CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

xlsx

Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx) where the workbook file is the primary deliverable. Use for formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel. Also applies to .csv/.tsv when the user wants spreadsheet output. Do NOT use for Word documents, HTML reports, standalone Python scripts, database pipelines, or Google Sheets API work.

85

Quality

99%

Does it follow best practices?

Impact

93%

1 of 3 eval scenarios. Add 2 more for a full score.

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is xlsx in K-Dense-AI/claude-scientific-writer

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 model of dense, high-value operational guidance: a task-routing table, mandatory recalculation with explicit validation and error-recovery loops, precise formula-selection rules, and environment-specific gotchas, all backed by real script files in the bundle. Nothing scored below the top anchor on any dimension.

DimensionReasoningScore

Conciseness

Every section carries non-obvious, environment-specific knowledge Claude cannot be assumed to know: recalc exit-code semantics ("errors_found exits 0, so never treat a clean exit as a clean workbook"), the `_xlfn.` prefix list, spill-function truncation, and `data_only` pitfalls. There is no padding and no explanation of concepts Claude already knows; the only candidate for trimming (the external-link paragraph) delivers a distinct actionable fact per sentence.

5 / 5

Actionability

Guidance is fully executable: the exact command `python scripts/recalc.py output.xlsx [timeout_seconds]`, concrete formula strings (`sheet['B10'] = '=SUM(B2:B9)'`, `='Assumptions Inputs'!$B$5`), explicit color RGB values, number-format strings (`$#,##0;($#,##0);-`), and a decision table routing each task type to an approach.

5 / 5

Workflow Clarity

The workflow has explicit validation with feedback loops: recalc JSON output interpretation ("Fix what it names and run it again"), a hard ship gate ("Never ship while recalc.py reports errors_found"), a pre-build checkpoint ("Write 2–3 formulas first and check they pull the values you expect, before building out a grid"), and guidance to verify inherited vs. introduced errors. The destructive/batch cap at 3 does not apply because validation is pervasive and explicit, so the top anchor fits.

5 / 5

Progressive Disclosure

The body is a well-sectioned overview whose referenced bundle files (`scripts/recalc.py`, `scripts/office/soffice.py`) exist in the bundle and are clearly signaled ("Script paths below are relative to this skill's directory"), one level deep with no nested reference chains. All inline content (gotchas, requirements, conventions) is core operational guidance that appropriately lives in SKILL.md rather than separate files.

5 / 5

Total

20

/

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: third-person voice, concrete capability list, explicit "Use for" triggers with file extensions and synonyms, and explicit negative boundaries that sharply reduce mis-triggering risk. No changes needed.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ("Create, edit, analyze, or convert") and enumerates specific domain tasks — "formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel" — giving comprehensive coverage of the skill's capabilities with no vague filler.

5 / 5

Completeness

Both questions are answered explicitly: the "what" ("Create, edit, analyze, or convert Excel spreadsheets... where the workbook file is the primary deliverable") and the "when" via a concrete "Use for formulas, formatting, financial models..." trigger clause plus "Also applies to .csv/.tsv when the user wants spreadsheet output". This matches the top anchor; it is not score 4 because the "when" is explicit with concrete trigger phrases rather than merely present.

5 / 5

Trigger Term Quality

Natural user phrasing is comprehensively covered with synonyms and file extensions: "Excel spreadsheets", ".xlsx, .xlsm, .xltx", ".csv/.tsv", "spreadsheet output", "formulas", "financial models". It matches the anchor's standard of including both everyday terms and extensions.

5 / 5

Distinctiveness Conflict Risk

The niche is distinct (Excel workbook as primary deliverable) and conflict risk is minimized by an explicit exclusion list: "Do NOT use for Word documents, HTML reports, standalone Python scripts, database pipelines, or Google Sheets API work". No neighboring anchor fits better.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

K-Dense-AI/claude-scientific-writer

Path

scientific_writer/.claude/skills/xlsx/SKILL.md

Reviewed

Table of Contents

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.