xlsx-official

Spreadsheet toolkit. Reach for it whenever the artifact on either side of the conversation is a workbook file — .xlsx, .xlsm, .xltx, .csv, .tsv — and the user wants that artifact produced, changed, cleaned, or read. Typical triggers: 'build me a model', 'update this sheet', 'add a column', 'compute the totals as formulas', 'sanity-check this xlsx', 'export sheet 2 to CSV', 'render the workbook as PDF', 'the spreadsheet in ~/Downloads is a mess, fix it'. Applies equally to financial models, ops reports, data cleanups, and template fills. Skip it when the workbook is only source material and the real output is a Word doc, an HTML page, a Python script that runs standalone, a Google Sheets integration, or an ingestion pipeline into a database — in those cases the spreadsheet is a means, not the deliverable.

Quality

96%

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

Quality

Content

92%

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

An actionable, well-sequenced body with strong validation feedback loops and token-efficient reference tables. Its one weakness is progressive disclosure: the four detail markdown files it points to are missing from the bundle, leaving dead links.

Suggestions

Ship the referenced create.md, edit.md, read.md, and analyze.md files in the bundle (or under references/) so the 'Where each detail lives' links resolve.

Verify each link target in the decision matrix and 'Where each detail lives' section exists at the stated path before publishing.

Consider moving the number-format and color-palette cheatsheets into a reference file if the overview grows, keeping SKILL.md as a navigation hub.

Dimension	Reasoning	Score
Conciseness	Lean and dense — a decision matrix, executable commands, and compact cheatsheets (number formats, color palette) that encode domain specifics Claude does not reliably memorize. It avoids explaining concepts Claude already knows and assumes competence throughout.	3 / 3
Actionability	Copy-paste-ready commands ('python scripts/bake.py output.xlsx --timeout 60', 'python scripts/overview.py input.xlsx') and executable code (load_workbook with data_only=True assertion). No pseudocode; every example is runnable.	3 / 3
Workflow Clarity	Clear sequence ('read → plan → edit/create → recalc → validate') plus a QA checklist with explicit validation checkpoints (recalculate via bake.py, audit.py, spot-check, PDF visual sanity) and a feedback loop ('If any of these fail, fix and re-run. Do not paper over.').	3 / 3
Progressive Disclosure	The overview is well-signaled and points one level deep to create.md, edit.md, read.md, analyze.md, and scripts/ — but the four referenced detail .md files are absent from the bundle (only scripts/ exists), so the navigation they promise is broken and discovery fails for those paths.	2 / 3
	Total	11 / 12 Passed

Description

100%

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, third-person description with concrete capabilities, natural trigger phrases, and an explicit use/skip boundary. It is distinguishable from neighboring skills and answers both what and when unambiguously.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produced, changed, cleaned, or read' — across workbook artifacts, matching the score-3 anchor of multiple specific concrete actions rather than vague domain-only phrasing.	3 / 3
Completeness	Explicitly answers both what ('Spreadsheet toolkit... produced, changed, cleaned, or read') and when ('Reach for it whenever the artifact... is a workbook file' + trigger list + a 'Skip it when...' exclusion clause).	3 / 3
Trigger Term Quality	Excellent coverage of natural user phrasing: 'build me a model', 'update this sheet', 'add a column', 'sanity-check this xlsx', 'export sheet 2 to CSV', 'render the workbook as PDF', plus file extensions (.xlsx, .xlsm, .xltx, .csv, .tsv).	3 / 3
Distinctiveness Conflict Risk	Clear workbook-file niche with distinct triggers and an explicit skip-list (Word doc, HTML page, standalone Python, Google Sheets, DB ingestion) that prevents triggering for adjacent skills.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 9 missing	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/xlsx-official/SKILL.md
Commit: ff87d47

Reviewed: about 8 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.