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

81%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 with an excellent validated workflow and QA delivery gate, strong enough to score at the top on actionability and workflow clarity. Its weaknesses are token cost from triple-stated rules and a monolithic single-file structure that could offload some detail to bundle references or lean harder on the help layer.

Suggestions

Consolidate the page-break belt-and-suspenders rule, the shd.fill/ind.firstLine schema-invalid pitfall, and the footer fldChar verification into one canonical location each, replacing the duplicate mentions with brief cross-references to trim roughly 10-15% of tokens.

Move the report-level recipes (a-f) or the CLI bug backlog / Known Issues tables into a reference bundle file (e.g. references/recipes.md, references/known-issues.md) and link to them from SKILL.md to improve progressive disclosure and reduce the inline footprint.

Tighten the prose around the Mental Model and Shell & Execution Discipline sections, which mix rationale with instruction; keep the imperative rules and drop the explanatory framing Claude can infer.

Dimension	Reasoning	Score
Conciseness	The ~660-line body is mostly efficient and assumes Claude's intelligence, but several rules are restated three times (page-break belt-and-suspenders, the shd.fill/ind.firstLine pitfall, footer fldChar verification appear in recipes, dedicated sections, and the pitfalls table), adding token cost that could be tightened via a single canonical statement plus cross-references.	3 / 5
Actionability	Fully executable, copy-paste-ready officecli commands with concrete semantic paths and props throughout (Quick Start, Tables, Lists, Fields, Headers/Footers, recipes a-f), with specific examples covering the common cases and explicit 'Verified:' confirmations.	5 / 5
Workflow Clarity	The Common Workflow gives a clear six-step sequence with explicit checkpoints ('After each structural op, get it back to confirm'), and the QA section adds a minimum cycle plus a Delivery Gate (validate -> token-leak count -> live PAGE field check) with a fix-and-verify feedback loop, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Good section structure with a clearly signaled 'Advanced / specialty topics (skip if you are writing a report)' gate and a one-level-deep reference layer via 'officecli help docx ...' ('Help is the authoritative schema; this skill is the decision guide'), but all detail lives inline in a single 660-line file rather than being split into bundle reference files, so it falls short of the top anchor.	4 / 5
	Total	17 / 20 Passed

Description

95%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, comprehensive description that clearly states capabilities and trigger conditions with natural keyword coverage and a distinct .docx niche. Its only flaw is second-person imperative voice ('Use this skill'), which costs it one point on specificity per the rubric.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text... editing, modifying, or updating... templates, tracked changes, comments, headers/footers, or tables of contents'), which is comprehensive, but the opening 'Use this skill any time...' is second-person imperative voice, which the rubric penalizes by reducing specificity by one.	4 / 5
Completeness	Explicitly answers both what ('This includes: creating... reading, parsing, or extracting... editing, modifying, or updating...') and when ('Use this skill any time a .docx file is involved' and 'Trigger whenever the user mentions...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural terms including synonyms and the file extension: 'Word doc', 'document', 'report', 'letter', 'memo', 'Word documents', and '.docx filename', matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche scoped to .docx files with distinct, file-extension-anchored triggers ('any time a .docx file is involved', 'references a .docx filename'), minimizing overlap with adjacent skills.	5 / 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: e701dba

Reviewed: 1 day 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.