{"id":"76174c70-bcd2-476c-8bc2-74b37e1d244a","entityType":"agent","slug":"clawhub-ivangdavila-word-docx-2","name":"Word / DOCX","canonicalUrl":"https://www.xpersona.co/agent/clawhub-ivangdavila-word-docx-2","canonicalPath":"/agent/clawhub-ivangdavila-word-docx-2","generatedAt":"2026-10-10T06:23:02.109Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-05-22T06:55:50.818Z","emptyReason":null},"description":"Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check... Skill: Word / DOCX Owner: ivangdavila Summary: Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check... Tags: latest:1.0.2 Version history: v1.0.2 | 2026-03-11T15:31:36.816Z | user Tightened the skill around fragile review workflows, reference stability, and layout drift after a stricter external audit. v1.0.1 | 20","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 76.1K downloads reported by the source. Last updated 5/22/2026.","installCommand":"clawhub skill install s178jdk12x4qj3gs2se3etxf3h83h7ft:word-docx","sourceUrl":"https://clawhub.ai/ivangdavila/word-docx","homepage":"https://clawhub.ai/ivangdavila/word-docx","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/ivangdavila/word-docx","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":97,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-05-22T06:55:50.818Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-05-22T06:55:50.818Z","emptyReason":null},"stars":null,"forks":null,"downloads":76052,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"76.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-05-22T06:55:50.803Z","emptyReason":null},"lastUpdatedAt":"2026-05-22T06:55:50.818Z","lastCrawledAt":"2026-05-22T06:55:50.803Z","lastIndexedAt":null,"nextCrawlAt":"2026-05-23T06:55:50.803Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-03-11T15:31:36.816Z","changelog":"Tightened the skill around fragile review workflows, reference stability, and layout drift after a stricter external audit.","fileCount":2,"zipByteSize":3676},{"version":"1.0.1","createdAt":"2026-03-09T09:28:39.521Z","changelog":"Clarified the skill name and added a page layout compatibility note.","fileCount":2,"zipByteSize":1998},{"version":"1.0.0","createdAt":"2026-02-10T01:23:30.173Z","changelog":"Initial release","fileCount":2,"zipByteSize":1886}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s178jdk12x4qj3gs2se3etxf3h83h7ft:word-docx","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T06:23:02.109Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ivangdavila-word-docx-2/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-05-22T06:55:50.818Z","emptyReason":null},"readme":"Skill: Word / DOCX\n\nOwner: ivangdavila\n\nSummary: Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check...\n\nTags: latest:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-03-11T15:31:36.816Z | user\n\nTightened the skill around fragile review workflows, reference stability, and layout drift after a stricter external audit.\n\nv1.0.1 | 2026-03-09T09:28:39.521Z | user\n\nClarified the skill name and added a page layout compatibility note.\n\nv1.0.0 | 2026-02-10T01:23:30.173Z | user\n\nInitial release\n\nArchive index:\n\nArchive v1.0.2: 2 files, 3676 bytes\n\nFiles: SKILL.md (7887b), _meta.json (128b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: Word / DOCX\nslug: word-docx\nversion: 1.0.2\nhomepage: https://clawic.com/skills/word-docx\ndescription: \"Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility checks. Use when (1) the task is about Word or `.docx`; (2) the file includes tracked changes, comments, fields, tables, templates, or page layout constraints; (3) the document must survive round-trip editing without formatting drift.\"\nchangelog: Tightened the skill around fragile review workflows, reference stability, and layout drift after a stricter external audit.\nmetadata: {\"clawdbot\":{\"emoji\":\"📘\",\"os\":[\"linux\",\"darwin\",\"win32\"]}}\n---\n\n## When to Use\n\nUse when the main artifact is a Microsoft Word document or `.docx` file, especially when tracked changes, comments, headers, numbering, fields, tables, templates, or compatibility matter.\n\n## Core Rules\n\n### 1. Treat DOCX as OOXML, not plain text\n\n- A `.docx` file is a ZIP of XML parts, so structure matters as much as visible text.\n- The critical parts are usually `word/document.xml`, `styles.xml`, `numbering.xml`, headers, footers, and relationship files.\n- Text may be split across multiple runs; never assume one word or sentence lives in one XML node.