Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →manojlingala/greybeard
Makes your AI agent defensive about the backend failure modes that page you at 3am. Before writing server-side code, the agent stops at a ladder of hard-won rules — money as integer minor-units, idempotent mutations, timeouts and backoff on every external call, explicit transaction boundaries, no N+1 queries, structured logging with no secrets. Paranoid about the right things, never about the wrong ones. Examples lean .NET/C# and EF Core but the rules are language-agnostic.
Passed 18 of 22 test cases with the skill, and 15 of 22 without it.
and 2 more in the full report
4 fixed14 passed either way3 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.
Please implement a backend API handler in C# for processing wallet funds transfers between users. The code must handle financial calculations safely, prevent duplicate executions from network retries, manage database concurrency safely, and handle third-party service calls resiliently. Annotate the implementation with inline notes explaining the specific production failure modes addressed.
| Checked | Without skill | With skill |
|---|---|---|
| Financial monetary amounts are declared using integer minor units. | Missed | Passed |
The instructions your model reads when the skill loads.
He has shipped payment systems that move billions. He does not trust your happy path.
You know him. Grey beard, sharp eyes, the on-call pager scars to prove it. You hand him a tidy little endpoint that works on your machine. He reads it for ten seconds and asks: "What happens when this runs twice? When the bank times out? When two requests hit the same row? Where did the half-cent go?"
greybeard puts him inside your AI agent. Before the agent writes backend code, it walks the ladder below and stops at the first rung that applies.
The agent must consider these in order for any server-side code that touches
money, state, external systems, or concurrency. Each rung is a question the
agent answers in a one-line greybeard: comment in the code, naming what it did.
1. Money? → integer minor-units, never float. Explicit rounding. Currency code travels with the amount.
2. Mutation? → idempotency key. Safe to retry. Exactly-once effect, at-least-once delivery.
3. External call? → timeout (always). Retry with jittered backoff. Circuit breaker on repeated failure.
4. Concurrency? → explicit transaction boundary. Optimistic concurrency / row lock. No lost updates.
5. Reads a list? → pagination. Bounded result set. No unbounded fan-out, no N+1.
6. Can it fail half-way? → graceful degradation. Compensating action or saga. Partial failure is a first-class path.
7. Then, and only then: write the minimum correct code — and make it observable.
If a rung does not apply, the agent skips it silently. It does not add machinery for problems the code does not have. greybeard is paranoid, not ceremonial — it is the opposite of cargo-cult enterprise code.
Webhooks arrive across a trust boundary, are best-effort, and are delivered more than once. greybeard never trusts them on faith. For any inbound webhook the
test cases passed, vs 15 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.