doc

Read, create, and edit .docx documents with formatting and layout fidelity via OpenAI's document skill.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/doc/SKILL.md

Quality

Content

72%

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

The body is a lean, well-organized catalogue pointer that delegates the real workflow upstream, which keeps conciseness and progressive disclosure high but leaves actionability and workflow clarity at 2 because the actual install/invoke steps lack executable commands.

Suggestions

Replace the vague "install the upstream bundle" step with a concrete, executable command (e.g., a git clone / symlink into the skills directory) to lift actionability.

Tighten the How-to-use sequence into numbered steps with a final verification step (e.g., confirm the skill appears via the trigger phrase) to improve workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean — short sections under 50 lines that assume Claude's competence and avoid explaining concepts Claude already knows — fitting the score-3 anchor of every token earning its place; the minor verbatim repeat of the description is not enough to drop below 3.	3 / 3
Actionability	It offers some concrete guidance (the `open https://github.com/openai/skills` command and invocation by name `doc` or trigger phrases), but the core step of installing the upstream bundle has no executable command and defers detail to the upstream README, matching the score-2 anchor of incomplete guidance with missing key details.	2 / 3
Workflow Clarity	A loose sequence is present (install bundle → open upstream README → invoke by name/triggers) but it is not a tightly ordered workflow with explicit checkpoints, fitting the score-2 anchor of steps listed with implicit/missing checkpoints.	2 / 3
Progressive Disclosure	Under 50 lines with no bundle files present (references/scripts/assets are empty) and well-organized sections (What it does, Source, How to use); the only reference is a clearly signaled one-level external GitHub URL, so the simple-skill guideline allows a 3.	3 / 3
	Total	10 / 12 Passed

Description

67%

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

The description is specific and well-scoped to .docx layout fidelity, but it omits an explicit "Use when..." trigger clause and lacks natural term variations like "Word", which together cap completeness and trigger-term quality at 2.

Suggestions

Append a "Use when working with .docx or Word files, or when the user mentions Word documents, document layout, or formatting fidelity." clause to raise completeness to 3.

Add natural term variations ("Word", "Word documents", "Word files") alongside ".docx" so trigger-term coverage reaches the score-3 anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Read, create, and edit .docx documents with formatting and layout fidelity" — matching the score-3 anchor of several specific actions rather than naming only a domain.	3 / 3
Completeness	It clearly answers what (read/create/edit .docx with layout fidelity) but lacks any "Use when..." clause or explicit trigger guidance, which the guidelines cap at 2.	2 / 3
Trigger Term Quality	".docx documents" is a relevant natural keyword, but common variations like "Word", "Word document", or "Word files" are missing, landing at the score-2 anchor of some relevant keywords without full coverage.	2 / 3
Distinctiveness Conflict Risk	The niche — .docx with formatting/layout fidelity, paired with distinct frontmatter triggers like "docx fidelity" and "layout doc" — is clear and unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/doc/SKILL.md
Commit: f2760fd

Reviewed: about 15 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.