Writes and reviews technical blog posts to the standards and voice of the Sentry engineering blog.
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 skillsReviews pull requests the way Sentry engineers do, covering security, performance, testing and design.
Simplifies and refines code for clarity, consistency and maintainability while keeping its behaviour.
Creates Sentry-style conventional commits with issue references.
Reviews Django code for performance problems such as N+1 queries and slow querysets.
Finds bugs, security vulnerabilities and code quality issues in the changes on the current branch.
Reviews GitHub Actions workflows for vulnerabilities that could be exploited.
Iterates on a pull request until CI passes and high and medium review feedback has been addressed.
Writes or refreshes pull request titles and descriptions for reviewers.
Creates data-driven presentation slides with React, Vite and Recharts in Sentry branding.
Creates, optimises and refines agent prompts, system prompts and reusable prompt templates.
Reviews code for security vulnerabilities such as injection, XSS and authentication or authorisation flaws.
Scans agent skills for security problems such as prompt injection before you install them.
Creates and improves agent skills according to the Agent Skills specification.
Scaffolds a new Terraform provider with the Plugin Framework: workspace layout, Go module, provider server and schema.
Turns monolithic Terraform configurations into reusable modules that follow HashiCorp's module design principles.
Discovers existing cloud resources with Terraform Search queries and imports them into Terraform management in bulk.
Guides work with Terraform Stacks: creating, modifying and validating stack component and deployment configurations.
Generates Terraform HCL that follows HashiCorp's official style conventions.
Guides writing and running Terraform tests: test files, run blocks, assertions and mocked providers.
Plans and reviews MySQL and InnoDB schemas, indexing, query tuning, transactions and operations.
Explains Neki, PlanetScale's sharded Postgres product, for Postgres scaling and sharding work.
Covers PostgreSQL best practices: query optimisation, connection troubleshooting and performance.
Covers Vitess best practices: query optimisation, sharding, VSchema configuration and keyspace management.
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.