thought-cabinet 0.1.13 → 0.2.1

package/README.md

@@ -21,30 +21,52 @@ Thought Cabinet solves these by providing:
 ## Quick Start
 
 ```bash
-cd your-project
-
 # 1. Install
 pnpm install -g thought-cabinet
 
-# 2. Initialize thoughts in your project
-thc init
+# 2. Install skills to your AI agent
+cd your-project
+thc skill install
 
-# 3. Install skills to your AI agent
-thc agent init
+# 3. Onboard the project (in your agent session)
+> /onboard
+```
 
-# 4. Use skills in your agent session (e.g. Claude Code)
+The `/onboard` skill initializes thoughts, creates agent memory (`AGENTS.md`), and installs git hooks — all in one step.
+
+Once onboarded, use the workflow skills:
+
+```bash
 > /research-codebase How does the authentication system work?
 > /creating-plan Add OAuth2 support based on the research
 > /implementing-plan thoughts/shared/plans/add-oauth.md
 > /validating-plan thoughts/shared/plans/add-oauth.md
 ```
 
+<details>
+<summary>Manual setup (without the onboard skill)</summary>
+
+If you prefer to set up manually instead of using `/onboard`:
+
+```bash
+cd your-project
+
+# Initialize thoughts
+thc init
+
+# Install skills to your AI agent
+thc skill install
+```
+
+</details>
+
 ## Skills
 
-Skills are installed by `thc agent init` and invoked as slash commands in your agent session:
+Skills are installed by `thc skill install` and invoked as slash commands in your agent session:
 
 | Skill                | Description                                                           |
 | -------------------- | --------------------------------------------------------------------- |
+| `/onboard`           | Initialize thoughts and bootstrap agent memory for a new project      |
 | `/research-codebase` | Deep-dive into codebase, save findings to `thoughts/shared/research/` |
 | `/creating-plan`     | Create implementation plan with phases and success criteria           |
 | `/iterating-plan`    | Refine existing plans based on feedback                               |
@@ -89,13 +111,14 @@ Research and plans are written to disk. The agent reads back only what it needs,
 
 ## CLI Overview
 
-| Command          | Description                                       |
-| ---------------- | ------------------------------------------------- |
-| `thc init`       | Initialize thoughts for current repository        |
-| `thc sync`       | Sync thoughts to git repository                   |
-| `thc status`     | Show thoughts repository status                   |
-| `thc agent init` | Install skills and agents to your AI coding agent |
-| `thc config`     | View or edit configuration                        |
+| Command             | Description                                        |
+| ------------------- | -------------------------------------------------- |
+| `thc init`          | Initialize thoughts for current repository         |
+| `thc sync`          | Sync thoughts to git repository                    |
+| `thc status`        | Show thoughts repository status                    |
+| `thc skill install` | Install skills and agents to your AI coding agent  |
+| `thc skill update`  | Update installed skills from latest package bundle |
+| `thc config`        | View or edit configuration                         |
 
 See [docs/CLI.md](docs/CLI.md) for the full command reference with all flags and options.