Define an implementation contract for Codex
Turn a feature request into scope, invariants, acceptance criteria, and concrete completion evidence.
Browse reusable instructions for your AI tools. Copy and customize a prompt, or download a skill for a supported agent.

Turn a feature request into scope, invariants, acceptance criteria, and concrete completion evidence.
Translate an issue report into a reproducible engineering task without inventing missing evidence.
Give Codex a bounded test failure with a behavior contract and limits on implementation changes.
Define a measurable performance question with workload, baseline, and comparison rules.
Describe CLI behavior across arguments, streams, exit codes, and machine-readable output.
Frame a review around concrete failure modes, invariants, and affected behavior.
Create a concise repository guide using supplied structure and verified development commands.
Create fixture requirements that isolate behavior and include meaningful boundary cases.
Ask Codex to trace error propagation, cleanup, and caller-visible behavior.
Build one user-visible feature slice while preserving repository conventions and existing work.
Restructure a bounded area while proving important observable behavior stays the same.
Test a real boundary's observable behavior without reproducing its internal implementation.
Find the interleaving that causes stale state, duplicate work, or lost updates.
Trace imports, entry points, and data dependencies for a scoped code change.
Find the first meaningful build error and separate environment issues from code defects.
Trace whether an operation enforces ownership or membership for the actual target object.
Create a release checklist tied to changed behavior, dependencies, and rollback evidence.
Map a repository for Codex before starting a substantial change.
Specify a coding task with repository context, acceptance criteria, and a verifiable finish line.
Review code changes for real bugs, edge cases, and actionable improvements.
Turn an ambitious project into a small, testable build plan.
Design tests around behavior, invariants, and plausible failures.
Investigate failures with evidence, ranked hypotheses, and a minimal regression-tested fix.
Check API contracts for consistent resources, ownership, validation, and failure behavior.
Try another platform, a broader search, or fewer filters.
Explore all resourcesResource formats: Prompts are ready to copy into a conversation. Skills install into the compatible agent shown on their page.
How it worksInclude the instructions, intended platforms, author, and license. Submissions are reviewed before publication.