Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/agent
Imported skill agent from langchain
Passed 21 of 22 test cases with the skill, and 12 of 22 without it.
and 6 more in the full report
9 fixed12 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
What specific SQLite database filename is referenced by absolute path when constructing the database connection?
| Checked | Without skill | With skill |
|---|---|---|
| Joins base_dir with chinook.db. | Missed | Passed |
The instructions your model reads when the skill loads.
import os import sys import argparse from dotenv import load_dotenv from langchain_community.utilities import SQLDatabase from langchain_community.agent_toolkits import SQLDatabaseToolkit from deepagents import create_deep_agent from deepagents.backends import FilesystemBackend from langchain_anthropic import ChatAnthropic from rich.console import Console from rich.panel import Panel
load_dotenv()
console = Console()
def create_sql_deep_agent(): """Create and return a text-to-SQL Deep Agent"""
# Get base directory
base_dir = os.path.dirname(os.path.abspath(__file__))
# Connect to Chinook database
db_path = os.path.join(base_dir, "chinook.db")
db = SQLDatabase.from_uri(
f"sqlite:///{db_path}",
sample_rows_in_table_info=3
)
# Initialize Claude Sonnet 4.5 for toolkit initialization
model = ChatAnthropic(
model="claude-sonnet-4-5-20250929",
temperature=0
)
# Create SQL toolkit and get tools
toolkit = SQLDatabaseToolkit(db=db, llm=model)
sql_tools = toolkit.get_tools()
test cases passed, vs 12 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.