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.
Draft migration requirements covering mixed versions, existing data, rollback, and validation.
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.
Review a proposed schema change for data preservation and mixed-version application behavior.
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.
Inspect parsing, row validation, duplicate handling, and atomicity for an import workflow.
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.
Synthesize supplied material with traceable claims, disagreements, and limitations.
Find actionable accessibility issues in supplied markup, styles, and user flows.
Improve a prompt's goal, context, constraints, and output requirements.
Investigate failures with evidence, ranked hypotheses, and a minimal regression-tested fix.
Check API contracts for consistent resources, ownership, validation, and failure behavior.
Plan a migration with compatibility checks, verification, and a recovery path.
Write task-focused documentation grounded in the actual product and code.
Edit for clarity, structure, and voice while preserving supplied facts.
Inspect dataset structure, missingness, duplication, and validity before analysis.
Review SQL grain, joins, aggregation, and null handling with concrete examples.
Analyze a supplied CSV with explicit assumptions and reproducible summaries.
Translate a hypothesis into an interpretable test with metrics and guardrails.
Review an interface against user tasks, hierarchy, consistency, and state coverage.
Check whether a scoped change is ready to ship and what still needs verification.
Review a proposed design for concrete trust boundaries, abuse cases, and missing controls.
Review a page for usefulness, answer completeness, and clear search intent.
Turn scattered notes into a clear brief with scope, constraints, and acceptance criteria.
Extract decisions and action items without inventing owners or deadlines.
Draft clear customer support replies grounded in verified policy and case details.
Guide a learner through a concept using small hints, practice, and feedback.
Improve a résumé's relevance, clarity, and evidence without manufacturing accomplishments.
Go from a fuzzy idea to a practical build plan with milestones and clear acceptance criteria.
Investigate a reproducible bug with hypotheses, a minimal fix, and a focused regression check.
Get a focused review of correctness, maintainability, and edge cases, grounded in your code.
Map a product workflow into predictable endpoints, validation rules, and error responses.
Choose meaningful tests around a feature’s actual risks and expected behavior.
Build a useful map of a repository and identify where a specific change belongs.
Save a resource with its bookmark button. It stays in this browser.
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.