Text promptClaude
Senior-engineer code review
A single Claude prompt that does a real code review — flags correctness bugs, hidden race conditions, and missing null-checks, and refuses to comment on style. Tuned over hundreds of real PRs.
How it works
Sealed — you'll run it and get the finished output. The source is never shown or downloaded.
Sealed text prompt
The source stays private. You provide the input, it runs on our servers, and you get the finished output — the prompt text itself is never shown or downloaded.
You receive: Plain text
Example outputs
What the prompt actually produces.
- Sample finding list
1. `apps/web/lib/auth.ts:42` — **correctness, high.** `getSession()` is called without `await` inside the catch block. The session check will silently no-op on error. Fix: `const s = await getSession();` 2. `apps/web/db/queries.ts:118` — **concurrency, medium.** The `inc(salesCount)` mutation runs inside a transaction that also reads the prompt for ratings. Two concurrent purchases will read pre-update values. Fix: wrap the read in `FOR UPDATE` or move the read out of the transaction. 3. `apps/web/components/PromptCard.tsx:34` — **data, low.** `prompt.ratingSum / prompt.ratingCount` divides without a zero-check; renders `NaN` for prompts with no reviews. Fix: `ratingCount > 0 ? ratingSum / ratingCount : null`.
Reviews
4.9(301)Buyers also picked
- Prompt chain
Release notes from a git diff
Two-step chain: extract the meaningful user-facing changes from a diff or PR summary, then write release notes in the voice you actually ship in. Drops refactors, dep bumps, and test-only churn.
ClaudeChatGPTGemini$9