--- name: export description: Convert thesis chapters and reading notes from Markdown to Word (.docx) and package for submission. Use when preparing materials for supervisors or examiners. disable-model-invocation: true allowed-tools: Bash(python *), Read, Glob, Write ---

# /export — Document Export Skill

## Purpose

Convert thesis chapters and reading notes from Markdown to Word (.docx) format and package them into a ZIP archive for submission to supervisors or examiners. This skill is user-invoked only and will not be triggered automatically.

## Trigger Words

This skill activates on: `/export`. It is never invoked automatically by the model.

## Parameters

- `$ARGUMENTS[0]` -- **scope**: `chapters` | `notes` | `all` (default: `all`) - `$ARGUMENTS[1]` -- **language filter**: `en-only` | `all` (default: `all`)

Examples: - `/export chapters en-only` -- export only chapter files, skip files with significant CJK content - `/export notes all` -- export only reading notes, include all languages - `/export` -- export everything, all languages

## Workflow

0. **Resolve every source first (Advisory here; Enforced in the AWT app).** Before converting, confirm that every author-year citation in `chapters/` has a lint-conforming notes file under `literature/reading_notes/`, and that `references.bib` (when present) neither contains entries nothing cites nor lacks an entry a chapter cites:

``` python3 scripts/audit-claim-positioning.py --base-dir chapters --bib references.bib --json ```

Stop and report if anything is unresolved. On this surface nothing blocks you from exporting anyway — say so if you do. In the AWT app the same condition is a typed denial (`EXPORT_SOURCES_UNRESOLVED`) on the `export_docx` tool, and the export does not run.

1. **Check dependencies.** Verify that `pypandoc` is installed AND a working `pandoc` binary is on PATH (the script smoke-probes via `pypandoc.get_pandoc_version()`). If pypandoc/pandoc are unavailable, fall back to `python-docx` + `markdown`. Report which conversion method is being used.

**Run from the project root.**

2. **Run the conversion script.** ``` python .claude/skills/export/scripts/convert_to_docx.py \ --base-dir {project_root} \ --output-dir {project_root}/final_output \ --scope {scope} \ --lang-filter {lang_filter} ```

3. **Report results.** ``` ## Export Complete

| Item | Value | |------|-------| | Files converted | {N} | | Files skipped (language filter) | {N} | | Output directory | {path} | | ZIP archive | {path} | | Total size | {size} |

Conversion method: {pandoc | python-docx fallback} ```

## Constraints

1. **User-invoked only.** This skill has `disable-model-invocation: true` and must not run unless the user explicitly calls `/export`. 2. **No hardcoded paths.** All paths are derived from arguments or project root. 3. **No emoji** in output. 4. **Preserve formatting** as much as possible during conversion -- headings, tables, block quotes, inline code.

--- name: export description: Convert thesis chapters and reading notes from Markdown to Word (.docx) and package for submission. Use when preparing materials for supervisors or examiners. disable-model-invocation: true allowed-tools: Bash(python *), Read, Glob, Write ---

# /export — Document Export Skill

## Purpose

Convert thesis chapters and reading notes from Markdown to Word (.docx) format and package them into a ZIP archive for submission to supervisors or examiners. This skill is user-invoked only and will not be triggered automatically.

## Trigger Words

This skill activates on: `/export`. It is never invoked automatically by the model.

## Parameters

- `$ARGUMENTS[0]` -- **scope**: `chapters` | `notes` | `all` (default: `all`) - `$ARGUMENTS[1]` -- **language filter**: `en-only` | `all` (default: `all`)

Examples: - `/export chapters en-only` -- export only chapter files, skip files with significant CJK content - `/export notes all` -- export only reading notes, include all languages - `/export` -- export everything, all languages

## Workflow

0. **Resolve every source first (Advisory here; Enforced in the AWT app).** Before converting, confirm that every author-year citation in `chapters/` has a lint-conforming notes file under `literature/reading_notes/`, and that `references.bib` (when present) neither contains entries nothing cites nor lacks an entry a chapter cites:

``` python3 scripts/audit-claim-positioning.py --base-dir chapters --bib references.bib --json ```

Stop and report if anything is unresolved. On this surface nothing blocks you from exporting anyway — say so if you do. In the AWT app the same condition is a typed denial (`EXPORT_SOURCES_UNRESOLVED`) on the `export_docx` tool, and the export does not run.

1. **Check dependencies.** Verify that `pypandoc` is installed AND a working `pandoc` binary is on PATH (the script smoke-probes via `pypandoc.get_pandoc_version()`). If pypandoc/pandoc are unavailable, fall back to `python-docx` + `markdown`. Report which conversion method is being used.

**Run from the project root.**

2. **Run the conversion script.** ``` python .claude/skills/export/scripts/convert_to_docx.py \ --base-dir {project_root} \ --output-dir {project_root}/final_output \ --scope {scope} \ --lang-filter {lang_filter} ```

3. **Report results.** ``` ## Export Complete

| Item | Value | |------|-------| | Files converted | {N} | | Files skipped (language filter) | {N} | | Output directory | {path} | | ZIP archive | {path} | | Total size | {size} |

Conversion method: {pandoc | python-docx fallback} ```

## Constraints

1. **User-invoked only.** This skill has `disable-model-invocation: true` and must not run unless the user explicitly calls `/export`. 2. **No hardcoded paths.** All paths are derived from arguments or project root. 3. **No emoji** in output. 4. **Preserve formatting** as much as possible during conversion -- headings, tables, block quotes, inline code.

