product-surface-areas
Consolidated dependency graph of Inkeep customer-facing surface areas (UIs, CLIs, SDKs, APIs, protocols, config formats). Example use: as a prd-time (planning/brainstorming phase) or post-change checklist to understand the full scope of side-effects or what making one change to the product means for the rest. Use whenever you need to understand the "ripple" out effects of any change.
Install
mkdir -p .claude/skills/product-surface-areas && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8591" && unzip -o skill.zip -d .claude/skills/product-surface-areas && rm skill.zipInstalls to .claude/skills/product-surface-areas
About this skill
Inkeep Product Surface Area Inventory
Overview
This is a consolidated inventory of customer-facing “surface areas”: anything a customer can directly use, interact with, or take a dependency on. Use it to conceptually understand the surface area of what one change may mean for the whole product (i.e. the entire feature dependency tree/propagation chain end-to-end).
Companion skills: For who is affected and how changes propagate per audience, load audience-impact. For internal/infra surfaces, load internal-surface-areas.
Summary
| Category | Count |
|---|---|
| APIs & Customer-facing Data Contracts | 13 |
| SDKs & Libraries | 2 |
| CLI Tools | 2 |
| MCP Servers & Endpoints | 7 |
| Management UI (Visual Builder & Dashboard) | 16 |
| Chat Experiences | 3 |
| Observability UI | 5 |
| Evaluations UI | 6 |
| Templates & Scaffolding | 2 |
| Deployment Interfaces | 3 |
| Documentation & Content | 4 |
| Total | 63 |
Surface Catalog
APIs & Customer-facing Data Contracts
Customer goal: integrate with, automate, or depend on platform contracts programmatically.
| Surface | Description | Depends On | Source Code |
|---|---|---|---|
| Management API | REST endpoints at /manage/... for configuration/CRUD operations. | Database Schemas (internal) | agents-api/src/domains/manage/routes/ |
| Run API (OpenAI Chat Completions) | OpenAI-compatible chat completions endpoint: POST /run/v1/chat/completions (SSE streaming). | Database Schemas (internal) | agents-api/src/domains/run/routes/chat.ts |
| Chat API (Vercel AI SDK Data Stream) | Vercel AI SDK data stream endpoint: POST /run/api/chat. | Database Schemas (internal) | agents-api/src/domains/run/routes/chatDataStream.ts |
| A2A Protocol | Agent-to-agent JSON-RPC 2.0 interface at /agents/a2a. | Database Schemas (internal) | agents-api/src/domains/run/a2a/ |
| Agent Discovery | A2A agent card discovery: GET /.well-known/agent.json. | A2A Protocol | agents-api/src/domains/run/routes/agents.ts |
| MCP Protocol | MCP JSON-RPC 2.0 interface (hosted endpoint referenced in transcript as POST /v1/mcp). | Database Schemas (internal) | agents-api/src/domains/run/routes/mcp.ts |
| Webhook Format (Trigger Invocation) | Trigger invocation request/response contract for event-driven agent runs. | Management API, Run API (OpenAI Chat Completions) | agents-api/src/domains/run/routes/webhooks.ts |
| OAuth Routes | OAuth flow routes for tool OAuth configuration (transcript: /manage/oauth/*). | Management API | agents-api/src/domains/manage/routes/oauth.ts |
| OpenAPI Docs | Hosted API documentation: /docs and /openapi.json. | Management API, Run API (OpenAI Chat Completions), Chat API (Vercel AI SDK Data Stream) | agents-api/src/index.ts |
| OpenTelemetry Schema | Span names and attribute keys used for tracing/observability. | — | packages/agents-core/src/constants/otel-attributes.ts |
inkeep.config.ts format | TypeScript project configuration structure consumed by CLI. | — | agents-cli/src/config.ts |
| Environment Variables | Required env var names and expected formats used across services. | — | agents-api/src/env.ts, packages/agents-core/src/env.ts |
Shared Types (@inkeep/agents-core exports) | Exported types/utilities used across SDK/UI/CLI (customer dependency via npm). | — | packages/agents-core/src/index.ts, packages/agents-core/src/client-exports.ts |
SDKs & Libraries
Customer goal: build against Inkeep in code via packaged libraries.
