docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', 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 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.

1.52x

Quality

94%

Does it follow best practices?

Impact

93%

1.52x

Average score across 8 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly actionable reference that earns its length: exact commands, complete code, explicit pitfalls, and a validated editing workflow with feedback loops. The only structural weakness is that the docx-js API cookbook and XML reference live entirely inline, and some rules are stated redundantly.

Suggestions

Consolidate the table-width guidance, which currently appears three times (Tables code comments, the 'Width rules' list, and the 'Critical Rules' recap), into one authoritative section to cut duplicate tokens.

Move the docx-js feature cookbook (Styles through Headers/Footers) or the XML Reference into a references/ file, keeping SKILL.md as an overview with clearly signaled one-level-deep links.

Trim duplicated CRITICAL annotations in code comments that restate the Critical Rules section verbatim (e.g., dual table widths and ShadingType.CLEAR appear in both).

Dimension	Reasoning	Score
Conciseness	Nearly every line carries non-obvious, high-value detail (DXA unit tables, CRITICAL pitfalls, smart-quote entity table, dual-width table rules) with no explanations of concepts Claude already knows. Not 5: table width guidance is repeated three times (Tables code comments, 'Width rules' list, and 'Critical Rules' recap), which could be consolidated; not 3: there is no padding or generic explanation.	4 / 5
Actionability	Fully executable copy-paste content: complete docx-js snippets (document setup, styles, numbering, tables, images, hyperlinks, footnotes, tab stops, columns, TOC, headers/footers), exact bash commands with flags, and exact unit conversions ('1440 DXA = 1 inch', '914400 EMU = 1 inch'). Not 4: the examples cover the common cases with concrete, runnable specifics throughout.	5 / 5
Workflow Clarity	The editing workflow is explicitly sequenced ('Follow all 3 steps in order': unpack → edit XML → pack) with a validation feedback loop — pack.py 'Validates with auto-repair' plus explicit auto-repair will/won't-fix lists — and the creation flow includes 'validate it. If validation fails, unpack, fix the XML, and repack'. Not 4: validation checkpoints and error-recovery loops are explicit, matching the top anchor for XML manipulation.	5 / 5
Progressive Disclosure	Good structure: Quick Reference table, clear section headers, and every referenced script path (scripts/office/soffice.py, unpack.py, pack.py, validate.py, scripts/accept_changes.py, scripts/comment.py) resolves to a real bundle file. Not 5: the ~200-line docx-js cookbook and the full XML reference are inlined in a single 590-line SKILL.md with no separate reference files for content that could be split out; not 3: navigation is easy, sections are well-organized, and the bundle is properly leveraged.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: it states capabilities concretely, enumerates natural trigger phrases and file extensions, and closes with explicit exclusion guidance. Everything stated is explicit with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'create, read, edit, or manipulate Word documents', 'extracting or reorganizing content', 'inserting or replacing images', 'performing find-and-replace', 'working with tracked changes or comments' — with comprehensive coverage. Not 4: there are no minor gaps; every core .docx capability is enumerated.	5 / 5
Completeness	Explicitly answers what ('create, read, edit, or manipulate Word documents (.docx files)') and when ('Triggers include...', 'Also use when...', 'If the user asks for a report, memo, letter...') with concrete trigger phrases. Not 4: the 'when' is fully explicit rather than merely present.	5 / 5
Trigger Term Quality	Covers natural terms users say ('Word doc', 'word document', 'report', 'memo', 'letter', 'template') plus the file extension '.docx'. Not 4: both everyday synonyms and extensions are present, matching the comprehensive anchor.	5 / 5
Distinctiveness Conflict Risk	Clear Word-document niche with explicit negative boundary: 'Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks'. Not 4: conflict risk is actively disambiguated against adjacent formats rather than just being low.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (591 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 7 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: tsinghua-fib-lab/AgentSociety
Path: extension/skills/docx/SKILL.md
Commit: 8cc5bb9

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.