flash: Skill for Claude Code

Flash Framework Explorer Skill

When to Use

Use this skill when:

• Exploring the runpod-flash framework codebase
• Understanding class hierarchies and relationships
• Finding where methods or classes are defined
• Checking what decorators are used in the codebase
• Getting a quick overview of file structure

Workflow

Step 1: Query the Code Intelligence Database FIRST

Before reading any files, use the MCP code intelligence tools:

Finding a symbol:

• Use find_symbol tool with the symbol name

Understanding a class:

• Use get_class_interface tool with the class name

Exploring a file:

• Use list_file_symbols tool with the file path

Finding decorated functions:

• Use find_by_decorator tool (e.g., decorator="remote")

Listing all classes:

• Use list_classes tool

Step 1.5: NEVER Use Bash Commands for MCP Tool Tasks

PROHIBITED patterns - use MCP tools instead:

❌ DO NOT use tail, grep, or cat for test output analysis ✅ DO use parse_test_output MCP tool after running tests

❌ DO NOT use grep or find to search for symbols/classes/methods ✅ DO use find_symbol, list_classes, or find_by_decorator MCP tools

❌ DO NOT use Read tool to scan files for class definitions or interfaces ✅ DO use get_class_interface or list_file_symbols MCP tools

Step 2: Only Read Full Files When Necessary

After querying the code intelligence database, only use the Read tool if:

• You need to understand the implementation details
• The database doesn't have the specific information you need
• You need to see the full context around a symbol

Analyzing Test Results

After running tests (make test-unit, make test, pytest), ALWAYS use parse_test_output MCP tool to analyze results:

Good - Use MCP tool (~200 tokens):

1. Run: make test-unit
2. Pass output to parse_test_output MCP tool
3. Get structured failures, coverage, passed tests, summary
4. No manual parsing needed

Bad - Using bash commands (~20,000+ tokens):

1. Run: make test-unit > output.txt
2. Use tail, cat, or grep on output file
3. Manually parse failures and coverage
4. Excessive token usage, poor context extraction