Align mcp-server-dev skills with claude.com/docs connector guidance (#1418)

- build-mcp-server: load llms-full.txt for Claude-specific context;
  add Phase 6 (test in Claude, review checklist, submit, ship plugin)
- references/auth.md: add Claude auth-type table, callback URL,
  not-supported list
- references/tool-design.md: add Anthropic Directory hard requirements
  (annotations, name length, read/write split, prompt-injection rule)
- build-mcp-app: add Claude host specifics (prefersBorder,
  safeAreaInsets, CSP) and submission asset specs; testing via
  custom connector
- build-mcpb: note remote servers are the recommended directory path

plugins/mcp-server-dev/skills/build-mcp-app/SKILL.md

@@ -10,6 +10,15 @@ An MCP app is a standard MCP server that **also serves UI resources** — intera
 
 The UI layer is **additive**. Under the hood it's still tools, resources, and the same wire protocol. If you haven't built a plain MCP server before, the `build-mcp-server` skill covers the base layer. This skill adds widgets on top.
 
+> **Testing in Claude:** Add the server as a custom connector in claude.ai (via a Cloudflare tunnel for local dev) — this exercises the real iframe sandbox and `hostContext`. See https://claude.com/docs/connectors/building/testing.
+
+## Claude host specifics
+
+- `_meta.ui.prefersBorder: false` on a `ui://` resource removes the outer card border (mobile).
+- `hostContext.safeAreaInsets: {top, right, bottom, left}` (px) — honor these for notches and the composer overlay.
+- `_meta.ui.csp.{connectDomains, resourceDomains, baseUriDomains}` — declare external origins per resource; default is block-all. `frameDomains` is currently restricted in Claude.
+- Directory submission for MCP Apps requires 3–5 PNG screenshots, ≥1000px wide, cropped to the app response only (no prompt in the image). See https://claude.com/docs/connectors/building/submission#asset-specifications.
+
 ---
 
 ## When a widget beats plain text

plugins/mcp-server-dev/skills/build-mcp-server/SKILL.md

@@ -8,6 +8,8 @@ version: 0.1.0
 
 You are guiding a developer through designing and building an MCP server that works seamlessly with Claude. MCP servers come in many forms — picking the wrong shape early causes painful rewrites later. Your first job is **discovery, not code**.
 
+**Load Claude-specific context first.** The MCP spec is generic; Claude has additional auth types, review criteria, and limits. Before answering questions or scaffolding, fetch `https://claude.com/docs/llms-full.txt` (the full export of the Claude connector docs) so your guidance reflects Claude's actual constraints.
+
 Do not start scaffolding until you have answers to the questions in Phase 1. If the user's opening message already answers them, acknowledge that and skip straight to the recommendation.
 
 ---
@@ -182,6 +184,17 @@ Tools are one of three server primitives. Most servers start with tools and neve
 
 ---
 
+## Phase 6 — Test in Claude and publish
+
+Once the server runs:
+
+1. **Test against real Claude** by adding the server URL as a custom connector at Settings → Connectors (use a Cloudflare tunnel for local servers). Claude identifies itself with `clientInfo.name: "claude-ai"` on initialize. → https://claude.com/docs/connectors/building/testing
+2. **Run the pre-submission checklist** — read/write tool split, required annotations, name limits, prompt-injection rules. → https://claude.com/docs/connectors/building/review-criteria
+3. **Submit to the Anthropic Directory.** → https://claude.com/docs/connectors/building/submission
+4. **Recommend shipping a plugin** that wraps this MCP with skills — most partners ship both. → https://claude.com/docs/connectors/building/what-to-build
+
+---
+
 ## Quick reference: decision matrix
 
 | Scenario | Deployment | Tool pattern |

plugins/mcp-server-dev/skills/build-mcp-server/references/auth.md

@@ -2,6 +2,22 @@
 
 Auth is the reason most people end up needing a **remote** server even when a local one would be simpler. OAuth redirects, token storage, and refresh all work cleanly when there's a real hosted endpoint to redirect back to.
 
+## Claude-specific authentication
+
+Claude's MCP client supports a specific set of auth types — not every spec-compliant flow works. Full reference: https://claude.com/docs/connectors/building/authentication
+
+| Type | Notes |
+|---|---|
+| `oauth_dcr` | Supported. For high-volume directory entries, prefer CIMD or Anthropic-held creds — DCR registers a new client on every fresh connection. |
+| `oauth_cimd` | Supported, recommended over DCR for directory entries. |
+| `oauth_anthropic_creds` | Partner provides `client_id`/`client_secret` to Anthropic; user-consent-gated. Contact `mcp-review@anthropic.com`. |
+| `custom_connection` | User supplies URL/creds at connect time (Snowflake-style). Contact `mcp-review@anthropic.com`. |
+| `none` | Authless. |
+
+**Not supported:** user-pasted bearer tokens (`static_bearer`); pure machine-to-machine `client_credentials` grant without user consent.
+
+**Callback URL** (single, all surfaces): `https://claude.ai/api/mcp/auth_callback`
+
 ---
 
 ## The three tiers

plugins/mcp-server-dev/skills/build-mcp-server/references/tool-design.md

@@ -2,6 +2,16 @@
 
 Tool schemas and descriptions are prompt engineering. They land directly in Claude's context and determine whether Claude picks the right tool with the right arguments. Most MCP integration bugs trace back to vague descriptions or loose schemas.
 
+## Anthropic Directory hard requirements
+
+If this server will be submitted to the Anthropic Directory, the following are pass/fail review criteria (full list: https://claude.com/docs/connectors/building/review-criteria):
+
+- Every tool **must** include `readOnlyHint`, `destructiveHint`, and `title` annotations — these determine auto-permissions in Claude.
+- Tool names **must** be ≤64 characters.
+- Read and write operations **must** be in separate tools. A single tool accepting both GET and POST/PUT/PATCH/DELETE is rejected — documenting safe vs unsafe within one tool's description does not satisfy this.
+- Tool descriptions **must not** instruct Claude how to behave (e.g. "always do X", "you must call Y first", overriding system instructions, promoting products) — treated as prompt injection at review.
+- Tools that accept freeform API endpoints/params **must** reference the target API's documentation in their description.
+
 ---
 
 ## Descriptions

plugins/mcp-server-dev/skills/build-mcpb/SKILL.md

@@ -8,6 +8,8 @@ version: 0.1.0
 
 MCPB is a local MCP server **packaged with its runtime**. The user installs one file; it runs without needing Node, Python, or any toolchain on their machine. It's the sanctioned way to distribute local MCP servers.
 
+> MCPB is the **secondary** distribution path. Anthropic recommends remote MCP servers for directory listing — see https://claude.com/docs/connectors/building/what-to-build.
+
 **Use MCPB when the server must run on the user's machine** — reading local files, driving a desktop app, talking to localhost services, OS-level APIs. If your server only hits cloud APIs, you almost certainly want a remote HTTP server instead (see `build-mcp-server`). Don't pay the MCPB packaging tax for something that could be a URL.
 
 ---