\n- Use different workflows on purpose: structured extraction for quick reading, style-driven generation for new files, and OOXML-aware editing for fragile existing documents.\n- If the job is mainly reading, extracting, or reviewing, prefer a structure-preserving read path before touching OOXML.\n- For deep edits, inspect the package layout instead of relying only on rendered output.\n- Reading, generating, and preserving an existing reviewed document are different jobs even when the format is the same.\n- Legacy `.doc` inputs usually need conversion before you can trust modern `.docx` assumptions.\n\n### 2. Preserve styles and direct formatting deliberately\n\n- Prefer named styles over direct formatting so the document stays editable.\n- Styles layer: paragraph styles, character styles, and direct formatting do not behave the same.\n- Removing direct formatting is often safer than stacking more inline formatting on top.\n- When editing an existing file, extend the current style system instead of inventing a parallel one.\n- Copying content between documents can silently import foreign styles, theme settings, and numbering definitions.\n\n### 3. Lists and numbering are their own system\n\n- Bullets and numbering belong to Word's numbering definitions, not pasted Unicode characters.\n- `abstractNum`, `num`, and paragraph numbering properties all matter, so restart behavior is rarely \"visual only\".\n- Indentation and numbering are related but not identical; a list can have broken numbering even if the indent looks right.\n- A list that looks correct in one editor can restart, flatten, or renumber itself later if the underlying numbering state is wrong.\n\n### 4. Page layout lives in sections\n\n- Margins, orientation, headers, footers, and page numbering are section-level behavior.\n- First-page and odd/even headers can differ inside the same document, so one header fix may not fix the document.\n- Set page size explicitly because A4 and US Letter defaults change pagination and table widths.\n- Use section breaks for layout changes; manual spacing and stray page breaks usually create drift.\n- Header and footer media use part-specific relationships, so copied IDs often break images or links.\n- Tables, page breaks, and headers often drift together, so treat layout fixes as document-wide, not local cosmetic edits.\n- Table geometry depends on page width, margins, and fixed widths, so \"close enough\" table edits often break later in Google Docs or LibreOffice.\n\n### 5. Track changes, comments, and fields need precise edits\n\n- Visible text is not the full document when tracked changes are enabled.\n- Insertions, deletions, and comments carry metadata that can survive careless edits.\n- Deleted text may still exist in the XML even when it no longer appears on screen.\n- Comment anchors and review ranges can break if edits move text without preserving the surrounding structure.\n- Comment markers and review wrappers do not behave like inline formatting, so moving text carelessly can orphan or misplace them.\n- Comments, footnotes, bookmarks, and linked media may live in separate parts, not only in the main document body.\n- Tables of contents, page numbers, dates, cross-references, and mail merge placeholders are fields.\n- Edit the field source carefully and expect cached display values to lag until refresh.\n- Hyperlinks, bookmarks, and references can break if IDs or relationships stop matching.\n- Bookmarks, footnotes, comment ranges, and cross-references depend on stable anchors even when the visible text seems untouched.\n- A document can look correct while still containing stale field output that refreshes later into something different.\n- For review workflows, make minimal replacements instead of rewriting whole paragraphs.\n- In tracked-change workflows, only the changed span should look changed; broad rewrites create noisy reviews and can destroy the original formatting context.\n- For legal, academic, or business review documents, default to review-style edits over wholesale paragraph rewrites unless the user explicitly wants a rewrite.\n\n### 6. Verify round-trip compatibility before delivery\n\n- Complex documents can shift between Word, LibreOffice, Google Docs, and conversion tools.\n- Tables, headers, embedded fonts, and copied styles are common sources of layout drift.\n- Treat `.docm` as macro-bearing and higher risk; treat `.doc` as legacy input that may need conversion first.\n- When layout matters, explicit table widths are safer than auto-fit or percentage-style behavior that different editors reinterpret.