office-artifacts

Use when creating, opening, reading, or editing Office artifacts such as LibreOffice-native ODT/ODS/ODP files and compatibility DOCX/XLSX/PPTX files with the office_artifact tool.

Quality

86%

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

76%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.

Highly actionable content with executable examples and a clear workflow, weakened mainly by missing post-edit validation/feedback loops for destructive operations. Organization is good but keeps some reference-grade detail inline.

Suggestions

Add an explicit post-edit validation/retry step to the Workflow (e.g., after `edit`, verify the result with `read` or check the returned state, and re-apply on failure) to satisfy the destructive/batch feedback-loop expectation.

Move the per-format operation table and the detailed `create_chart` argument spec into a short reference section or reference file so the core flow stays scannable.

Tighten the Desktop-surface and canvas-opening guidance into a single concise rule to lift conciseness to the top anchor.

Dimension	Reasoning	Score
Conciseness	Largely lean with executable JSON examples and terse rule bullets, assuming Claude's competence; a few slightly editorial passages (Desktop-surface and canvas-opening guidance) could be trimmed, keeping it just below the top anchor.	4 / 5
Actionability	Provides multiple copy-paste-ready JSON calls (create, read, replace_text, append_text, set_cells, create_chart), per-format operation tables, and explicit argument rules covering the common cases.	5 / 5
Workflow Clarity	A clear 4-step numbered workflow with a read-before-edit checkpoint exists, but destructive/batch operations (replace_text, delete_text, set_cells) lack explicit post-edit validation or error-recovery feedback loops, triggering the cap for destructive/batch skills.	3 / 5
Progressive Disclosure	Well-organized into clear sections (Workflow, Minimal Calls, Edit Operations, Practical Rules) with clearly signaled pointers to sibling skills; minor gaps because chart and per-format detail that could be split into references is inlined and no bundle files exist.	4 / 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 concretely states actions, formats, and the tool, with an explicit "Use when" trigger and rich keyword coverage. The only soft spot is mild overlap with the format-specific sibling skills it points to.

Dimension	Reasoning	Score
Specificity	Names four concrete actions ("creating, opening, reading, or editing") alongside specific formats (ODT/ODS/ODP/DOCX/XLSX/PPTX) and the exact tool, giving comprehensive coverage with no meaningful gaps.	5 / 5
Completeness	Explicitly answers what ("creating, opening, reading, or editing Office artifacts...") and when ("Use when...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Covers natural terms ("Office artifacts"), synonyms ("office document"), and file extensions (odt/ods/odp/docx/xlsx/pptx) plus matching YAML triggers, giving comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	The Office-artifact niche with named formats and a named tool is mostly distinct, but the body delegates to sibling skills (writer-documents/calc-spreadsheets/impress-presentations), signaling minor overlap risk with those 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: agent0ai/agent-zero
Path: plugins/_office/skills/office-artifacts/SKILL.md
Commit: b22a144

Reviewed: 4 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.