Explore Prompts

Design a modularization plan: identify seams, extract modules, keep interfaces stable, and add integration tests. Require incremental steps and metrics.

Create a formatting agent that guarantees no semantic change: parse/print equivalence, tests, and diff classification. Include a strict policy for format-only PRs.

Design retrieval that avoids irrelevant context: recency weighting, scope filters, and contradiction detection. Include evals for context precision/recall.

Create review prompts that guide humans: “check invariants,” “check auth,” “check rollback.” Tune them based on escaped defects and reviewer feedback.

Design an agent to tune security headers and CSP safely: staged enforcement, report-only mode, breakage monitoring, and rollback. Require security team sign-off.

Create a plan to reduce logging costs: sampling, cardinality caps, and aggregation. Require proof that debugging capability is preserved via incident drills.

Design an agent that improves error handling: retries, timeouts, and clearer exception types. Require integration tests and telemetry validation post-deploy.

Create a workflow to propose UX copy changes, test via A/B, and ensure no dark patterns. Include an ethics checklist and rollback criteria.

Design a controlled translation system: glossary, style guide, human review, and back-translation checks. Integrate with MCP and require provenance logs.

Design an agent to improve alt-text and form labels, requiring neutral phrasing, avoiding sensitive inference, and validating with accessibility tests.

Create a plan for coding standards that includes auto-fixers (formatters) and a “fix-it PR” bot, with reviewer load controls and staged rollout.

Design a system to generate API docs from code annotations and schemas, but require verification via integration tests and manual spot checks.