\n- A document that passes a text check can still fail on pagination, table widths, or reference refresh after the recipient opens it.\n\n## Common Traps\n\n- Copy-paste can import unwanted styles and numbering definitions.\n- Header or footer images use part-specific relationships, so reusing IDs blindly breaks them.\n- Empty paragraphs used as spacing make templates fragile; spacing belongs in paragraph settings.\n- A clean-looking export can still hide unresolved revisions, comments, or stale field values.\n- Restarting lists \"by eye\" usually fails because numbering state lives outside the paragraph text.\n- One visible phrase can be split across several runs, bookmarks, revision tags, or field boundaries.\n- Replacing a whole paragraph to change one clause often breaks review quality, bookmarks, comments, or nearby inline formatting.\n- Deleting all visible text from a paragraph or list item can still leave behind an empty paragraph mark, empty bullet, or unstable numbering.\n- Table auto-fit and percentage-like width behavior can look acceptable in Word and still drift in Google Docs or LibreOffice.\n- LibreOffice and Google Docs can shift complex tables, section behavior, and embedded fonts even when Word looks perfect.\n- Compatibility mode can silently cap newer features or change pagination behavior.\n- A single change in page size or margin defaults can ripple through tables, headers, TOC, and cross-references.\n- A revision workflow can look accepted on screen while leftover metadata, comments, or field caches still make the file unstable later.\n- TOC entries, footnotes, and cross-references can look correct until the recipient updates fields and exposes broken anchors.\n\n## Related Skills\nInstall with `clawhub install <slug>` if user confirms:\n- `documents` — General document handling and format conversion.\n- `brief` — Concise business writing and structured summaries.\n- `article` — Long-form drafting and editorial structure.\n\n## Feedback\n\n- If useful: `clawhub star word-docx`\n- Stay updated: `clawhub sync`\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn73vp5rarc3b14rc7wjcw8f8580t5d1\",\n  \"slug\": \"word-docx\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1773243096816\n}\n\nArchive v1.0.1: 2 files, 1998 bytes\n\nFiles: SKILL.md (3277b), _meta.json (128b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: Word / Docx\nversion: 1.0.1\ndescription: Read and generate Word documents with correct structure, styles, and cross-platform compatibility.\nchangelog: Clarified the skill name and added a page layout compatibility note.\nmetadata: {\"clawdbot\":{\"emoji\":\"📘\",\"os\":[\"linux\",\"darwin\",\"win32\"]}}\n---\n\n## Structure\n\n- DOCX is a ZIP containing XML files—`word/document.xml` has main content, `word/styles.xml` has styles\n- Text splits into runs (`<w:r>`)—each run has uniform formatting; one word may span multiple runs\n- Paragraphs (`<w:p>`) contain runs—never assume one paragraph = one text block\n- Sections control page layout—headers/footers, margins, orientation are per-section\n\n## Styles vs Direct Formatting\n\n- Styles (Heading 1, Normal) are named and reusable—direct formatting is inline and overrides style\n- Removing direct formatting reveals underlying style—useful for cleanup\n- Character styles apply to runs, paragraph styles to paragraphs—they layer together\n- Linked styles can be both—applying to paragraph or selected text behaves differently\n\n## Lists & Numbering\n\n- Numbering is complex: `abstractNum` defines pattern, `num` references it, paragraphs reference `numId`\n- Restart numbering not automatic—need explicit `<w:numPr>` with restart flag\n- Bullets and numbers share the numbering system—both use `numId`\n- Indentation controlled separately from numbering—list can exist without visual indent\n\n## Headers, Footers, Sections\n\n- Each section can have different headers/footers—first page, odd, even pages\n- Section breaks: next page, continuous, even/odd page—affects pagination\n- Headers/footers stored in separate XML files—referenced by section properties\n- Page numbers are fields, not static text—update on open or print\n\n## Track Changes & Comments\n\n- Track changes stores original and revised in same document—accept/reject to finalize\n- Deleted text still present with `<w:del>` wrapper—don't assume visible = all content\n- Comments reference ranges via bookmark IDs—`<w:commentRangeStart>` to `<w:commentRangeEnd>`\n- Revision IDs