docx-official

Use this skill whenever a Microsoft Word (.docx) file is being produced, opened, transformed, or read. That includes: drafting reports, letters, contracts, RFPs, technical documents, or any long-form written deliverable; extracting text or structure from an existing Word file; filling a Word template with values; converting Word to PDF or plain text; splitting or merging documents; inspecting styles, headings, sections, tables, images, comments, or tracked changes. Trigger on mentions of 'Word doc', 'DOCX', 'Office document', a filename ending in .docx, or requests like 'turn this into a Word report'.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%

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

A strong, lean, highly actionable SKILL.md with explicit sequencing and a genuine validate→fix feedback loop in the QA checklist. The one weakness is progressive disclosure: the three headline detail files (create.md, edit.md, read.md) referenced by the body are absent from the bundle, so the disclosed navigation is partly broken.

Suggestions

Add the missing bundle files create.md, edit.md, and read.md that the decision matrix and 'Where each detail lives' section link to, so the one-level-deep navigation actually resolves.

If those details are intentionally folded into SKILL.md, replace the dangling [create.md]/[edit.md]/[read.md] links with the in-file section anchors they should point to.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what a .docx is or how python-docx works, instead giving a decision matrix, terse command snippets, and a tight QA checklist; every section earns its place rather than padding tokens.	3 / 3
Actionability	Fully executable guidance throughout: concrete `uv run scripts/...` commands, copy-paste QA snippets (e.g. the python-docx open test and the fake-heading grep), and a runnable typography table — matching the level-3 'copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear 'read → plan → edit/create → validate' sequence anchors the decision matrix, and the QA checklist is an explicit validate→fix→re-run feedback loop ('If any of these fail, fix and re-run — don't paper over'), meeting the level-3 anchor for explicit validation checkpoints on the fragile .docx operations the scoring notes flag.	3 / 3
Progressive Disclosure	The body cleanly points to one-level-deep references ([create.md], [edit.md], [read.md], [scripts/]) and an overview 'Where each detail lives' map, but those referenced files (create.md, edit.md, read.md) are NOT present in the bundle, so the disclosed structure is partially broken — one level deep but not fully realized.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 is specific, third-person, enumerates concrete capabilities, and pairs them with natural user trigger phrases and a clear 'Use when' clause. It is narrowly scoped to .docx, which keeps conflict risk low.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'drafting reports, letters, contracts, RFPs', 'extracting text or structure', 'filling a Word template', 'converting Word to PDF or plain text', 'splitting or merging', 'inspecting styles, headings, sections, tables, images, comments, tracked changes' — matching the level-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (produce/open/transform/read .docx files plus enumerated tasks) and 'when' ('Use this skill whenever...' with explicit trigger list), satisfying the level-3 anchor for clear what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Good coverage of natural user terms — 'Word doc', 'DOCX', 'Office document', '.docx', 'turn this into a Word report' — mirroring the level-3 example of natural phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to Microsoft Word .docx with distinct, file-extension-based triggers ('.docx', 'DOCX', 'Office document'), making it unlikely to fire for PDF, spreadsheet, or generic-document skills; matches the level-3 clear-niche anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 7 missing	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/docx-official/SKILL.md
Commit: ff87d47

Reviewed: about 13 hours 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.