Skip to content
cccskills

OpenAI

@openai

Official · CodexOrganization

467 skills22 repositories 360.3K

Skills (467)

Refine in search

ios-debugger-agent

Official · CodexFreeSummary

Build and run iOS apps in Simulator using XcodeBuildMCP, then inspect screens, interact with controls, and capture logs to investigate runtime problems. It also supports launching an already built app and checking that the expected app opened.

  • Build and launch an iOS app in Simulator
  • Inspect screens and test taps or text entry
  • Capture logs to investigate runtime problems
openai/plugins7.5KUpdated Oct 8, 2026

geospatial-and-cartographic-visualization

Official · CodexFreeSummary

Decide whether geographic data needs a map, then choose suitable background maps, visual forms, and implementation tools. Plan overlapping markers, zoom behavior, and mobile interactions so the map supports the intended analysis or product task.

  • Deciding whether regional comparisons need a map
  • Designing regional maps with meaningful color scales
  • Planning overlapping markers and zoom behavior
openai/plugins7.5KUpdated Oct 8, 2026

view-refactor

Official · CodexFreeSummary

Refactor large macOS SwiftUI views into focused files and components. Clarify window state, selection, commands, and AppKit integration while preserving existing behavior and keeping the main layout stable as users change selections.

  • Split oversized SwiftUI views
  • Organize state for each window
  • Extract toolbar and command logic
openai/plugins7.5KUpdated Oct 8, 2026

react-best-practices

Official · CodexFreeSummary

Apply Vercel Engineering’s performance guidelines when writing, reviewing, or refactoring React and Next.js code. Prioritize improvements to data fetching, downloaded code size, server processing, and unnecessary rendering using rules with explanations and code examples.

  • Review React components for performance issues
  • Improve data fetching in Next.js pages
  • Reduce downloaded code and loading time
openai/plugins7.5KUpdated Oct 8, 2026

boltz-small-molecule-design

Official · CodexFreeSummary

Generate new small molecules intended to bind a target protein with Boltz. The workflow covers cost estimation, job submission, result downloads, and ranking candidates by binding confidence or a score for improving promising molecules.

  • Generate binding candidates without an existing compound library
  • Rank generated molecules by binding confidence
  • Review solubility and permeability of promising candidates
openai/plugins7.5KUpdated Oct 8, 2026

boltz-small-molecule-adme

Official · CodexFreeSummary

Estimate small molecule solubility, permeability, and lipophilicity with Boltz using SMILES, a text notation for molecular structures. Process individual molecules or lists, review costs before submission, and receive results mapped to each input.

  • Estimate properties for a molecule from its SMILES
  • Evaluate a molecule list from a CSV file
  • Compare predicted properties during initial screening
openai/plugins7.5KUpdated Oct 8, 2026

frontend-app-builder

Official · CodexFreeSummary

Create websites, dashboards, games, and app interfaces from image-generated design concepts. The skill turns the accepted concept into reusable UI components, implements working controls, and checks browser rendering, interactions, and responsive layouts against the design.

  • Build a new website from visual concepts
  • Create a dashboard or management interface
  • Redesign the appearance of an existing site
openai/plugins7.5KUpdated Oct 8, 2026

build-run-debug

Official · CodexFreeSummary

Set up a repeatable build, launch, and debugging workflow for macOS apps using Xcode or SwiftPM, Swift’s package manager. A project script handles relaunching, connects to the Codex Run button, and supports logs and process checks.

  • Build and launch a macOS app with one script
  • Connect a project to the Codex Run button
  • Investigate build errors or startup failures
openai/plugins7.5KUpdated Oct 8, 2026

shadcn

Official · CodexFreeSummary

Build and maintain interfaces with shadcn/ui components, reusable pieces such as forms, cards, and dialogs. Find suitable components, follow project settings, fix composition and styling issues, and review updates while preserving local changes.

  • Build settings pages and dashboards
  • Fix form and dialog composition
  • Update components while preserving local changes
openai/plugins7.5KUpdated Oct 8, 2026

supabase-postgres-best-practices

Official · CodexFreeSummary

Write, review, and optimize Postgres queries, database structures, and configuration using guidance maintained by Supabase. Prioritized rules and SQL examples help assess query speed, connections, indexes, and row-level security, which controls access to individual rows.

  • Review slow SQL queries
  • Assess table structures and indexes
  • Review connection pooling and scaling settings
openai/plugins7.5KUpdated Oct 8, 2026

liquid-glass

Official · CodexFreeSummary

Implement and review Liquid Glass interfaces in macOS SwiftUI apps. The skill prioritizes standard layouts and controls, removes backgrounds that obscure system materials, and guides custom glass surfaces, toolbar grouping, search placement, and transitions.

  • Adopting Liquid Glass in an existing macOS app
  • Reviewing custom toolbar and sidebar backgrounds
  • Implementing custom glass controls and transitions
openai/plugins7.5KUpdated Oct 8, 2026

final-release-review

Official · CodexFreeSummary

Review a JavaScript SDK release plan or final candidate against the previous release. Check compatibility, packaging, regressions, and Changesets version records, then recommend shipping or blocking with supporting evidence and a separate assessment of documentation coverage.

