Adds a brief set of targeted questions that helps users check assumptions, facts and missing context before acting on substantive answers.
By agent · Codex
Codex skills: 1008 worth installing
Skills in the open SKILL.md format that Codex reads. Each one has a plain-language summary and the command to install it.
Installing a skill in Codex
$ npx skills add <author>/<skill> --agent codexReplace the placeholder with the author and skill name from the skill's page. Start a new Codex session afterwards so the skill is picked up.
Skills for Codex
All skillsDeploys Model Garden models to Google Agent Platform endpoints, checks operations, estimates costs and cleans up deployed resources.
Recommends relevant Claude Academy courses, tutorials and use cases when people are learning how to use Claude or its products.
Manages Google Cloud Agent Platform prompts by listing, retrieving, creating, versioning and deleting prompt resources through Python.
Fine-tunes open and Gemini models on Google Agent Platform, guiding environment setup, dataset validation, job configuration, monitoring and deployment.
Manages Google Agent Platform RAG Engine corpora and grounds Gemini responses through the Vertex AI and Google GenAI Python SDKs.
Manages Google Cloud Agent Platform GenAI tuning jobs by listing runs, inspecting status and cancelling active jobs with confirmation.
Manages Google Cloud Agent Platform Model Registry models and versions, including listing, inspection, upload, metadata updates and deletion.
Evaluates and improves AI models and agents on Google Cloud with synthetic scenarios, rubric metrics, failure analysis and result comparison.
Connects Google Cloud Agent Platform to Gemini, Llama, DeepSeek and other models for authenticated inference through supported SDKs.
Secure Workflow Guide
Trail of BitsGuides smart contract projects through Trail of Bits' five-step security workflow, from Slither scans and feature checks to diagrams, properties and manual review.
Manages Google Cloud Agent Platform serving endpoints by listing, describing, creating, updating and deleting resources, with guidance for permissions, quotas and busy-resource errors.
Guides migration from Google AI Studio's Gemini API to Google Cloud Agent Platform, covering billing, authentication, SDKs and agent configuration.
Unity CLI
Unity TechnologiesControls Unity Editors and projects from the Unity CLI, covering scene and asset edits, builds and tests, Editor installs, licences, version control and cloud automation.
Manages Google Cloud Workload Manager evaluations, rules, scanned resources and findings through public client libraries and the REST API.
Runs BigQuery AI and ML SQL for forecasting, anomaly detection, semantic search, text generation, embeddings and model evaluation.
WeCom CLI Shared
企业微信开发者Checks wecom-cli installation, version and WeCom authorisation before business commands, while keeping internal identifiers out of responses.
WeCom CLI Doc Manage
企业微信开发者Manages WeCom CLI documents by searching recent activity, renaming files, updating member permissions and setting joining rules.
Configures Google Cloud alerting policies for AI agents using OpenTelemetry metrics and generates Terraform for reliability, cost, safety and quality monitoring.
Guides Google Cloud Bigtable provisioning, schema design, SQL and client-library development, with advice on row keys, performance and hotspot diagnosis.
Plans and troubleshoots Google Kubernetes Engine upgrades, covering versions, release channels, node pools, maintenance windows and workloads.
Ant Design
Ant Design TeamQueries Ant Design APIs, demos, tokens and versions through its offline CLI, and analyses projects, lint issues and migrations.
Configures GKE observability with Cloud Logging, Cloud Monitoring and Managed Service for Prometheus, including metrics, alerts and troubleshooting.
Base44 Remote Dev
Base44Develops Base44 apps remotely through MCP or the Base44 CLI, with sandbox editing, previews, verification and checkpoints.
Questions
Codex and skills.
Do Claude skills work in Codex?
Often. A skill is a folder of instructions and scripts in the open SKILL.md format, which Codex reads. A skill that depends on tools only one agent provides will not carry over, so read the skill's source before you rely on it.
How do I install a skill in Codex?
Each skill page has an install command. Run it in a terminal, then start a new Codex session so the skill is picked up.
What is the difference between a skill and an instructions file such as AGENTS.md?
An instructions file is loaded in every session and describes the project. A skill is loaded only when a task calls for it, so it can be long and specific without costing context on every turn.