doc

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

Quality

53%

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

53%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.

The body is a well-organized, token-efficient catalogue entry, but it is a pointer rather than a skill: it contains no docx workflow, no code, and an undefined installation step, so an agent landing here cannot actually do anything with .docx files. Structure and navigation are good; substance is minimal.

Suggestions

Replace the placeholder bash block with a concrete, executable installation command (e.g., the actual git clone / copy path into the skills directory) instead of `open https://github.com/openai/skills`.

Inline a minimal quick-start (e.g., how to unpack/edit/pack a .docx once the bundle is installed) so the skill has some standalone value.

Remove the "What it does" section that duplicates the frontmatter description verbatim, and use that space for trigger phrases or prerequisites.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean with no concept explanations Claude already knows and no padding. It loses a point only because "What it does" repeats the frontmatter description verbatim, a small redundancy that could be trimmed.	4 / 5
Actionability	The only executable content is `open https://github.com/openai/skills`; the essential step — "install the upstream bundle into your active agent's skills directory" — is a high-level hint with no command, path, or example. Matches anchor 2 ("Minimal concrete guidance; high-level hints but missing the specific steps to execute"), not 1 because a concrete pointer and command exist.	2 / 5
Workflow Clarity	The sequence ("inspect the upstream README" → "install the upstream bundle" → "invoke this skill by name (`doc`) or with one of the trigger phrases") is ordered and coherent, and no validation is needed for non-destructive operations. But the critical install step is undefined, leaving a major gap in the middle of the sequence — anchor 3, not 4.	3 / 5
Progressive Disclosure	No references/, scripts/, or assets/ directories exist, and the body itself is short and cleanly sectioned with a single well-signaled, one-level-deep external reference (the upstream URL). Not 5 because the actual instructional content lives entirely outside the skill bundle rather than being appropriately split into in-bundle files.	4 / 5
	Total	13 / 20 Passed

Description

53%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.

The description is concise, third-person, and names a clear domain and three core actions, but it reads like a catalogue blurb rather than a trigger-ready skill description. It lacks any "when to use" guidance and the natural synonyms (Word, .docx, document editing) that users would actually say.

Suggestions

Append a 'Use when...' clause, e.g., "Use when working with .docx files, Word documents, or when the user asks to read, create, or edit formatted documents."

Add common synonyms and the file extension users would naturally mention: "Word documents", ".docx", "docx", "document formatting".

Make the actions more granular (e.g., "unpack and repack document XML, preserve styles and layout, edit formatting") instead of the broad verbs read/create/edit.

Dimension	Reasoning	Score
Specificity	"Read, create, and edit .docx documents with formatting and layout fidelity" names the domain and three actions, but the verbs are broad ("read/create/edit") rather than the granular operations of anchor 4 (e.g., "extracts text, fills forms, converts pages to images"). It fits anchor 3: domain plus a few concrete actions with gaps in coverage.	3 / 5
Completeness	The description has a clear "what" ("Read, create, and edit .docx documents with formatting and layout fidelity") but no "when"/"Use when..." clause or trigger guidance at all, which the rubric explicitly caps at 3. Not 4 because the "when" is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	The only natural keyword is ".docx documents"; common variations users would actually say — "Word documents", "Word files", ".docx", "document editing" — are missing. Matches anchor 3 ("Some relevant keywords but missing common variations or synonyms"), not 4 because synonym coverage is thin.	3 / 5
Distinctiveness Conflict Risk	".docx documents with formatting and layout fidelity" is a clear niche with minimal conflict risk against PDF or presentation skills, though it could mildly overlap with generic "documents" skills. Not 5 because no distinct trigger phrases reinforce the niche separation.	4 / 5
	Total	13 / 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
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: 1b47e60

Reviewed: 3 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.