@mulmocast/slide 0.3.0 → 0.3.2

package/.claude/skills/extend/SKILL.md

@@ -8,22 +8,27 @@ Convert a MulmoScript JSON into an ExtendedScript by adding `scriptMeta` and `be
 /extend <mulmo_script.json path> [--source <source file path>]
 ```
 
+## CLI Command
+
+Determine the correct CLI command prefix by checking `package.json` in the project root:
+- If `name` is `"@mulmocast/slide"` (i.e., developing MulmoCast-Slides itself) → use `yarn cli`
+- Otherwise → use `npx mulmo-slide`
+
+Use this prefix (referred to as `{cli}` below) for all CLI calls in the steps.
+
 ## Instructions
 
 ### Step 1: Read Inputs
 
-1. Read the MulmoScript JSON at the specified path
-2. Read the ExtendedScript schema: `.claude/skills/extend/references/extended-script-schema.md`
-3. Check for extracted texts file:
-   - Look for `extracted_texts.json` in the same directory as the MulmoScript
-   - This file is generated by `mulmo-slide pdf` and contains per-page text extracted from the source PDF
-   - If found, read it — this provides the raw text content for each beat
-4. Locate the source file:
+Use the Read tool (not bash/node commands) to read the following files:
+
+1. The MulmoScript JSON at the specified path
+2. `.claude/skills/extend/references/extended-script-schema.md`
+3. `extracted_texts.json` in the same directory as the MulmoScript (if it exists — generated by PDF converter, provides raw text per beat)
+4. The source file:
    - If `--source` is specified, use that file
-   - Otherwise, infer from the MulmoScript path:
-     - `scripts/{basename}/mulmo_script.json` -> search for `samples/{basename}.*` (try `.md`, `.pptx`, `.pdf`, `.key`)
+   - Otherwise, infer from the MulmoScript path: `scripts/{basename}/mulmo_script.json` -> search for `samples/{basename}.*` (try `.md`, `.pptx`, `.pdf`, `.key`)
    - If no source file found, work from the MulmoScript content and extracted texts alone
-5. If a source file is found, read it
 
 ### Step 2: Analyze Content
 
@@ -85,7 +90,7 @@ Based on the analysis, generate:
    - Same directory as input: replace `mulmo_script.json` with `extended_script.json`
    - Example: `scripts/simple_text/mulmo_script.json` -> `scripts/simple_text/extended_script.json`
 2. Write the JSON with 2-space indentation
-3. Run `mulmo-slide extend validate <output_path>` (or `yarn cli extend validate <output_path>`) to validate against the schema
+3. Run `{cli} extend validate <output_path>` to validate against the schema
 4. If validation fails, fix the errors and re-write the file, then validate again
 5. Generate MulmoScript from ExtendedScript using the preprocessor:
    ```bash

package/.claude/skills/narrate/SKILL.md

@@ -10,6 +10,14 @@ Convert any supported source file (PDF, PPTX, Markdown, Keynote) into a validate
 
 Supported formats: `.pdf`, `.pptx`, `.md`, `.key`
 
+## CLI Command
+
+Determine the correct CLI command prefix by checking `package.json` in the project root:
+- If `name` is `"@mulmocast/slide"` (i.e., developing MulmoCast-Slides itself) → use `yarn cli`
+- Otherwise → use `npx mulmo-slide`
+
+Use this prefix (referred to as `{cli}` below) for all CLI calls in the steps.
+
 ## Instructions
 
 ### Step 1: Convert Source to MulmoScript
@@ -18,22 +26,22 @@ Detect the file format and run the appropriate converter.
 
 **PDF:**
 ```bash
-yarn cli pdf <file>
+{cli} pdf <file>
 ```
 
 **PPTX:**
 ```bash
-yarn cli pptx <file>
+{cli} pptx <file>
 ```
 
 **Markdown:**
 ```bash
-yarn cli markdown <file>
+{cli} markdown <file>
 ```
 
 **Keynote (.key):**
 ```bash
-yarn cli keynote <file>
+{cli} keynote <file>
 ```
 
 This produces `scripts/{basename}/mulmo_script.json` and (for PDF) `scripts/{basename}/extracted_texts.json`.
@@ -44,11 +52,12 @@ Confirm the output:
 
 ### Step 2: Read Inputs
 
-1. Read the generated `scripts/{basename}/mulmo_script.json`
-2. Read the ExtendedScript schema: `.claude/skills/narrate/references/extended-script-schema.md`
-3. Check for `scripts/{basename}/extracted_texts.json` (generated by PDF converter)
-   - If found, read it — this provides raw text content for each beat
-4. If the source is Markdown, also read the original `.md` file for speaker notes and structure
+Use the Read tool (not bash/node commands) to read the following files:
+
+1. `scripts/{basename}/mulmo_script.json`
+2. `.claude/skills/narrate/references/extended-script-schema.md`
+3. `scripts/{basename}/extracted_texts.json` (if it exists, generated by PDF converter — provides raw text per beat)
+4. The original source `.md` file (if Markdown, for speaker notes and structure)
 
 ### Step 3: Analyze Content
 
@@ -103,7 +112,7 @@ Based on the analysis, generate:
 
 Run validation:
 ```bash
-yarn cli extend validate scripts/{basename}/extended_script.json
+{cli} extend validate scripts/{basename}/extended_script.json
 ```
 
 If validation fails, fix the errors and re-write the file. Repeat until validation passes.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mulmocast/slide",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "Convert presentations (Keynote, PowerPoint, PDF, Marp) and videos to MulmoScript format",
   "homepage": "https://github.com/receptron/MulmoCast-Slides#readme",
   "bugs": {