track who changed what—metadata persists even after accepting\n\n## Fields & Dynamic Content\n\n- Fields have code and cached result—`{ DATE \\@ \"yyyy-MM-dd\" }` vs displayed date\n- TOC, page numbers, cross-references are fields—update fields to refresh\n- Hyperlinks can be fields or direct `<w:hyperlink>`—both valid\n- MERGEFIELD for mail merge—placeholder until merge executes\n\n## Compatibility\n\n- Compatibility mode limits features to earlier Word version—check `w:compat` settings\n- Page size defaults vary by tool and region—set US Letter vs A4 explicitly or pagination and table widths can drift\n- LibreOffice/Google Docs: complex formatting may shift—test roundtrip\n- Embedded fonts may not transfer—fallback fonts substitute\n- DOCM contains macros (security risk); DOC is legacy binary format\n\n## Common Pitfalls\n\n- Empty paragraphs for spacing—prefer space before/after in paragraph style\n- Manual page breaks inside paragraphs—use section breaks for layout control\n- Images in headers: relationship IDs are per-part—same image needs separate relationship in header\n- Copy-paste brings source styles—can pollute style gallery with duplicates\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn73vp5rarc3b14rc7wjcw8f8580t5d1\",\n  \"slug\": \"word-docx\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1773048519521\n}\n\nArchive v1.0.0: 2 files, 1886 bytes\n\nFiles: SKILL.md (3056b), _meta.json (128b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: DOCX\ndescription: Read and generate Word documents with correct structure, styles, and cross-platform compatibility.\nmetadata: {\"clawdbot\":{\"emoji\":\"📘\",\"os\":[\"linux\",\"darwin\",\"win32\"]}}\n---\n\n## Structure\n\n- DOCX is a ZIP containing XML files—`word/document.xml` has main content, `word/styles.xml` has styles\n- Text splits into runs (`<w:r>`)—each run has uniform formatting; one word may span multiple runs\n- Paragraphs (`<w:p>`) contain runs—never assume one paragraph = one text block\n- Sections control page layout—headers/footers, margins, orientation are per-section\n\n## Styles vs Direct Formatting\n\n- Styles (Heading 1, Normal) are named and reusable—direct formatting is inline and overrides style\n- Removing direct formatting reveals underlying style—useful for cleanup\n- Character styles apply to runs, paragraph styles to paragraphs—they layer together\n- Linked styles can be both—applying to paragraph or selected text behaves differently\n\n## Lists & Numbering\n\n- Numbering is complex: `abstractNum` defines pattern, `num` references it, paragraphs reference `numId`\n- Restart numbering not automatic—need explicit `<w:numPr>` with restart flag\n- Bullets and numbers share the numbering system—both use `numId`\n- Indentation controlled separately from numbering—list can exist without visual indent\n\n## Headers, Footers, Sections\n\n- Each section can have different headers/footers—first page, odd, even pages\n- Section breaks: next page, continuous, even/odd page—affects pagination\n- Headers/footers stored in separate XML files—referenced by section properties\n- Page numbers are fields, not static text—update on open or print\n\n## Track Changes & Comments\n\n- Track changes stores original and revised in same document—accept/reject to finalize\n- Deleted text still present with `<w:del>` wrapper—don't assume visible = all content\n- Comments reference ranges via bookmark IDs—`<w:commentRangeStart>` to `<w:commentRangeEnd>`\n- Revision IDs track who changed what—metadata persists even after accepting\n\n## Fields & Dynamic Content\n\n- Fields have code and cached result—`{ DATE \\@ \"yyyy-MM-dd\" }` vs displayed date\n- TOC, page numbers, cross-references are fields—update fields to refresh\n- Hyperlinks can be fields or direct `<w:hyperlink>`—both valid\n- MERGEFIELD for mail merge—placeholder until merge executes\n\n## Compatibility\n\n- Compatibility mode limits features to earlier Word version—check `w:compat` settings\n- LibreOffice/Google Docs: complex formatting may shift—test roundtrip\n- Embedded fonts may not transfer—fallback fonts substitute\n- DOCM contains macros (security risk); DOC is legacy binary format\n\n## Common Pitfalls\n\n- Empty paragraphs for spacing—prefer space before/after in paragraph style\n- Manual page breaks inside paragraphs—use section breaks for layout control\n- Images in headers: relationship IDs are per-part—same image needs separate relationship in header\n- Copy-paste brings source styles—can pollute style gallery with