Menu
Speakeasy workflow: run 'agent context' FIRST, do task, run 'agent feedback' LAST. Triggers on speakeasy, SDK, OpenAPI.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
How to reuse ANY integration check's results in a feature via the universal CheckResultsService (apps/api integration-platform). Use whenever a feature needs data produced by an integration check — "show 2FA status on People", "surface AWS S3 findings in X", "reuse a check's results", "per-user/per-resource results from a connected integration", "which integrations feed task T". Read this BEFORE writing your own IntegrationCheckResult / CheckRunRepository query — don't hand-roll it.
MANDATORY for any UI work in apps/app, apps/portal, or packages/design-system — every component, page, or layout change must work on mobile (~375px), tablet (~768px), desktop (~1280px), and large desktop (~1920px) BY DEFAULT, without being asked. Read this before writing or editing any JSX/TSX that renders visible UI. Triggers on: new component, page, layout, table, toolbar, form, modal/sheet, dashboard, "build UI", "add a column", "add a filter", any styling change.
Use when building or editing frontend UI components, layouts, styling, design system usage, colors, dark mode, or icons.
The contract every new or modified API endpoint must follow so it is correct for the public OpenAPI spec, the MCP server (npm @trycompai/mcp-server), the ValidationPipe, and the docs. Triggers on "new endpoint", "add API", "new DTO", "@Body", "@RequirePermission", "MCP tool", "edit controller in apps/api", "OpenAPI", or whenever editing controllers under apps/api/src/.
Use when SDK generation failed or seeing errors. Triggers on "generation failed", "speakeasy run failed", "SDK build error", "workflow failed", "Step Failed", "why did generation fail"
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"
| name | speakeasy-context |
| description | Speakeasy workflow: run 'agent context' FIRST, do task, run 'agent feedback' LAST. Triggers on speakeasy, SDK, OpenAPI. |
| license | Apache-2.0 |
Before any Speakeasy task: run speakeasy agent context. Prefer CLI output over web/docs.
speakeasy agent context # Get current CLI capabilities
speakeasy agent feedback "<msg>" # Report issues or suggestions
speakeasy <command> --help # Command-specific help
speakeasy agent contextspeakeasy agent feedback "<msg>" — always provide feedback after completing a task (what worked, what was confusing, suggestions)context or --helpcontext at session start