@atlashub/smartstack-cli 3.39.0 → 3.41.0

package/templates/skills/cc-skill/references/frontmatter-reference.md

@@ -1,182 +1,182 @@
-# Skill Frontmatter Reference
-
-Complete reference for all SKILL.md YAML frontmatter fields, based on the official Claude Code documentation.
-
-Source: https://code.claude.com/docs/en/skills
-
-## Required Fields
-
-### `name`
-- **Type:** string
-- **Required:** YES
-- **Constraints:** lowercase, max 64 characters, kebab-case
-- **Purpose:** Unique identifier. Becomes the `/name` command.
-- **Examples:**
-  ```yaml
-  name: my-skill
-  name: code-review
-  name: deploy-staging
-  ```
-
-### `description`
-- **Type:** string (multi-line supported)
-- **Required:** YES
-- **Purpose:** Claude uses this to decide when to auto-invoke the skill. Include trigger keywords.
-- **Examples:**
-  ```yaml
-  description: Generate API controllers following REST conventions.
-
-  description: |
-    Deploy application to staging environment.
-    Use this skill when:
-    - User mentions "deploy", "staging", "release"
-    - User wants to push changes to staging
-    - Deployment pipeline needs to be triggered
-  ```
-
-## Optional Fields
-
-### `disable-model-invocation`
-- **Type:** boolean
-- **Default:** false
-- **Purpose:** When `true`, only the user can invoke via `/name`. Claude will never auto-invoke.
-- **Use for:** Side-effect operations (deploy, commit, publish, delete)
-- **Example:**
-  ```yaml
-  disable-model-invocation: true
-  ```
-
-### `user-invocable`
-- **Type:** boolean
-- **Default:** true
-- **Purpose:** When `false`, skill is hidden from /menu. Used for background knowledge injection.
-- **Example:**
-  ```yaml
-  user-invocable: false
-  ```
-
-### `allowed-tools`
-- **Type:** string (comma-separated)
-- **Default:** (none)
-- **Purpose:** Tools the skill can use without triggering permission prompts.
-- **Valid tools:** Read, Write, Edit, Bash, Glob, Grep, Task, WebFetch, WebSearch, NotebookEdit, AskUserQuestion, TodoWrite, Skill, ToolSearch
-- **Example:**
-  ```yaml
-  allowed-tools: "Read, Grep, Glob, WebSearch, WebFetch"
-  ```
-
-### `model`
-- **Type:** string
-- **Default:** inherit
-- **Valid values:** inherit, sonnet, opus, haiku
-- **Purpose:** Override the model used when this skill runs.
-- **Guidance:**
-  - `haiku` - Fast, cheap. Simple tasks.
-  - `sonnet` - Balanced. Most tasks.
-  - `opus` - Most capable. Complex reasoning.
-  - `inherit` - Use user's configured model.
-- **Example:**
-  ```yaml
-  model: haiku
-  ```
-
-### `context`
-- **Type:** string
-- **Valid values:** fork
-- **Purpose:** Run skill in an isolated subagent context. Separate conversation, clean state.
-- **Example:**
-  ```yaml
-  context: fork
-  ```
-
-### `agent`
-- **Type:** string
-- **Purpose:** Which subagent type to use when `context: fork`.
-- **Valid values:** Explore, Plan, general-purpose, Bash, or any custom agent name
-- **Example:**
-  ```yaml
-  context: fork
-  agent: Explore
-  ```
-
-### `argument-hint`
-- **Type:** string
-- **Purpose:** Autocomplete hint shown in the /menu.
-- **Example:**
-  ```yaml
-  argument-hint: "<command> [options]"
-  argument-hint: "[filename]"
-  argument-hint: "<create|update> [name]"
-  ```
-
-### `hooks`
-- **Type:** object
-- **Purpose:** Lifecycle hooks scoped to this skill.
-- **Events:** PreToolUse, PostToolUse, Stop, SessionStart, etc.
-- **Example:**
-  ```yaml
-  hooks:
-    PreToolUse:
-      - matcher: "Bash"
-        hooks:
-          - type: command
-            command: "./scripts/validate.sh"
-  ```
-
-## Dynamic Placeholders
-
-Available in SKILL.md content (not frontmatter):
-
-| Placeholder | Description |
-|-------------|-------------|
-| `$ARGUMENTS` | All arguments passed to skill |
-| `$1`, `$2`, ... | Positional arguments |
-| `$ARGUMENTS[0]` | Same as $1 |
-| `${CLAUDE_SESSION_ID}` | Current session ID |
-| `` !`command` `` | Run shell command, inject output |
-
-## Examples
-
-### Minimal Skill
-```yaml
----
-name: hello
-description: Greet the user
----
-
-Say hello to the user: $ARGUMENTS
-```
-
-### Side-Effect Skill
-```yaml
----
-name: deploy
-description: Deploy to staging
-disable-model-invocation: true
-argument-hint: "[environment]"
----
-```
-
-### Research Skill
-```yaml
----
-name: search-code
-description: Search codebase for patterns
-context: fork
-agent: Explore
-allowed-tools: "Read, Grep, Glob"
-argument-hint: "<query>"
----
-```
-
-### Complex Workflow
-```yaml
----
-name: generate-api
-description: |
-  Generate API endpoints. Use when:
-  - Creating new API routes
-  - Adding CRUD operations
-argument-hint: "<entity> [--with-tests]"
----
-```
+# Skill Frontmatter Reference
+
+Complete reference for all SKILL.md YAML frontmatter fields, based on the official Claude Code documentation.
