CtrlK
BlogDocsLog inGet started
Tessl Logo

spreadsheet-direct-python

Use direct Python execution for reliable spreadsheet operations instead of shell_agent

51

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/spreadsheet-direct-python/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

66%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 highly actionable with strong executable examples and clean sectioning, but workflow clarity is capped by missing validation checkpoints for destructive/batch spreadsheet writes, and some explanatory prose could be trimmed.

Suggestions

Add an explicit validation step after save/load in batch or destructive operations (e.g., reopen the saved workbook and assert expected sheet/cell values before declaring success).

Trim the 'Why Direct Execution?' section — Claude already understands step-limit and error-verbosity tradeoffs; a one-line rationale suffices.

Fix the duplicate numbering in Best Practices (two items labeled '4') to avoid navigation confusion.

DimensionReasoningScore

Conciseness

Mostly efficient with code-forward examples, but the 'Why Direct Execution?' section restates tool-failure rationale that Claude already understands and the Best Practices list duplicates concepts; some tightening possible without losing clarity.

3 / 5

Actionability

Four fully executable, copy-paste-ready Python examples plus a basic heredoc pattern cover the common cases (read/transform, multi-sheet, formatting, error handling), with specific library usage throughout.

5 / 5

Workflow Clarity

A basic sequence is conveyed through progressive examples, but there are no explicit validation checkpoints for batch/destructive spreadsheet writes (e.g., verify output opened correctly, confirm save succeeded), which per the rubric caps this at 3.

3 / 5

Progressive Disclosure

Well-organized sections (When to Use, How to Use, Best Practices, When NOT to Use, Troubleshooting) with no bundle files present; content is appropriately inlined and easy to navigate, with only minor gaps.

4 / 5

Total

15

/

20

Passed

Description

45%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.

The description states a clear purpose but omits explicit trigger guidance and natural user keywords, relying on internal tool names instead. Specificity is moderate with no enumerated spreadsheet actions.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when working with .xlsx files, formulas, formatting, or multi-sheet Excel operations').

Replace the internal tool framing with user-facing keywords: Excel, spreadsheets, .xlsx, openpyxl, pandas.

List 3-4 concrete actions (read/write sheets, apply formulas, format cells, multi-sheet transforms) to raise specificity.

DimensionReasoningScore

Specificity

Names the domain ('spreadsheet operations') and one concrete action framing ('direct Python execution') but lists no specific spreadsheet actions (e.g., read sheets, apply formulas, format cells); comparable to 'Processes PDF files and extracts content'.

3 / 5

Completeness

A clear 'what' is present (use direct Python for spreadsheet operations) but the 'when' is missing from the description — there is no 'Use when...' clause, which per guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Only generic terms ('spreadsheet operations', 'shell_agent', 'Python') appear; natural user phrasing like 'Excel', 'xlsx', 'formulas', 'pandas', 'openpyxl' is absent, so it misses the natural phrases users would say.

2 / 5

Distinctiveness Conflict Risk

'Spreadsheet operations' is somewhat specific but the framing is tool-internal (shell_agent vs run_shell) rather than user-triggering, so it could overlap with a general Excel/spreadsheet skill.

3 / 5

Total

11

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
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.