CtrlK
BlogDocsLog inGet started
Tessl Logo

spreadsheet-direct-python

Use direct Python execution for reliable spreadsheet operations instead of shell_agent

55

Quality

61%

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

72%

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

The body is strong on actionability with concrete, executable examples and clean organization. Its main weaknesses are minor verbosity/duplication and the absence of explicit validation feedback loops for risky batch operations.

Suggestions

Merge or trim the 'Why Direct Execution?' section to remove overlap with 'When to Use This Skill'.

Fix the duplicated '4.' numbering in Best Practices and remove the tangential DataFrame-constructor tip unless it is load-bearing.

Add an explicit validate-then-fix-then-retry feedback loop for batch transformations (e.g. verify row counts or schema before saving).

DimensionReasoningScore

Conciseness

Content is mostly lean and example-driven without explaining basics Claude already knows, but the 'Why Direct Execution?' section overlaps the 'When to Use' bullets and Best Practices has a duplicated '4.' item and padded tips that could be tightened.

2 / 3

Actionability

Provides multiple complete, executable Python examples (pandas read/transform, openpyxl multi-sheet, styling, error handling) that are copy-paste ready with real imports and save calls.

3 / 3

Workflow Clarity

Examples are clearly labeled and an error-handling pattern exists, but batch/destructive spreadsheet operations lack explicit validate-then-fix-then-retry feedback loops; the Troubleshooting section is reactive rather than a proactive checkpoint.

2 / 3

Progressive Disclosure

The skill is a single self-contained SKILL.md with no bundle files (references/scripts/assets absent) and well-organized sections, which per the rubric's simple-skill note can score 3 with just clear organization.

3 / 3

Total

10

/

12

Passed

Description

50%

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 stops short of listing specific actions or providing an explicit trigger clause. It relies on an internal tool comparison rather than natural user-facing keywords.

Suggestions

Add concrete actions: e.g. 'Read, write, format, and transform Excel files using embedded Python'.

Append an explicit 'Use when...' trigger: e.g. 'Use when working with complex Excel files, multiple sheets, formulas, or .xlsx data transformations.'

Replace the internal 'shell_agent' jargon with natural terms users would actually say, like 'Excel', '.xlsx', and 'spreadsheets'.

DimensionReasoningScore

Specificity

Names the domain ('spreadsheet operations') and a concrete approach ('direct Python execution') but lists only one generic action rather than multiple specific concrete actions like 'read', 'format', or 'transform'.

2 / 3

Completeness

States what it does ('direct Python execution for reliable spreadsheet operations') but the 'when' is only implied via 'instead of shell_agent' with no explicit 'Use when...' trigger clause, capping it at 2.

2 / 3

Trigger Term Quality

'spreadsheet operations' and 'Python execution' are relevant, but 'shell_agent' is internal tool jargon and natural user terms like 'Excel', '.xlsx', or 'formulas' are missing.

2 / 3

Distinctiveness Conflict Risk

The spreadsheet-plus-direct-Python niche is fairly distinct, but the 'instead of shell_agent' framing is unusual and could overlap with general scripting skills rather than carving a clear unique trigger.

2 / 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.

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.