--- name: export description: Convert thesis chapters and reading notes from Markdown to Word (.docx) and package for submission. Use when preparing materials for supervisors or examiners. disable-model-invocation: true allowed-tools: Bash(python *), Read, Glob, Write ---

# /export — Document Export Skill

## Purpose

Convert thesis chapters and reading notes from Markdown to Word (.docx) format and package them into a ZIP archive for submission to supervisors or examiners. This skill is user-invoked only and will not be triggered automatically.

## Trigger Words

This skill activates on: `/export`. It is never invoked automatically by the model.

## Parameters

- `$ARGUMENTS[0]` -- **scope**: `chapters` | `notes` | `all` (default: `all`) - `$ARGUMENTS[1]` -- **language filter**: `en-only` | `all` (default: `all`)

Examples: - `/export chapters en-only` -- export only chapter files, skip files with significant CJK content - `/export notes all` -- export only reading notes, include all languages - `/export` -- export everything, all languages

## Workflow

0. **Resolve every source first (Advisory here; Enforced in the AWT app).** Before converting, confirm that every author-year citation in `chapters/` has a lint-conforming notes file under `literature/reading_notes/`, and that `references.bib` (when present) neither contains entries nothing cites nor lacks an entry a chapter cites:

``` python3 scripts/audit-claim-positioning.py --base-dir chapters --bib references.bib --json ```

Stop and report if anything is unresolved. On this surface nothing blocks you from exporting anyway — say so if you do. In the AWT app the same condition is a typed denial (`EXPORT_SOURCES_UNRESOLVED`) on the `export_docx` tool, and the export does not run.

1. **Check dependencies.** Verify that `pypandoc` is installed AND a working `pandoc` binary is on PATH (the script smoke-probes via `pypandoc.get_pandoc_version()`). If pypandoc/pandoc are unavailable, fall back to `python-docx` + `markdown`. Report which conversion method is being used.

**Run from the project root.**

2. **Run the conversion script.** ``` python .claude/skills/export/scripts/convert_to_docx.py \ --base-dir {project_root} \ --output-dir {project_root}/final_output \ --scope {scope} \ --lang-filter {lang_filter} ```

3. **Report results.** ``` ## Export Complete

| Item | Value | |------|-------| | Files converted | {N} | | Files skipped (language filter) | {N} | | Output directory | {path} | | ZIP archive | {path} | | Total size | {size} |

Conversion method: {pandoc | python-docx fallback} ```

## Constraints

1. **User-invoked only.** This skill has `disable-model-invocation: true` and must not run unless the user explicitly calls `/export`. 2. **No hardcoded paths.** All paths are derived from arguments or project root. 3. **No emoji** in output. 4. **Preserve formatting** as much as possible during conversion -- headings, tables, block quotes, inline code.

--- name: export description: Convert thesis chapters and reading notes from Markdown to Word (.docx) and package for submission. Use when preparing materials for supervisors or examiners. disable-model-invocation: true allowed-tools: Bash(python *), Read, Glob, Write ---

# /export — Document Export Skill

## Purpose

Convert thesis chapters and reading notes from Markdown to Word (.docx) format and package them into a ZIP archive for submission to supervisors or examiners. This skill is user-invoked only and will not be triggered automatically.

## Trigger Words

This skill activates on: `/export`. It is never invoked automatically by the model.

## Parameters

- `$ARGUMENTS[0]` -- **scope**: `chapters` | `notes` | `all` (default: `all`) - `$ARGUMENTS[1]` -- **language filter**: `en-only` | `all` (default: `all`)

Examples: - `/export chapters en-only` -- export only chapter files, skip files with significant CJK content - `/export notes all` -- export only reading notes, include all languages - `/export` -- export everything, all languages

## Workflow

0. **Resolve every source first (Advisory here; Enforced in the AWT app).** Before converting, confirm that every author-year citation in `chapters/` has a lint-conforming notes file under `literature/reading_notes/`, and that `references.bib` (when present) neither contains entries nothing cites nor lacks an entry a chapter cites:

``` python3 scripts/audit-claim-positioning.py --base-dir chapters --bib references.bib --json ```

Stop and report if anything is unresolved. On this surface nothing blocks you from exporting anyway — say so if you do. In the AWT app the same condition is a typed denial (`EXPORT_SOURCES_UNRESOLVED`) on the `export_docx` tool, and the export does not run.

1. **Check dependencies.** Verify that `pypandoc` is installed AND a working `pandoc` binary is on PATH (the script smoke-probes via `pypandoc.get_pandoc_version()`). If pypandoc/pandoc are unavailable, fall back to `python-docx` + `markdown`. Report which conversion method is being used.

**Run from the project root.**

2. **Run the conversion script.** ``` python .claude/skills/export/scripts/convert_to_docx.py \ --base-dir {project_root} \ --output-dir {project_root}/final_output \ --scope {scope} \ --lang-filter {lang_filter} ```

3. **Report results.** ``` ## Export Complete

| Item | Value | |------|-------| | Files converted | {N} | | Files skipped (language filter) | {N} | | Output directory | {path} | | ZIP archive | {path} | | Total size | {size} |

Conversion method: {pandoc | python-docx fallback} ```

## Constraints

1. **User-invoked only.** This skill has `disable-model-invocation: true` and must not run unless the user explicitly calls `/export`. 2. **No hardcoded paths.** All paths are derived from arguments or project root. 3. **No emoji** in output. 4. **Preserve formatting** as much as possible during conversion -- headings, tables, block quotes, inline code.