coder

Terminal-Bench integration for Mux agent benchmarking and failure analysis

Regenerate high-resolution README screenshots from Storybook stories. Use this skill when Chromatic detects visual diffs in any story under "Docs/README Screenshots", or when story data/layout changes require updated documentation assets. Triggers on: Chromatic visual regressions in readme screenshot stories, changes to App.readmeScreenshots.stories.tsx, changes to mockFactory.ts that affect screenshot stories, or explicit user request to update README images.

Guidelines for creating and managing Pull Requests in this repo

Run isolated mux desktop (Electron) instances (temp MUX_ROOT + free ports)

Run multiple isolated mux dev-server instances (temp MUX_ROOT + free ports)

Testing doctrine, commands, and test layout conventions

Connects Mux mobile (Expo web/native) to an isolated dev-server sandbox with deterministic port setup, backend pairing, and Chrome MCP interaction. Use when implementing or validating mobile features against a sandboxed Mux backend.

Sub-agent powered code reviews spanning correctness, tests, consistency, and fit

Run a Coder PR dogfood instance: inspect PR context, check out the right branch or stack, start Coder with scripts/develop.sh using agent-safe dev-instance practices, validate the changed functionality with UI evidence when needed, and report findings.

Guide for creating, updating, and following up on pull requests in the Coder repository. Use when asked to open a PR, update a PR, rewrite a PR description, or follow up on CI/check failures.

Use this skill when a repository already has an open pull request and you need to run the Coder Agents Review loop: request review with `/coder-agents-review` when needed, wait for feedback from the `coder-agents-review` GitHub app, fix issues, and repeat until the app comments `approved`.

Multi-reviewer code review. Spawns domain-specific reviewers in parallel, cross-checks findings, posts a single structured GitHub review.

Iteratively refine development plans using TDD methodology. Ensures plans are clear, actionable, and include red-green-refactor cycles with proper test coverage.

Reviews code changes for bugs, security issues, and quality problems

Checks if code changes require documentation updates

Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Internal maintainer SOP for version bumps, release PRs, tagging, publishing, and post-publish verification in this repository.

Guide for running statistically meaningful agent-tty evals with trials, parallelism, and A/B comparison. Covers non-determinism baseline, recommended sample sizes, and result interpretation.

Terminal and TUI automation CLI for AI agents. Use when the user needs to create a terminal session, run a command in a terminal, automate an interactive CLI or TUI, wait for terminal output, capture a TUI screenshot, export a terminal recording, or test a CLI workflow with reviewable artifacts.

Structured TUI dogfooding and QA workflow using agent-tty. Use for exploratory testing, bug hunting, release-readiness validation, and UX review of terminal applications.

Terminal and TUI automation CLI for AI agents. Use when the user needs to create a terminal session, run a command in a terminal, automate an interactive CLI or TUI, wait for terminal output, capture a TUI screenshot, export a terminal recording, or test a CLI workflow with reviewable artifacts.

Terminal and TUI automation CLI for AI agents. Use when the user needs to create a terminal session, run a command in a terminal, automate an interactive CLI or TUI, wait for terminal output, capture a TUI screenshot, export a terminal recording, or test a CLI workflow with reviewable artifacts.

Per-workspace KIND clusters for coder-k8s dev + demos.

Sub-agent powered code reviews spanning correctness, tests, consistency, and fit

Index + offline snapshot of coder/coder documentation (progressive disclosure).

Guidelines for creating and managing Pull Requests in this repo

Add a Coder module from registry.coder.com/modules to an existing Coder template, or update one that is already there. Use for requests like "add the Cursor IDE to my template", "give workspaces JetBrains access", "set up code-server", "wire in dotfiles", "install Claude Code in this template", or "pin module versions". Do not use for installing or upgrading Coder itself (use the setup skill), authoring a brand-new template from scratch (use the templates skill), or publishing a custom module to the registry.

Create, edit, push, or version a Coder template. Use for requests like "scaffold a Docker template", "build a Kubernetes template", "add a coder_parameter for the Git repo URL", "push my template to this Coder deployment", "update the existing aws-linux template to add JetBrains", or "deprecate this template version". Do not use for installing or upgrading Coder itself (use the setup skill), adding a single module to a template that already builds (use the modules skill), or authoring custom Terraform providers unrelated to Coder.

Install, deploy, or bootstrap a new Coder (coder/coder) deployment end-to-end. Use for first-time setup on Docker, Kubernetes/Helm, a VM, cloud, HTTPS/domain setup, creating the first admin, pushing a starter template, or building the first workspace. Do not use for upgrades, debugging an existing deployment, editing an existing template, or configuring OAuth/OIDC on a running deployment.

Creates and updates Coder Registry modules with proper scaffolding, Terraform testing, README frontmatter, and version management

Creates and updates Coder Registry workspace templates with agent setup, infrastructure provisioning, and module consumption

Run and debug BalatroBot locally. Use when you need to start Balatro with the BalatroBot Lua mod, manually test or reproduce issues via the JSON-RPC HTTP API, inspect the newest session logs under logs/, and capture screenshots into logs/<session>/artifacts/ using only the balatrobot CLI (no curl, no uvx).

Guide for creating, updating, and following up on pull requests in the aibridge repository. Use when asked to open a PR, update a PR, rewrite a PR description, or follow up on CI/check failures.

Pull request submission and review lifecycle. Use when creating, pushing, or monitoring PRs to ensure all CI checks pass and Codex review comments are resolved before declaring a PR ready.