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

92%

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

85%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.

Strong, actionable content with executable commands, a clear decision matrix, and a validation-driven QA workflow. The one substantive defect is progressive disclosure: the body points to create.md/edit.md/read.md/analyze.md, but none of those files ship in the bundle, leaving the detail references broken.

Suggestions

Ship the four referenced detail files (create.md, edit.md, read.md, analyze.md) in the bundle, or remove the dead links and inline the essential material — the current state leaves 'Where each detail lives' pointing at nothing.

Trim the license-attribution roll-call in the opening paragraph ('openpyxl MIT, pandas BSD-3-Clause, lxml BSD-3-Clause, optional xlsxwriter BSD-2-Clause, optional external binary soffice MPL 2.0'); a single LICENSE pointer would reclaim tokens without losing the compliance signal.

Consider moving the number-format cheatsheet and color/style palette tables into one of the detail files (e.g. create.md) so the SKILL.md overview stays leaner while keeping them reachable.

Dimension	Reasoning	Score
Conciseness	Mostly lean and well-targeted — decision matrix, command list, cheatsheets, and pitfalls are dense and domain-specific rather than padded; held below 5 by the opening license roll-call ('openpyxl MIT, pandas BSD-3-Clause, lxml BSD-3-Clause...') and a little framing prose Claude does not need.	4 / 5
Actionability	Copy-paste-ready bash commands for every script and executable Python snippets (e.g. sheet.freeze_panes = "A2", the data_only=True assert, number_format strings) covering the common cases; matches the fully-executable top anchor.	5 / 5
Workflow Clarity	Explicit sequence ('read → plan → edit/create → recalc → validate') and a QA checklist with validation checkpoints and a feedback loop ('If any of these fail, fix and re-run. Do not paper over.') for batch/destructive workbook writes; matches the top anchor with error-recovery loops.	5 / 5
Progressive Disclosure	The SKILL.md is well-structured as an overview with clearly signaled one-level-deep references ('Where each detail lives' → create.md, edit.md, read.md, analyze.md), but those four referenced files are absent from the bundle, so navigation leads to dead ends; the broken reference targets pull an otherwise 5-quality structure down to 3.	3 / 5
	Total	17 / 20 Passed

Description

100%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.

An exemplary description: concrete actions, comprehensive natural trigger terms, explicit what/when guidance, and a clear boundary clause that reduces conflict risk. Voice stays in acceptable directive/third-person form without first- or second-person slip.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produced, changed, cleaned, or read' — plus concrete task examples like 'build me a model', 'compute the totals as formulas', 'render the workbook as PDF', giving comprehensive coverage; not below 5 because coverage is broad and specific, not above because 5 is the ceiling.	5 / 5
Completeness	Explicitly answers both 'what' (produce, change, clean, read workbook files) and 'when' ('Reach for it whenever...', 'Typical triggers: ...') with concrete trigger phrases, and adds a 'Skip it when...' exclusion; clearly the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including file extensions (.xlsx, .xlsm, .xltx, .csv, .tsv) and realistic user phrasings like 'update this sheet', 'sanity-check this xlsx', 'export sheet 2 to CSV'; matches the anchor for synonyms plus extensions.	5 / 5
Distinctiveness Conflict Risk	Clear niche (workbook files) with a distinct 'Skip it when...' boundary excluding Word docs, HTML, standalone scripts, Google Sheets, and DB ingestion, minimizing overlap with adjacent skills.	5 / 5
	Total	20 / 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
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: be5af90

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.