+
+Source: https://code.claude.com/docs/en/skills
+
+## Required Fields
+
+### `name`
+- **Type:** string
+- **Required:** YES
+- **Constraints:** lowercase, max 64 characters, kebab-case
+- **Purpose:** Unique identifier. Becomes the `/name` command.
+- **Examples:**
+  ```yaml
+  name: my-skill
+  name: code-review
+  name: deploy-staging
+  ```
+
+### `description`
+- **Type:** string (multi-line supported)
+- **Required:** YES
+- **Purpose:** Claude uses this to decide when to auto-invoke the skill. Include trigger keywords.
+- **Examples:**
+  ```yaml
+  description: Generate API controllers following REST conventions.
+
+  description: |
+    Deploy application to staging environment.
+    Use this skill when:
+    - User mentions "deploy", "staging", "release"
+    - User wants to push changes to staging
+    - Deployment pipeline needs to be triggered
+  ```
+
+## Optional Fields
+
+### `disable-model-invocation`
+- **Type:** boolean
+- **Default:** false
+- **Purpose:** When `true`, only the user can invoke via `/name`. Claude will never auto-invoke.
+- **Use for:** Side-effect operations (deploy, commit, publish, delete)
+- **Example:**
+  ```yaml
+  disable-model-invocation: true
+  ```
+
+### `user-invocable`
+- **Type:** boolean
+- **Default:** true
+- **Purpose:** When `false`, skill is hidden from /menu. Used for background knowledge injection.
+- **Example:**
+  ```yaml
+  user-invocable: false
+  ```
+
+### `allowed-tools`
+- **Type:** string (comma-separated)
+- **Default:** (none)
+- **Purpose:** Tools the skill can use without triggering permission prompts.
+- **Valid tools:** Read, Write, Edit, Bash, Glob, Grep, Task, WebFetch, WebSearch, NotebookEdit, AskUserQuestion, TodoWrite, Skill, ToolSearch
+- **Example:**
+  ```yaml
+  allowed-tools: "Read, Grep, Glob, WebSearch, WebFetch"
+  ```
+
+### `model`
+- **Type:** string
+- **Default:** inherit
+- **Valid values:** inherit, sonnet, opus, haiku
+- **Purpose:** Override the model used when this skill runs.
+- **Guidance:**
+  - `haiku` - Fast, cheap. Simple tasks.
+  - `sonnet` - Balanced. Most tasks.
+  - `opus` - Most capable. Complex reasoning.
+  - `inherit` - Use user's configured model.
+- **Example:**
+  ```yaml
+  model: haiku
+  ```
+
+### `context`
+- **Type:** string
+- **Valid values:** fork
+- **Purpose:** Run skill in an isolated subagent context. Separate conversation, clean state.
+- **Example:**
+  ```yaml
+  context: fork
+  ```
+
+### `agent`
+- **Type:** string
+- **Purpose:** Which subagent type to use when `context: fork`.
+- **Valid values:** Explore, Plan, general-purpose, Bash, or any custom agent name
+- **Example:**
+  ```yaml
+  context: fork
+  agent: Explore
+  ```
+
+### `argument-hint`
+- **Type:** string
+- **Purpose:** Autocomplete hint shown in the /menu.
+- **Example:**
+  ```yaml
+  argument-hint: "<command> [options]"
+  argument-hint: "[filename]"
+  argument-hint: "<create|update> [name]"
+  ```
+
+### `hooks`
+- **Type:** object
+- **Purpose:** Lifecycle hooks scoped to this skill.
+- **Events:** PreToolUse, PostToolUse, Stop, SessionStart, etc.
+- **Example:**
+  ```yaml
+  hooks:
+    PreToolUse:
+      - matcher: "Bash"
+        hooks:
+          - type: command
+            command: "./scripts/validate.sh"
+  ```
+
+## Dynamic Placeholders
+
+Available in SKILL.md content (not frontmatter):
+
+| Placeholder | Description |
+|-------------|-------------|
+| `$ARGUMENTS` | All arguments passed to skill |
+| `$1`, `$2`, ... | Positional arguments |
+| `$ARGUMENTS[0]` | Same as $1 |
+| `${CLAUDE_SESSION_ID}` | Current session ID |
+| `` !`command` `` | Run shell command, inject output |
+
+## Examples
+
+### Minimal Skill
+```yaml
+---
+name: hello
+description: Greet the user
+---
+
+Say hello to the user: $ARGUMENTS
+```
+
+### Side-Effect Skill
+```yaml
+---
+name: deploy
+description: Deploy to staging
+disable-model-invocation: true
+argument-hint: "[environment]"
+---
+```
+
+### Research Skill
+```yaml
+---
+name: search-code
+description: Search codebase for patterns
+context: fork
+agent: Explore
+allowed-tools: "Read, Grep, Glob"
+argument-hint: "<query>"
+---
+```
+
+### Complex Workflow
+```yaml
+---
+name: generate-api
+description: |
+  Generate API endpoints. Use when:
+  - Creating new API routes
+  - Adding CRUD operations
+argument-hint: "<entity> [--with-tests]"
+---
+```