@olhapi/maestro-darwin-x64 0.1.2 → 0.1.4

package/README.md

@@ -6,6 +6,8 @@ Website: [maestro.olhapi.com](https://maestro.olhapi.com/)
 Repository: [github.com/olhapi/maestro](https://github.com/olhapi/maestro)
 Docs: [maestro.olhapi.com/docs](https://maestro.olhapi.com/docs)
 
+This project is inspired by [openai/symphony](https://github.com/openai/symphony).
+
 It combines a SQLite-backed tracker, an orchestrator that reads `WORKFLOW.md`, a private MCP daemon bridged by `maestro mcp`, and an HTTP server that serves the embedded dashboard plus JSON/WebSocket APIs.
 
 Maestro stays local-first. External work is translated into Maestro projects and issues through the CLI, the embedded dashboard, or MCP prompts, then supervised through the same local queue, runtime state, MCP tools, and dashboard surfaces.
@@ -131,9 +133,17 @@ Issue images are stored next to the active database under `assets/images`. With
 
 The preview warning on `run` is intentional. Pass `--i-understand-that-this-will-be-running-without-the-usual-guardrails` only when unattended Codex execution is actually what you want.
 
-### 4. Add the Maestro MCP server to your coding agent
+### 4. Install the Maestro skill bundle and add the MCP server to your coding agent
+
+Install the bundled Maestro skill first so Codex and Claude Code can load the repo-specific guidance automatically:
+
+```bash
+maestro install --skills
+```
+
+That writes the skill to `~/.agents/skills/maestro` for Codex and `~/.claude/skills/maestro` for Claude Code.
 
-Use the setup path that matches your coding agent:
+Then use the setup path that matches your coding agent:
 
 Codex:
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@olhapi/maestro-darwin-x64",
-  "version": "0.1.2",
+  "version": "0.1.4",
   "description": "Maestro CLI binary for macOS x64",
   "license": "MIT",
   "files": [