Data transformations
- External API calls
- Caching layers
- Response formatting
4. Create Visual Diagrams
Use ASCII diagrams to visualize:
For data flows:
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Source │────▶│ Transform │────▶│ Destination │
└─────────────┘ └─────────────┘ └─────────────┘
For component interactions:
┌──────────────────┐
│ Controller │
└────────┬─────────┘
│
┌────────────┼────────────┐
▼ ▼ ▼
┌─────────┐ ┌─────────┐ ┌─────────┐
│Service A│ │Service B│ │Service C│
└─────────┘ └─────────┘ └─────────┘
For state transitions:
[State A] ──(action)──▶ [State B] ──(action)──▶ [State C]
5. Provide Step-by-Step Breakdown
Structure the explanation as:
- Overview: High-level summary (2-3 sentences)
- Entry Point: Where the flow begins
- Step-by-Step Flow: Each processing step with file:line references
- Key Code Snippets: Important code sections (keep concise)
- Data Transformations: How data shape changes
- External Dependencies: APIs, databases, caches involved
- Error Handling: How errors are managed
- Related Components: Other parts of the system that interact
6. Include Code References
Always include file paths with line numbers for easy navigation:
src/main/java/.../SpotsController.java:45- endpoint definitionsrc/main/java/.../AggregatorService.java:120- data aggregation
Output Format
# Explaining: [Topic]
## Overview
[2-3 sentence summary]
## Visual Diagram
[ASCII diagram showing the flow]
## Step-by-Step Flow
### 1. [Step Name]
**File**: `path/to/file.java:line`
[Description of what happens]
```java
// Key code snippet (if helpful)
2. [Next Step]
...
Data Transformations
| Stage | Data Shape | Example | |-------|------------|---------| | Input | Type | {...} | | Output| Type | {...} |
Key Files Involved
path/to/file1.java- [purpose]path/to/file2.java- [purpose]
Related Features
- [Feature 1]: [brief relation]
- [Feature 2]: [brief relation]
## Example Topics
Common explanations users might request:
### Data Flows
- "How do forecasts get from Windguru to the frontend?"
- "How are live conditions fetched and displayed?"
- "How does the caching system work?"
- "How does the spot data flow from JSON to API response?"
### Features
- "How does the favorites system work?"
- "How does country filtering work?"
- "How does the search functionality work?"
- "How does theme switching work?"
- "How does the kite size calculator work?"
### Components
- "How does AggregatorService orchestrate data fetching?"
- "How do the FetchCurrentConditionsStrategy implementations work?"
- "How does the ForecastService parse Windguru data?"
- "How does the frontend manage state?"
### Integrations
- "How is Windguru integrated?"
- "How is Google Maps integration working?"
- "How does the AI analysis feature work?"
## Notes
- Keep explanations concise but complete
- Use diagrams to make complex flows understandable
- Always include file:line references for code navigation
- Focus on the specific topic, don't over-explain tangential concerns
- If the topic is ambiguous, ask clarifying questions
- Reference CLAUDE.md, docs/BACKEND.md, and docs/FRONTEND.md for architectural context
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/explain-data-flows-and-code-paths-mmh8qrjl/download' --output '.skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl/SKILL.md.part' && mv '.skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl/SKILL.md.part' '.skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl/SKILL.md' && test -s '.skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/explain' && cp -R '.skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl' '.claude/skills/explain'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl'openskills read 'explain-data-flows-and-code-paths-mmh8qrjl'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/explain-data-flows-and-code-paths-mmh8qrjl/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.