OpenParable
Skip to content
← Back to skills

Parse

Testing & Quality
parse

Parse is an Agent Skill for testing & quality published in the LalitMaganti/syntaqlite repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Parse SQL and inspect the AST using syntaqlite. Use when the user wants to see the parse tree, debug SQL syntax, or understand how a query is structured.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/LalitMaganti/syntaqlite/blob/HEAD/integrations/claude-code/skills/parse/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/parse, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Parse SQL

Parse SQLite SQL and display the abstract syntax tree (AST) using the syntaqlite CLI.

Usage

# Print AST from a file
syntaqlite parse query.sql

# Print AST from stdin
echo "SELECT 1 + 2 FROM t" | syntaqlite parse

# Parse an inline expression
syntaqlite parse -e "SELECT 1"

# Output as JSON
syntaqlite parse -o json query.sql

Options

  • -e, --expression <SQL> — parse an inline SQL expression instead of files
  • -o, --output <FORMAT> — output format (default: text)

Output modes

  • text — Human-readable indented AST tree (default)
  • json — Machine-readable JSON AST

Notes

  • Use the default text output for quick inspection and json for programmatic use.