| Surface | Description | Depends On | Source Code |
|---|---|---|---|
TypeScript SDK (@inkeep/agents-sdk) | Builder APIs for defining agents/projects/tools/components. | Management API, Run API (OpenAI Chat Completions), Shared Types (@inkeep/agents-core exports) | packages/agents-sdk/src/ (entry: index.ts) |
Vercel AI SDK Provider (@inkeep/ai-sdk-provider) | Provider integration for Vercel AI SDK (useChat, data stream). | Chat API (Vercel AI SDK Data Stream) | packages/ai-sdk-provider/src/ (entry: index.ts) |
CLI Tools
Customer goal: manage and sync projects from the terminal.
| Surface | Description | Depends On | Source Code |
|---|---|---|---|
Inkeep CLI (inkeep / agents-cli) | Command-line workflows: init, push, pull, add, dev, login. | TypeScript SDK (@inkeep/agents-sdk), Management API, inkeep.config.ts format | agents-cli/src/ (entry: index.ts, commands: commands/) |
Create-Agents CLI (@inkeep/create-agents) | Scaffolding CLI to bootstrap a project from the template. | Create-Agents Template | packages/create-agents/src/ |
MCP Servers & Endpoints
Customer goal: connect MCP clients to Inkeep capabilities via servers/endpoints and examples.
| Surface | Description | Depends On | Source Code |
|---|---|---|---|
Unified MCP Server (@inkeep/agents-mcp) | Standalone MCP server package wrapping multiple APIs (manage, run, evals). | MCP Protocol, Management API, Run API (OpenAI Chat Completions) | packages/agents-mcp/src/ |
Unified MCP Endpoint (/mcp) | Hosted unified MCP server endpoint. | Unified MCP Server (@inkeep/agents-mcp) | agents-api/src/domains/mcp/routes/mcp.ts |
Runtime MCP Endpoint (/run/v1/mcp) | Hosted runtime MCP endpoint for per-agent chat MCP. | MCP Protocol | agents-api/src/domains/run/routes/mcp.ts |
GitHub MCP Server (/work-apps/github/mcp) | Hosted MCP surface for GitHub operations. | MCP Protocol, GitHub Integration | packages/agents-work-apps/src/github/mcp/ |
| MCP Templates | Example MCP integrations (Slack, Zendesk, Vercel template). | MCP Protocol | agents-cookbook/template-mcps/ |
Management UI (Visual Builder & Dashboard)
Customer goal: configure agents, projects, tools, and org settings through the web app.
