pmx-canvas 0.6.2 → 0.6.3

package/CHANGELOG.md

@@ -3,6 +3,25 @@
 All notable changes to `pmx-canvas` are documented here. This project follows
 [Semantic Versioning](https://semver.org/).
 
+## [0.6.3] - 2026-09-23
+
+### Added
+
+- MCP Skills extension support lets compatible hosts discover bundled skills and read their references, scripts, and assets on demand.
+- JSON-render Cards support custom header and footer slots around their body content.
+
+### Changed
+
+- Updated the json-render packages to 0.21.0.
+
+### Fixed
+
+- JSON-render validation preserves initial state, repeat definitions, watchers, and named-slot references instead of dropping them.
+- Authored iframe cards remeasure changing content and leave space around neighbors when growing automatically.
+- Automatic card fitting waits for human grabs to end, and relocations can be undone.
+- Repointing file nodes resolves relative paths against the workspace and rejects unreadable targets without losing the existing content or watcher.
+- Bundled installation instructions match the package version, and paint guidance requires visual confirmation in the affected host.
+
 ## [0.6.2] - 2026-09-09
 
 ### Changed

package/Readme.md

@@ -4,6 +4,12 @@ pmx-canvas is a visual workspace for planning, discovery, analysis, coordination
 and orchestrating work with agents—from exploring an idea to directing its
 execution and carrying the learning forward.
 
+**The board is your extended memory and your agent's working memory.** Use it
+to research, analyze, work with dashboards, and start or plan coding and other
+knowledge work—not just to prepare context for an agent. The [long-term vision](docs/product-context-vision-2026-09.md#work-becomes-memory-and-memory-supports-more-work)
+connects that work to a growing memory graph and maintained wiki, bringing useful
+understanding back into whatever you do next.
+
 **A moldable canvas for agent-assisted thinking.** An infinite 2D surface
 where files, plans, status, charts, fetched web pages, annotations, code
 diffs, and diagrams live side by side. Every node carries its own renderer; agents
@@ -359,7 +365,7 @@ services:
 ```bash
 # .agents/setup — install the CLI (pin the exact version: a fresh orb running
 # @latest can silently pick up a newer release than the one you validated)
-npm install -g pmx-canvas@0.6.2
+npm install -g pmx-canvas@0.6.3
 ```
 
 The server binds the portal-assigned `$PORT` automatically (gated on the
@@ -405,6 +411,12 @@ the agent can read `canvas://skills` and pull in companion skills
 `control-session-orchestrator`, `web-artifacts-builder`, `json-render-*`,
 `pmx-canvas-testing`, `playwright-cli`, etc.) as the work demands.
 
+The MCP server also supports the [Skills extension](docs/mcp.md#skills-extension-sep-2640):
+compatible hosts discover skills through `skills/list` and read instructions, references,
+scripts, and assets at `skill://<name>/<path>`. Files come from the running MCP package;
+restart MCP after an upgrade. Host support determines automatic skill loading, and reading
+a skill never grants permission to execute its scripts. Filesystem installation remains available.
+
 ## Documentation
 
 - **[Node types](docs/node-types.md)** — every node type, edge types, and