  • Review the next SDK release plan
  • Assess whether a final release candidate can ship
  • Check generated versions and changelogs for consistency
openai/openai-agents-js3.9KUpdated Oct 21, 2026

implementation-final-review

Official · CodexFreeSummary

Review completed implementation changes before final verification. Classify their impact, arrange independent review when required, resolve actionable findings, and preserve evidence that the final delivered content matches what was reviewed and passes the applicable verification checks.

  • Review the complete implementation diff before final verification
  • Choose review depth based on the impact of a change
  • Coordinate independent review and fixes
openai/openai-agents-js3.9KUpdated Oct 21, 2026

pr-draft-summary

Official · CodexFreeSummary

Turn the actual task changes into an English PR title, description, and branch name suggestion. Include relevant committed and uncommitted work, explain the motivation and behavior changes, and prepare text ready to paste into GitHub.

  • Preparing a PR draft after implementation
  • Explaining the motivation and behavior changes in English
  • Summarizing changes including untracked files
openai/openai-agents-js3.9KUpdated Oct 21, 2026

sensitive-logging-audit

Official · CodexFreeSummary

Audit JS SDK logs, exceptions, and telemetry for exposed model or tool inputs and outputs. It traces values to logging destinations, verifies suppression settings, fixes demonstrated leaks, and adds regression tests while preserving permitted operational diagnostics.

  • Auditing logs for model and tool payload exposure
  • Checking that data-suppression flags work
  • Fixing demonstrated leaks through error logging
openai/openai-agents-js3.9KUpdated Oct 21, 2026

changeset-validation

Official · CodexFreeSummary

Check package changes against changesets, the files describing release updates, to assess summaries and required version increases. Use it to review pull requests or uncommitted changes and obtain a structured verdict with errors, warnings, and the required bump.

  • Reviewing changeset compliance in a pull request
  • Checking release notes against uncommitted changes
  • Choosing the appropriate version bump
openai/openai-agents-js3.9KUpdated Oct 21, 2026

docs-sync

Official · CodexFreeSummary

Compare English SDK documentation with source code to find missing features, incorrect defaults, and outdated explanations. Produce evidence-backed findings or update the requested pages, with verification matched to the scope of the documentation changes.

  • Audit documentation for a specific SDK feature
  • Check documentation against branch changes
  • Correct outdated option names and defaults
openai/openai-agents-js3.9KUpdated Oct 21, 2026

maintainer-review

Official · CodexFreeSummary

Review GitHub issues and pull requests to assess demonstrated user need, existing alternatives, correctness, compatibility, and maintenance cost. Using static evidence, it develops a maintainer recommendation and compares competing proposals without running code or changing remote items.

  • Deciding whether an issue warrants maintainer action
  • Assessing whether a pull request is worth merging
  • Comparing competing pull requests for the same problem
openai/openai-agents-js3.9KUpdated Oct 21, 2026

implementation-kickoff

Official · CodexFreeSummary

Carry an agreed implementation through a separate Git working copy, focused checks, and final review. Receive a local branch with one commit and a PR draft, while preserving the original checkout and unrelated changes.

  • Implementing agreed changes in a separate working copy
  • Preparing a reviewed local branch with one commit
  • Taking over another author's pull request
openai/openai-agents-js3.9KUpdated Oct 21, 2026

test-coverage-improver

Official · CodexFreeSummary

Measure JS SDK test coverage and identify untested behavior using coverage reports. It supports gap assessments and scoped test improvements, prioritizing public behavior, error handling, cancellation, and lifecycle paths, then reporting verification results and remaining gaps.

  • Auditing current JS SDK test coverage
  • Investigating a decline in coverage metrics
  • Adding tests for uncovered public behavior
openai/openai-agents-js3.9KUpdated Oct 21, 2026

invoice-total-fixer

Official · CodexFreeSummary

Fix invoice total calculations in the sandbox quickstart repository by inspecting the implementation and tests, applying tax to the subtotal, and running the repository's tests to report the result.

  • Fixing an invoice total calculation
  • Checking how tax is applied to a subtotal
  • Running tests after a calculation fix
openai/openai-agents-js3.9KUpdated Oct 21, 2026

implementation-strategy

Official · CodexFreeSummary

Define the scope of SDK behavior changes, including required behavior, compatibility obligations, unsupported cases, and existing alternatives. Guide implementation toward existing code paths, and reassess the design when review feedback introduces repeated complexity or expands supported behavior.

  • Define the supported scope before changing SDK behavior
  • Assess compatibility with released APIs and saved data
  • Revisit a design as review findings accumulate
openai/openai-agents-js3.9KUpdated Oct 21, 2026

examples-run-analysis

Official · CodexFreeSummary

Analyze existing logs and source files from a completed example run to verify that intended actions actually occurred. Review every entry, classify failures and skips, and report evidence without running examples, controlling processes, or modifying files.

  • Verify behavior after a completed example run
  • Check whether exit-zero examples performed their intended actions
  • Separate repository failures from environment restrictions
openai/openai-agents-js3.9KUpdated Oct 21, 2026

openai-knowledge

Official · CodexFreeSummary

Look up OpenAI API and platform details in official documentation through the documentation MCP server. Retrieve relevant pages, endpoint definitions, and parameters so integration guidance and factual claims are grounded in the fetched source text.

  • Verify specifications before integrating an OpenAI API
  • Check endpoint parameters and definitions
  • Confirm documented defaults and limits
openai/openai-agents-js3.9KUpdated Oct 21, 2026

Is this your account? Link GitHub to bring it onto your creator page (Japanese)