Skip to content

FISCFED9/CLI / .agents/skills/docx-processing-lawvable

Word Editor

Verified

Edit, query, and transform Word documents (.docx) with the SuperDoc CLI. Use when the user asks to read, search, modify, format, comment, track changes, or review changes in .docx files. Triggers on any task involving Word documents — text replacement, redlining, contract markup, template filling, bulk edits, content extraction, or document review.

FileKindSize
LICENSE.txtmarkdown33.7 KB
SKILL.mdskill md5.6 KB
references/bookmarks-footnotes.mdmarkdown2.2 KB
references/citations.mdmarkdown2.6 KB
references/comments.mdmarkdown2.6 KB
references/content-controls.mdmarkdown6.2 KB
references/create.mdmarkdown2.6 KB
references/diff.mdmarkdown2.0 KB
references/format.mdmarkdown7.3 KB
references/headers-footers.mdmarkdown1.4 KB
references/hyperlinks.mdmarkdown2.1 KB
references/images.mdmarkdown2.6 KB
references/index.mdmarkdown6.0 KB
references/lists.mdmarkdown4.3 KB
references/mutations-apply.mdmarkdown6.4 KB
references/mutations.mdmarkdown4.8 KB
references/protection.mdmarkdown849 B
references/reading.mdmarkdown5.2 KB
references/sections.mdmarkdown1.8 KB
references/session.mdmarkdown2.7 KB
references/tables.mdmarkdown7.2 KB
references/toc.mdmarkdown2.3 KB
references/track-changes.mdmarkdown1.8 KB

references/reading.md

View on GitHub
# Core Reading Commands

### get-text

Extract the plain-text content of the document.

```bash
superdoc get-text <doc> 2>/dev/null
superdoc get-text 2>/dev/null                # with active session
```

| Flag | Type | Description |
|------|------|-------------|
| `<doc>` | string | Path to .docx (stateless mode) |
| `--session` | string | Session ID |
| `--in-json` | JSON | Story scope (body, header/footer, footnote, endnote) |

### get-markdown

Extract the document content as a Markdown string.

```bash
superdoc get-markdown <doc> 2>/dev/null
superdoc get-markdown 2>/dev/null            # with active session
```

| Flag | Type | Description |
|------|------|-------------|
| `<doc>` | string | Path to .docx (stateless mode) |
| `--session` | string | Session ID |
| `--in-json` | JSON | Story scope |

### get-html

Extract the document content as an HTML string.

```bash
superdoc get-html <doc> 2>/dev/null
```

| Flag | Type | Description |
|------|------|-------------|
| `<doc>` | string | Path to .docx (stateless mode) |
| `--session` | string | Session ID |
| `--in-json` | JSON | Story scope |

### info

Return document summary info including word, character, paragraph, heading, table, image, comment, tracked-change, SDT-field, list, and page counts, plus outline and capabilities.

```bash
superdoc info <doc> 2>/dev/null
superdoc info 2>/dev/null                    # with active session
```

| Flag | Type | Description |
|------|------|-------------|
| `<doc>` | string | Path to .docx (stateless mode) |
| `--session` | string | Session ID |

### find

Search the document for text or node matches using SDM/1 selectors. Returns discovery-grade results. **For mutation targeting, use `query match` instead.**

```bash
superdoc find --select-json '<selector>' [flags] 2>/dev/null
```

| Flag | Type | Description |
|------|------|-------------|
| `--select-json` | JSON | Selector: `{"type":"text","pattern":"..."}` or `{"type":"node","nodeType":"paragraph"}` |
| `--within-json` | JSON | Scope to a block: `{"kind":"block","nodeType":"paragraph","nodeId":"..."}` |
| `--limit` | number | Max results |
| `--offset` | number | Skip first N results |
| `--in-json` | JSON | Story scope |
| `--options-json` | JSON | `{"includeResolved":bool, "includeProvenance":bool, "includeContext":bool}` |
| `--pattern` | string | Flat flag alternative for text pattern |
| `--type` | string | Flat flag: `text` or `node` |
| `--node-type` | string | Flat flag for node type |
| `--mode` | string | `contains` (default) or `regex` |
| `--case-sensitive` | boolean | Case-sensitive matching |

### query match

Deterministic selector-based search returning mutation-grade addresses and text ranges. **Always use this instead of `find` when preparing mutations.**

```bash
superdoc query match --select-json '<selector>' --require <cardinality> [flags] 2>/dev/null
```

| Flag | Type | Required | Description |
|------|------|----------|-------------|
| `--select-json` | JSON | yes | `{"type":"text","pattern":"..."}` or `{"type":"node","nodeType":"paragraph"}` |
| `--require` | string | no | `any`, `first`, `exactlyOne`, `all` |
| `--within-json` | JSON | no | Scope: `{"kind":"block","nodeType":"paragraph","nodeId":"..."}` |
| `--mode` | string | no | `strict` (default) or `candidates` (scored fuzzy matches) |
| `--limit` | number | no | Max results |
| `--offset` | number | no | Skip first N |
| `--include-nodes` | boolean | no | Include full node data in results |
| `--in-json` | JSON | no | Story scope |

**Select types:**

| Type | Description | Example |
|------|-------------|---------|
| Text (substring) | Case-insensitive substring match | `{"type":"text","pattern":"Introduction"}` |
| Text (regex) | Regular expression match | `{"type":"text","pattern":"Section \\d+","mode":"regex"}` |
| Text (case-sensitive) | Exact case matching | `{"type":"text","pattern":"ACME","caseSensitive":true}` |
| Node (block) | Match by block node type | `{"type":"node","nodeType":"paragraph"}` |
| Node (inline) | Match by inline node type | `{"type":"node","nodeType":"hyperlink","kind":"inline"}` |

**Require cardinalities:**

| Value | Behavior |
|-------|----------|
| `any` | Return all matches (no failure) |
| `first` | Return only the first match |
| `exactlyOne` | Fail if count != 1 |
| `all` | Return all matches, fail if 0 |

**Response shape** -- each match includes `.target` (SelectionTarget) and `.handle.ref` (ref string), both usable directly in `replace`, `delete`, `format apply`, or `mutations apply` steps.

### get-node

Retrieve a single node by target position.

```bash
superdoc get-node --target-json '<target>' 2>/dev/null
```

### get-node-by-id

Retrieve a single node by its unique ID.

```bash
superdoc get-node-by-id --id <nodeId> 2>/dev/null
```

### blocks list

List top-level blocks in document order with IDs, types, and text previews. Supports pagination.

```bash
superdoc blocks list [flags] 2>/dev/null
```

| Flag | Type | Description |
|------|------|-------------|
| `--offset` | number | Skip first N blocks |
| `--limit` | number | Max blocks to return |
| `--node-types-json` | JSON array | Filter: `["paragraph","heading"]` |
| `--session` | string | Session ID |

Valid node types for filtering: `paragraph`, `heading`, `listItem`, `table`, `tableRow`, `tableCell`, `tableOfContents`, `image`, `sdt`.
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 197kUpdated Claude CodeCodexVerifiedInstall