duplicates\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn73vp5rarc3b14rc7wjcw8f8580t5d1\",\n  \"slug\": \"word-docx\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770686610173\n}","readmeExcerpt":"Skill: Word / DOCX Owner: ivangdavila Summary: Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check... Tags: latest:1.0.2 Version history: v1.0.2 | 2026-03-11T15:31:36.816Z | user Tightened the skill around fragile review workflows, reference stability, and layout drift after a stricter external audit. v1.0.1 | 20","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: Word / DOCX\nslug: word-docx\nversion: 1.0.2\nhomepage: https://clawic.com/skills/word-docx\ndescription: \"Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility checks. Use when (1) the task is about Word or `.docx`; (2) the file includes tracked changes, comments, fields, tables, templates, or page layout constraints; (3) the document must survive round-trip editing without formatting drift.\"\nchangelog: Tightened the skill around fragile review workflows, reference stability, and layout drift after a stricter external audit.\nmetadata: {\"clawdbot\":{\"emoji\":\"📘\",\"os\":[\"linux\",\"darwin\",\"win32\"]}}\n---\n\n## When to Use\n\nUse when the main artifact is a Microsoft Word document or `.docx` file, especially when tracked changes, comments, headers, numbering, fields, tables, templates, or compatibility matter.\n\n## Core Rules\n\n### 1. Treat DOCX as OOXML, not plain text\n\n- A `.docx` file is a ZIP of XML parts, so structure matters as much as visible text.\n- The critical parts are usually `word/document.xml`, `styles.xml`, `numbering.xml`, headers, footers, and relationship files.\n- Text may be split across multiple runs; never assume one word or sentence lives in one XML node.\n- Use different workflows on purpose: structured extraction for quick reading, style-driven generation for new files, and OOXML-aware editing for fragile existing documents.\n- If the job is mainly reading, extracting, or reviewing, prefer a structure-preserving read path before touching OOXML.\n- For deep edits, inspect the package layout instead of relying only on rendered output.\n- Reading, generating, and preserving an existing reviewed document are different jobs even when the format is the same.\n- Legacy `.doc` inputs usually need conversion before you can trust modern `.docx` assumptions.\n\n### 2. Preserve styles and direct formatting deliberately\n\n- Prefer named styles over direct formatting so the document stays editable.\n- Styles layer: paragraph styles, character styles, and direct formatting do not behave the same.\n- Removing direct formatting is often safer than stacking more inline formatting on top.\n- When editing an existing file, extend the current style system instead of inventing a parallel one.\n- Copying content between documents can silently import foreign styles, theme settings, and numbering definitions.\n\n### 3. Lists and numbering are their own system\n\n- Bullets and numbering belong to Word's numbering definitions, not pasted Unicode characters.\n- `abstractNum`, `num`, and paragraph numbering properties all matter, so restart behavior is rarely \"visual only\".\n- Indentation and numbering are related but not identical; a list can have broken numbering even if the indent looks right.\n- A list that looks correct in one editor can restart, flatten, or renumber itself later if the underlying numbering state is wrong.\n\n### 4. Page layout lives in sections\n\n- Margins, ori"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn73vp5rarc3b14rc7wjcw8f8580t5d1\",\n  \"slug\": \"word-docx\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1773243096816\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check... Skill: Word / DOCX Owner: ivangdavila Summary: Create, inspect, and edit Microsoft Word documents and DOCX files with reliable styles, numbering, tracked changes, tables, sections, and compatibility check... Tags: latest:1.0.2 Version history: v1.0.2 | 2026-03-11T15:31:36.816Z | user Tightened the skill around fragile review workflows, reference stability, and layout drift after a stricter external audit. v1.0.1 | 20","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":837,"uniquenessScore":56,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-05-22T06:55:50.818Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-05-22T06:55:50.818Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T06:23:02.109Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}