speakeasy-api

Speakeasy workflow: run 'agent context' FIRST, do task, run 'agent feedback' LAST. Triggers on speakeasy, SDK, OpenAPI.

Use when generating an MCP server from an OpenAPI spec with Speakeasy. Triggers on "generate MCP server", "MCP server", "Model Context Protocol", "AI assistant tools", "Claude tools", "speakeasy MCP", "mcp-typescript"

Use when CONFIGURING an existing SDK - NOT for initial generation. Covers gen.yaml configuration for all languages: TypeScript, Python, Go, Java, C#, PHP, Ruby. Also covers runtime overrides (retries, timeouts, server selection) in application code. Triggers on "configure SDK", "gen.yaml", "SDK options", "SDK config", "SDK configuration", "runtime override", "SDK client config", "override timeout", "per-call config". For NEW SDK generation, use start-new-sdk-project instead.

Use when creating, applying, or validating overlay files including x-speakeasy extensions. Covers overlay syntax, JSONPath targeting, retries, pagination, naming, grouping, open enums, global headers, custom security. Triggers on "create overlay", "apply overlay", "overlay file", "x-speakeasy", "add extension", "configure retries", "add pagination", "overlay for retries".

Use when generating SDKs for multiple languages from a single OpenAPI spec, or multiple SDK variants from different sources. Covers workflow.yaml multi-target configuration, per-language gen.yaml, monorepo structure. Triggers on "multiple SDKs", "multi-language SDK", "SDK for each language", "multi-target SDK", "SDK monorepo", "generate SDKs for".

Use when extracting or generating an OpenAPI spec from existing API code. Triggers on "extract OpenAPI", "code first", "generate spec from code", "FastAPI OpenAPI", "Spring Boot OpenAPI", "NestJS swagger", "Django OpenAPI", "Flask OpenAPI", "Rails swagger", "Laravel OpenAPI", "existing API code"

Use when generating a Terraform provider from an OpenAPI spec with Speakeasy. Covers entity annotations, CRUD mapping, type inference, workflow configuration, and publishing. Triggers on "terraform provider", "generate terraform", "create terraform provider", "CRUD mapping", "x-speakeasy-entity", "terraform resource", "terraform registry".

Use when setting up SDK testing, configuring contract tests, writing Arazzo test workflows, or running integration tests. Triggers on "SDK testing", "test SDK", "contract testing", "Arazzo tests", "integration tests", "speakeasy test", "mock server", "test generation", "ResponseValidationError"

Rules and best practices when working on the dashboard and elements React frontend codebases

Concepts, external interfaces, and conventions for Gram's audit logging subsystem — the internal Go API for recording actor/action/subject events and the `/rpc/auditlogs.*` management API that exposes them. Activate whenever the task involves recording or exposing audit events (adding or changing audit coverage on a service, introducing a new audited subject or action, writing tests that assert an event was recorded, changing how entries are displayed or filtered).

Rules and best practices when writing and editing Go (Golang) code

Concepts, external interfaces, and conventions for Gram's management API — the Goa-designed HTTP-RPC surface under `/rpc/<service>.<method>` that powers the dashboard, CLI, and public SDK. Activate whenever the task involves designing, implementing, or modifying a management endpoint (new service, new method, payload/result changes, OpenAPI/SDK surface changes, CLI changes, wiring a new service into the server).

Concepts, external interfaces, and conventions for Gram's role-based access control (RBAC) subsystem — scopes, grants, principals, system roles, and the `authz.Engine.Require` enforcement path used inside handlers. Activate whenever the task involves authorization (adding or modifying a scope or resource type, declaring a new role or grant, gating a handler, changing scope inheritance, exposing RBAC state through the dashboard).

Rules when working with PostgreSQL database in Gram

Conventions for authoring or editing analyzers in the `glint/` Go static-analysis package — Gram's custom golangci-lint plugin built on `go/analysis`. Activate this skill whenever the task involves adding, modifying, or testing a `glint` analyzer (new rule key, new diagnostic, settings struct, fixture under `glint/testdata/`, wiring in `BuildAnalyzers`), even if the user does not say "glint" explicitly — phrases like "add a lint rule", "write a custom analyzer", "go/analysis", or "enforce X via golangci-lint" should trigger it.

Use the local Jaeger instance to inspect OpenTelemetry traces emitted by the Gram server and worker during development. Activate when testing backend endpoints, debugging request flows, or validating instrumentation.

Set up granary in a new project. Use when asked to initialize granary, install it, or get started with task management.

Plan and organize multi-project initiatives or significant, substantial projects. Use when work spans multiple services, repositories, or has natural project boundaries.

Orchestrate sub-agents and coordinate multi-agent workflows with granary. Use when delegating tasks, spawning workers, or managing parallel execution.

Execute an assigned granary task as a sub-agent. Use when you receive a task ID to complete.

Plan and organize work into granary projects and tasks. Use when breaking down a feature, creating tasks, or setting up dependencies.

Compare dprint-plugin-java output against spotless:palantir-java-format on a Java project. Builds the WASM plugin, formats with both tools, normalizes imports, and reports match rate with categorized diffs.