Explore Prompts

Create a blueprint for self-editing CI/CD scripts safely: validate configs, run in sandbox, and require manual approval for permission changes.

Design an ADR generator that proposes ADRs for significant changes: context, decision, alternatives, consequences. Require human approval and link tests/metrics.

Create a doc search agent that indexes internal docs, code comments, and ADRs, then answers “why is this here?” with citations for maintainers.

Design an incremental modernization strategy (language/runtime upgrades) with compatibility tests, staged rollouts, and metrics. Include “stop if risk” criteria.

Create an agent that turns bug reports into minimal reproducible cases, adds regression tests, and proposes fixes. Include a triage rubric and severity mapping.

Design a process where the agent proposes new lint rules only with evidence of repeated issues. Include rollout plan, false-positive checks, and developer ergonomics.

Design an automated PR reviewer that adds checklists, risk annotations, and required evidence links (tests, benchmarks, docs). It must not auto-merge without gates.

Create a plan to deprecate APIs safely: warnings, dual-run, client update automation, and cutoff dates. Include dashboards to track migration progress.

Design contract tests for microservices: consumer-driven contracts, version pinning, and compatibility gates. Integrate with the self-edit loop for safe rollouts.

Create a property-based testing strategy for critical modules: define properties, generators, shrinking, and CI integration. Use failures to guide safer edits.

Design memory policies for the self-improver: store only non-sensitive, useful facts; avoid personal data; set retention windows. Include audit and deletion workflows.

Design a constrained codegen system: templates, typed interfaces, and lint rules that prevent unsafe patterns. Include a “reject list” of disallowed code constructs.