officecli-docx

Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments, headers/footers, or tables of contents. Trigger whenever the user mentions 'Word doc', 'document', 'report', 'letter', 'memo', or references a .docx filename.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%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.

An exceptionally actionable skill body with a model workflow (build → QA → delivery gate) and deep, verified CLI-specific knowledge. Its weaknesses are length and structure: heavy repetition of the same hard rules across sections and a monolithic single-file layout that inlines what should be separate reference files.

Suggestions

Split reference-grade material into one-level-deep bundle files (e.g. references/recipes.md, references/known-issues.md, references/cli-bugs.md) and keep SKILL.md as an overview with clearly signaled pointers, per the progressive_disclosure rationale.

Deduplicate the rules stated three times each (footer --prop field=page, differentFirstPage, TOC pagenumbers, page-break belt-and-suspenders) into the single 'Hard rules' or 'Known Issues' location and cross-reference it from the other sections.

Tighten the narrative sections (Smart quotes, TOC delivery step, Fresh eyes, Honest limit) to compress the ~57KB body toward a leaner core that respects the token budget.

Dimension	Reasoning	Score
Conciseness	Mostly high-value CLI-specific knowledge Claude cannot know (bug IDs, prop whitelists, quoting traps), but at ~57KB it is noticeably padded: at least four rules (footer field=page, differentFirstPage, TOC pagenumbers, page-break belt-and-suspenders) are each repeated verbatim in three separate sections, and prose sections like 'Fresh eyes' and 'Honest limit' could be tightened.	3 / 5
Actionability	Every section ships executable, copy-paste-ready commands — the Quick Start, recipes (a)-(f), and a complete Delivery Gate bash block with explicit REJECT/exit semantics; pattern placeholders like '/body/p[N]' and '--index <pos>' are explicitly framed as adaptable patterns, not gaps.	5 / 5
Workflow Clarity	The six-step Common Workflow, QA 'Minimum cycle' checklist, explicit fix-then-rerun feedback loop ('One fix commonly creates another problem'), and the gated REJECT path before delivery together match the anchor-5 example: clear sequence, explicit validation steps, feedback loops, and checklists.	5 / 5
Progressive Disclosure	No bundle files exist and reference-grade material (report recipes, CLI bug backlog, Known Issues tables) is inlined in a single 660-line file — content that clearly belongs in separate files — but section headers, 'skip if you are writing a report' scoping, and in-file navigation are genuinely good, placing it above the anchor-2 'no structure' example and between anchors 2 and 3.	3 / 5
	Total	16 / 20 Passed

Description

96%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.

A strong description that explicitly states both capabilities and trigger conditions with concrete, natural user phrasings and the .docx extension. The only weakness is over-broad triggers ('document', 'report') that create minor conflict risk with the sibling docx skills the body itself references.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions across the full lifecycle — 'creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments, headers/footers, or tables of contents' — comprehensive coverage beyond the anchor-4 example's three actions.	5 / 5
Completeness	Explicitly answers both what ('This includes: creating... reading, parsing, or extracting... editing, modifying...') and when ('Use this skill any time a .docx file is involved', 'Trigger whenever the user mentions...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural user phrasings ('Word doc', 'document', 'report', 'letter', 'memo') plus the file extension ('references a .docx filename'), matching the anchor-5 pattern of synonyms plus extension; no common variation is obviously missing.	5 / 5
Distinctiveness Conflict Risk	The .docx pin gives it a clear niche, but the very broad trigger terms 'document' and 'report' could fire on non-docx documents, and the body itself defines sibling docx skills (academic-paper, word-form) that overlap the 'any time a .docx file is involved' claim — minor overlap risk with closely related skills.	4 / 5
	Total	19 / 20 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
skill_md_line_count	SKILL.md is long (662 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Team-Commonly/commonly
Path: backend/commonly-bundled-skills/officecli/skills/officecli-docx/SKILL.md
Commit: 5bd4f1a

Reviewed: 7 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.