xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When GLM needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
65
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/xlsx/SKILL.mdQuality
Discovery
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.
This is a strong skill description that clearly defines its scope around spreadsheet operations, lists specific file types and actions, and provides explicit trigger conditions via a numbered list. The only minor issue is the reference to 'GLM' instead of 'Claude', which is a naming inconsistency but doesn't affect functional quality. The description follows the pattern of good examples in the rubric closely.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creation, editing, analysis, formulas, formatting, data analysis, visualization, reading data, modifying while preserving formulas, and recalculating formulas. | 3 / 3 |
Completeness | Clearly answers both 'what' (comprehensive spreadsheet creation, editing, analysis with formulas, formatting, etc.) and 'when' (explicit numbered list of trigger scenarios starting with 'When GLM needs to work with spreadsheets'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'spreadsheet', '.xlsx', '.xlsm', '.csv', '.tsv', 'formulas', 'formatting', 'data analysis', 'visualization'. Good coverage of file extensions and common terms. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to spreadsheet files with specific file extensions (.xlsx, .xlsm, .csv, .tsv) and spreadsheet-specific operations like formula recalculation. Unlikely to conflict with other document or data skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with executable code examples and has a well-structured workflow with explicit validation steps via recalc.py. However, it is severely bloated—style guides, financial model conventions, and chart notes should be in separate referenced files rather than inline. Significant redundancy (repeated title formatting rules, repeated recalc.py explanations) and unnecessary explanations of concepts Claude already knows (basic pandas operations, what Excel formulas are) waste substantial token budget.
Suggestions
Extract the style rules (Default Style, Professional Finance Style, font standards, title formatting) into a separate STYLES.md file and reference it from the main skill with a one-line summary.
Extract financial model conventions (color coding, number formatting, formula construction rules, documentation requirements) into a separate FINANCIAL_MODELS.md file.
Remove redundant content: title formatting rules appear 3+ times, recalc.py usage is explained in 3 separate sections, and color conventions are duplicated between financial models and content color conventions.
Remove basic pandas/openpyxl tutorials (df.head(), df.info(), basic load_workbook usage) that Claude already knows, keeping only project-specific patterns like the recalc.py integration and the formulas-not-hardcodes rule.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It explains many concepts Claude already knows (what pandas is, how to read Excel files, basic Python patterns). There is significant redundancy—title formatting rules are repeated across multiple sections, color coding conventions appear in both financial models and content color conventions sections, and the recalc.py workflow is explained three separate times. The style guide code examples are overly detailed with comments explaining obvious things. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code throughout—openpyxl workbook creation, pandas data reading, formula construction, chart configuration, and recalc.py usage. Concrete examples show both correct and incorrect patterns (✅/❌), and specific color codes, font names, and formatting rules are provided rather than vague descriptions. | 3 / 3 |
Workflow Clarity | The common workflow is clearly sequenced (choose tool → plan → create/load → modify → save → recalculate → verify). The recalc.py validation step is explicitly marked as MANDATORY, with a clear feedback loop: check JSON output, fix errors, recalculate again. The formula verification checklist provides structured validation checkpoints. Error types are enumerated with specific remediation guidance. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files for detailed content. The extensive style guides, color palettes, financial model conventions, and chart creation notes could all be split into separate reference files. Everything is inline, making the skill extremely long and difficult to navigate. No bundle files are provided to offload this content. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jjyaoao/HelloAgents
- Commit
52b2597
- 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.