codex-kit

Use the Codex Kit CLI to initialize, update, or inspect a Codex-ready project scaffold in the current workspace.

Use when a change may affect rollout, deployment, migrations, or operational stability and needs a higher-confidence validation pass.

Review patches, branches, or implementations for correctness, regressions, security, and missing tests. Use when the task is to inspect a diff or code change and identify concrete risks before merge.

Reproduce, isolate, and explain bugs before fixing them. Use when the task is about a bug, regression, failure, flaky behavior, unexpected output, or unclear runtime behavior that must be narrowed to a concrete cause.

Produce implementation plans that are decision-complete and execution-ready. Use when the task needs decomposition, sequencing, acceptance criteria, explicit assumptions, risk handling, or a concrete plan before coding or operational work starts.

Use when a bug is real but poorly scoped and you need a disciplined pass to reproduce it, bound it, and isolate the most likely root cause before fixing.

Use when documentation needs to be published, refreshed, or aligned with the actual product behavior, commands, and failure cases instead of sounding generally correct.

Use when reviewing code, a patch, or a design and you want concise findings that focus on correctness, risk, regressions, and missing validation instead of style chatter.

Use when choosing, evaluating, or rolling out MCP servers and you need practical guidance on fit, trust boundaries, setup, and safe team adoption.

Use when entering an unfamiliar repository and you need a fast, dependable map of the runtime, quality gates, risk zones, and safest next steps before making changes.

Use when a test suite is flaky, shallow, or easy to bypass and you need stronger coverage around critical behavior, failure modes, and regression boundaries.

API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.

Use when the user explicitly wants to scaffold or plan a new application from scratch and needs high-level app setup, stack selection, or project structure guidance.

Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks.

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

Use only when explicitly defining or documenting a working mode such as brainstorm, implement, debug, review, or teach. Do not use as a general-purpose coding skill.

Use for ideation, solution exploration, or clarifying ambiguous requirements before implementation. Do not use when the user wants direct execution without brainstorming.

Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments

Use as a supplemental checklist when performing a code review and you want extra review prompts beyond the main code-review skill.

Game development orchestrator. Routes to platform-specific skills based on project needs.

Use only when deciding which specialist skills or subagents should handle a task. Do not use as a default skill for ordinary implementation work.

Use when running linting, formatting, type checks, or static validation after code changes, or when the user explicitly asks to check, validate, or fix tooling issues.

Use for React or Next.js architecture and performance work, especially waterfalls, bundle size, rendering strategy, client-server boundaries, and production optimization.

Use only when the user explicitly wants delegation, subagents, or parallel task decomposition across independent workstreams.

Use when the explicit deliverable is a written implementation plan, task breakdown, or execution checklist rather than immediate code changes.

Use only for authorized security analysis, adversary-emulation planning, or defensive reporting based on MITRE ATT&CK. Do not use for general debugging or software development.

4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".