| Surface | Description | Depends On | Source Code |
|---|---|---|---|
| Login Page | Manage UI authentication entry point (email/password, OAuth, SSO). | — | agents-manage-ui/src/app/login/ |
| Device Auth Page | Device authorization flow used by CLI login. | — | agents-manage-ui/src/app/device/ |
| Visual Agent Builder | Drag-and-drop agent configuration UI. | Management API, Shared Types (@inkeep/agents-core exports) | agents-manage-ui/src/app/[tenantId]/projects/[projectId]/agents/[agentId]/ |
| Projects Dashboard | Project list and creation UI. | Management API | agents-manage-ui/src/app/[tenantId]/projects/page.tsx |
| Team Members | Roles and permissions management UI. | Management API | agents-manage-ui/src/app/[tenantId]/projects/[projectId]/members/ |
| API Keys | API key creation and management UI. | Management API | agents-manage-ui/src/app/[tenantId]/projects/[projectId]/api-keys/ |
| Organization Settings | Tenant/org settings UI. | Management API | agents-manage-ui/src/app/[tenantId]/settings/ |
| GitHub Integration | UI to connect/configure the GitHub work app. | Management API | agents-manage-ui/src/app/[tenantId]/work-apps/github/ |
| MCP Tools UI | UI for configuring MCP servers. | Management API | agents-manage-ui/src/app/[tenantId]/projects/[projectId]/mcp-servers/ |
| Function Tools UI | UI for inline/function tool configuration. | Management API | agents-manage-ui/src/components/agent/sidepane/nodes/function-tool-node-editor.tsx |
| Credentials UI | UI for secrets and OAuth credential management. | Management API | agents-manage-ui/src/app/[tenantId]/projects/[projectId]/credentials/ |
| Data Components UI | UI for structured output schemas (data components). | Management API | agents-manage-ui/src/app/[tenantId]/projects/[projectId]/components/ |
| Artifacts UI | UI for artifact component schemas. | Management API | agents-manage-ui/src/app/[tenantId]/projects/[projectId]/artifacts/ |
| External Agents UI | UI for configuring third-party agent connections. | Management API | agents-manage-ui/src/app/[tenantId]/projects/[projectId]/external-agents/ |
| Triggers UI | UI for webhook trigger configuration. | Management API | agents-manage-ui/src/app/.../triggers/ |
| Trigger Invocations UI | UI for trigger execution history. | Management API | agents-manage-ui/src/app/.../triggers/[triggerId]/invocations/ |
Chat Experiences
Customer goal: talk to agents (and, for Copilot, edit/build agents) via chat interfaces.
| Surface | Description | Depends On | Source Code |
|---|---|---|---|
| Chat Widget | Embeddable chat components for end-user chat. | Chat API (Vercel AI SDK Data Stream) | agents-ui/src/ |
| Playground (“Try it”) | In-dashboard agent testing chat panel with optional debug/traces. | Chat API (Vercel AI SDK Data Stream), Management API, OpenTelemetry Schema | agents-manage-ui/src/components/agent/playground/, agents-api/src/domains/manage/routes/playgroundToken.ts |
| Chat-to-Edit (Copilot) | "Build/Edit with AI" chat-driven agent creation/modification experience in the builder. | Chat API (Vercel AI SDK Data Stream), Unified MCP Server (@inkeep/agents-mcp), Management API | agents-manage-ui/src/components/agent/copilot/, agents-manage-ui/src/contexts/copilot.tsx |
Observability UI
Customer goal: understand what agents did and why (traces, analytics, debugging).
| Surface | Description | Depends On | Source Code |
|---|---|---|---|
| Traces Dashboard | Conversation analytics, charts, filters. | OpenTelemetry Schema, Management API | agents-manage-ui/src/app/[tenantId]/projects/[projectId]/traces/page.tsx |
| Conversation Inspector | Message-level drilldown for a conversation trace. | OpenTelemetry Schema | agents-manage-ui/src/app/.../traces/conversations/[conversationId]/ |
| AI Calls View | Trace view for LLM calls (prompts/responses, token usage). | OpenTelemetry Schema | agents-manage-ui/src/app/.../traces/ai-calls/ |
| Tool Calls View | Trace view for tool |
Content truncated.
More by inkeep
View all skills by inkeep →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all servers
Knowledge Graph MemoryBuild persistent semantic networks for enterprise & engineering data management. Enable data persistence and memory acro
MCP Server ChartEffortlessly create 25+ chart types with MCP Server Chart. Visualize complex datasets using TypeScript and AntV for powe
Basic MemoryBasic Memory is a knowledge management system that builds a persistent semantic graph in markdown, locally and securely.
Context PortalContext Portal: Manage project memory with a database-backed system for decisions, tracking, and semantic search via a k
Microsoft 365Easily automate Microsoft 365 tasks with simplified Graph API authentication. Access email, calendar, OneDrive, and more
TypeScript RefactoringTypeScript Refactoring offers advanced TypeScript/JavaScript code analysis and intelligent refactoring for seamless and
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.