workos

Scaffold a new language emitter for oagen, implementing the Emitter interface with idiomatic target-language code generation. Use this skill whenever the user wants to add a new target language, generate SDKs for a new language, add Go/Python/Kotlin/Java/etc. support, create an emitter, or asks about code generation for a language — even if they don't use the word "emitter" explicitly. Also triggers when the user mentions "add language support" or "new SDK target".

Scaffold a new language extractor for oagen's compat system, implementing the Extractor interface to extract a live SDK's public API surface. Use when the user wants to add backwards-compatibility support, build an extractor, check for breaking changes or regressions, or asks about extracting an API surface for any language — even if they don't use the word "extractor" explicitly. Also triggers for "compat support", "API surface analysis", or "public surface extraction".

Create a smoke test script for a new SDK language that verifies wire-level HTTP parity against the OpenAPI spec and live API baseline. Use when adding smoke tests for a new language, verifying a generated SDK against the real API, or checking HTTP request/response correctness. Also triggers for "integration test", "wire-level test", "HTTP parity", or "end-to-end SDK test".

Run the generate-verify loop to iteratively fix an emitter until smoke tests pass. Use after smoke tests are created, when verify reports findings or compile errors, when you need to fix emitter output, or when debugging smoke test failures. Also triggers for "emitter-fixing loop", "generate-verify loop", "fix smoke test failures", "emitter not passing", or "iterate on emitter".

Integrate generated SDK code into a live SDK by running `oagen generate --target`. Required for every Scenario A generation cycle — initial setup and ongoing spec updates. Use when the user wants to merge generated code into an existing SDK or integrate emitter output into a live codebase.

Orchestrate generating an SDK for a target language end-to-end. Determines the right scenario (backwards-compatible or fresh) and guides through the correct sequence of sub-skills. Use when the user wants to generate an SDK, add a new language, create SDK bindings, start a new language target, or asks "how do I add X support". Also triggers for "new SDK", "language support", or "scaffold SDK".

Review resolved operation names from the OpenAPI spec. Runs the resolution algorithm with hints applied and outputs a review table for human approval. Use when reviewing operation names, checking for unhinted operations, auditing method naming, or after spec changes. Also triggers for "operation names", "method names", "hint map", "operation review", "unhinted operations".

Verify that generated SDK code preserves backwards compatibility with a live SDK. Use when regenerating an SDK for a language that has an existing published SDK, checking for breaking changes, regressions, or API surface drift. Also triggers for "BC check", "backwards compatibility", "compat verification", "breaking change detection", "API surface comparison", or "regression check".

One-shot setup for Lifestyles of the AI-Native workshop. Installs and verifies the dev tools an attendee needs — Bun (the check-in tool), the Codex CLI + plugin (Block 3 adversarial review), and git — then confirms the repo is wired up and hands off to the opening check-in. (Voice/Handy is NOT installed here — it's the first hands-on moment of Block 1.) Triggers on "set me up for the workshop", "get me set up", "workshop setup", "set up the workshop", or starting the workshop.

Install and configure Handy, the free, local, open-source push-to-talk voice dictation app, so the user can voice-code in any terminal. Use when someone wants to set up voice input / dictation / "talk to Claude", asks to "set up Handy" or "set up voice coding", or is starting the Lifestyles of the AI-Native workshop. Detects macOS vs. Windows and walks through install, model download, permissions, and a hotkey test.

Run the opt-in Lifestyles of the AI-Native workshop check-in. Use at the start of the workshop and again at the close. Auto-detects opening vs closing, runs the short interview, records your AI-Native score from a LOCAL scan at the open, and at the close posts your answers and your before→after score (anonymously) to the live room board. Triggers on "check in", "coach check-in", "workshop check-in", "run my workshop check-in", "closing check-in", or "share my workflow".

Use when the user asks for a WorkOS docs URL, term, or dashboard field (Sign-in endpoint, initiate_login_uri, Redirect URI, `WORKOS_*` env vars), or is implementing, debugging, or migrating WorkOS — AuthKit, SSO/SAML, Directory Sync, RBAC, FGA, MFA, Vault, Audit Logs, Admin Portal, Pipes (Connected Apps), Feature Flags, Radar (bot/fraud detection), webhooks, Custom Domains, running the `workos` CLI in agent or sandbox sessions (`WORKOS_MODE`, `workos doctor`), or migrating from Auth0, Clerk, Cognito, Firebase, Supabase, Stytch, Descope, or Better Auth. Also triggers on @workos-inc/* imports.

Use when the user is implementing, embedding, or debugging a WorkOS Widget — specifically the User Management, User Profile, Admin Portal SSO Connection, or Admin Portal Domain Verification widgets. Handles the full stack — detecting the frontend (Next.js, React, React Router, TanStack Start, Vite, SvelteKit), generating access tokens via the backend SDK in use (Node, Python, Go, Ruby, PHP, Java, .NET), and wiring up the widget component correctly per the bundled OpenAPI spec. Also use when code imports from @workos-inc/widgets or the user pastes <UserManagement /> or <UserProfile /> JSX.

Analyzes repository health.

Procedure for creating Pipes elevated-access approvals, polling request status, and respecting user instructions. Use whenever calling request_elevated_access, check_access_request, or working with Pipes integration APIs.