Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/deepagents-code-review
Reviews Deep Agents code for bugs, anti-patterns, and improvements.
Passed 19 of 22 test cases with the skill, and 16 of 22 without it.
and 4 more in the full report
4 fixed15 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am writing a custom middleware component and a system prompt for my Deep Agents project. Look over my code to ensure it aligns with framework best practices. Your output must be a JSON object containing an 'errors' array and a 'corrected_snippet' string.
| Checked | Without skill | With skill |
|---|---|---|
| Specifies returning a new object or ModelRequest | Missed | Passed |
| States that the middleware should implement the transform_request method | Missed | Passed |
The instructions your model reads when the skill loads.
When reviewing Deep Agents code, check for these categories of issues.
# BAD - interrupt_on without checkpointer
agent = create_deep_agent(
tools=[send_email],
interrupt_on={"send_email": True},
# No checkpointer! Interrupts will fail
)
# GOOD - checkpointer required for interrupts
from langgraph.checkpoint.memory import InMemorySaver
agent = create_deep_agent(
tools=[send_email],
interrupt_on={"send_email": True},
checkpointer=InMemorySaver(),
)
# BAD - StoreBackend without store
from deepagents.backends import StoreBackend
agent = create_deep_agent(
backend=lambda rt: StoreBackend(rt),
# No store! Will raise ValueError at runtime
)
# GOOD - provide store
from langgraph.store.memory import InMemoryStore
test cases passed, vs 16 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.