@latellu/atlas-agent-skills 0.5.0 → 0.5.1

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "atlas",
-  "version": "0.5.0",
+  "version": "0.5.1",
   "description": "Work with Atlas CMS from Claude Code: bundles the Atlas MCP server (read/write content via tools) and the atlas-cms skill that teaches agents when and how to use the MCP tools, the @latellu/atlas-sdk delivery/management clients, and the @latellu/atlas-cli type generator.",
   "author": {
     "name": "Latellu",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@latellu/atlas-agent-skills",
-  "version": "0.5.0",
+  "version": "0.5.1",
   "description": "Agent skill + MCP configuration for Atlas CMS. Works as a Claude Code plugin and as plain markdown guidance for any AI coding agent (Cursor, Codex, opencode, Gemini CLI, ...).",
   "license": "MIT",
   "author": "Latellu (https://github.com/tenriajeng)",

package/skills/atlas-cms/SKILL.md

@@ -53,15 +53,16 @@ browser-delivered code. Management usage is server-side only (API routes, script
 
 Every REST response is an envelope: `{ success, message, data?, meta?, code?, errors? }`.
 The SDK and MCP unwrap it, but two payload quirks leak through in places: `entry.data`,
-page `seo`, and block `data` are stored/transported as **JSON strings** (the SDK parses
-them for you; MCP `get_page` does not), and list `meta` uses
+page `seo`, and block `data` are stored/transported as **JSON strings** (the SDK and
+MCP ≥ 1.2.0 parse them for you), and list `meta` uses
 `{ total_data, current_page, page_size, total_pages, next_cursor }`.
 
 Error codes you will actually see: `UNAUTHORIZED` (401 — missing/empty/wrong-class key),
 `FORBIDDEN` (403 — missing scope or RBAC), `NOT_FOUND` (404 — also returned for
 other-workspace resources), `VALIDATION_ERROR` (400 — with field detail),
 `PAGE_TOO_DEEP` (400 — offset pagination past page 1000), and 429 rate limiting
-(back off exponentially; only the SDK management client retries for you).
+(the SDK management client and MCP ≥ 1.2.0 retry automatically; elsewhere back off
+exponentially yourself).
 
 Pagination limits: `limit` max 100, `page` max 1000; past that, switch to cursor
 pagination (`meta.next_cursor`, opaque — never construct cursors yourself; `total_data`

package/skills/atlas-cms/references/mcp.md

@@ -88,7 +88,8 @@ The MCP manage plane is now fully covered. These gaps remain:
 
 - **No automatic merge on `update_entry`** — the tool replaces `data` wholesale, so you
   must read-modify-write yourself: `get_entry` → merge your changes → `update_entry`.
-  The management SDK offers an `update` overload that accepts a patch, but MCP does not.
+  (The management SDK's `update` is a full replace too — this is API semantics, not an
+  MCP quirk.)
 - **Schema is dashboard-only.** Creating content types, fields, or block types is not
   exposed via MCP, SDK, or API. "Create a content type" = ask the user to do it in the
   dashboard, then continue.
@@ -100,8 +101,9 @@ format per field type (richtext = Tiptap HTML, relation/image = UUIDs, etc.).
 
 - **Drafts are invisible to live keys** — `list_entries(status="draft")` returning
   empty means key scoping, not an empty workspace.
-- **`get_entry` errors if the slug belongs to a different content type** — content types
-  used to share slug namespaces, now you get a clear error instead of silent mismatch.
+- **`get_entry` looks up by slug alone** (slug-global, `content_type` is not sent to the
+  API) — but if the entry found belongs to a different content type than you requested,
+  the tool returns a clear mismatch error instead of the wrong entry.
 - Every write sends a fresh auto-generated `Idempotency-Key` per call, so re-issuing a
   failed create as a *new tool call* is a new operation — check whether the first call
   actually landed (e.g. `get_entry`) before retrying creates.