overview-exploration

Overview Exploration Skill

Quick project overview exploration executed directly without agent spawn.

When to Use

• At the start of ultrawork sessions (exploration phase)
• When project structure understanding is needed
• Context collection before targeted exploration

---

Execution Steps

Step 1: Detect Project Type

Check for language/framework config files:

Glob(pattern="package.json")      # Node.js/JS
Glob(pattern="go.mod")            # Go
Glob(pattern="requirements.txt")  # Python
Glob(pattern="Cargo.toml")        # Rust
Glob(pattern="pom.xml")           # Java/Maven

Read discovered files to understand dependencies and framework.

Step 2: Explore Directory Structure

# Top-level structure
Glob(pattern="*", path=".")

# Main source directories
Glob(pattern="src/*")
Glob(pattern="app/*")
Glob(pattern="lib/*")

Step 3: Identify Entry Points and Patterns

# Find entry points (language-specific)
Grep(pattern="export default|module.exports", type="ts")
Grep(pattern="def main|if __name__", type="py")
Grep(pattern="func main", type="go")

# Check for existing patterns
Grep(pattern="auth|login|session", output_mode="files_with_matches")

Step 4: Quantitative Data Collection

Beyond descriptive findings, collect measurable data that enables informed planning decisions.

Test file count:

# Count test files in project
find . -name "*.test.*" -o -name "*.spec.*" | wc -l

# Check for test configuration
ls jest.config* vitest.config* .bun* 2>/dev/null

Key interface signatures:

# Extract exported interfaces and types
grep -A3 "export.*interface\|export.*type\|export.*function" src/ --include="*.ts" -rn | head -20

File line counts for main source files:

# Line counts for relevant source files
wc -l src/**/*.ts 2>/dev/null | tail -5

Include these metrics in your exploration output under a "Quantitative Data" subsection (see Output Format below).

Step 5: Read Documentation