spreadsheet-validated-exec

Execute Python scripts for spreadsheets with prerequisite data validation and source accessibility checks

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/spreadsheet-direct-python-enhanced-enhanced-f0b1db/SKILL.md

Quality

Content

77%

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 executable code and a clear, well-validated workflow, but it is verbose and monolithic, repeating validation boilerplate and inlining material that would benefit from separate reference files.

Suggestions

Factor the repeated local-file validation (exists + non-empty check) into a single reusable snippet and reference it rather than duplicating it in Examples 1-4.

Move the large Troubleshooting and Data Access Failure Protocols sections into a reference file (e.g. TROUBLESHOOTING.md) and link to it from SKILL.md to improve progressive disclosure.

Trim the explanatory prose in 'Why Validated Direct Execution?' and the Common Libraries table to the essentials, relying on Claude's existing knowledge of these libraries.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful concrete code, but it repeats the same file-existence and empty-file validation boilerplate across at least four examples and carries a large troubleshooting section with prose; it could be tightened, matching the score-2 anchor over the lean score-3 example.	2 / 3
Actionability	Examples are fully executable Python with imports, real functions (verify_local_file, retry_with_backoff, get_data_with_fallback), copy-paste-ready heredoc templates, and a libraries table giving specific tool guidance, matching the score-3 anchor of fully executable code.	3 / 3
Workflow Clarity	A clearly sequenced Validate -> Process -> Report flow with a required Phase 0, numbered steps, a pre-execution checklist, and explicit error-recovery feedback loops (retry_with_backoff, fail-fast on validation) matches the score-3 anchor for explicit validation checkpoints and feedback loops.	3 / 3
Progressive Disclosure	The skill is well-sectioned but monolithic at ~580 lines with no bundle files and no external references; content that could be split (troubleshooting, full error-handling templates, four complete examples) is all inline, matching the score-2 anchor of structure with content that should be separate inline rather than the one-level-deep reference pattern of score 3.	2 / 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 and domain with a few concrete actions, but lacks an explicit use-when trigger and the most natural user keywords (Excel, xlsx). It is a solid mid-range description rather than a strong one.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g. 'Use when reading or writing complex Excel files, multi-sheet workbooks, or when data sources need validation before processing.'

Include natural user-facing terms like 'Excel', '.xlsx', 'openpyxl', and 'pandas' alongside 'spreadsheets' to improve trigger coverage.

Consider concrete outputs (e.g. 'validate, read, transform, and write .xlsx files') instead of abstract process phrases like 'source accessibility checks'.

Dimension	Reasoning	Score
Specificity	Names the spreadsheet domain and several action phrases ("Execute Python scripts", "prerequisite data validation", "source accessibility checks"), but these describe phases rather than concrete deliverables and are not a comprehensive action list, matching the score-2 anchor over the more tangible score-3 example.	2 / 3
Completeness	It clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance; per the judging guidelines a missing when-clause caps completeness at 2.	2 / 3
Trigger Term Quality	"Python scripts", "spreadsheets", and "data validation" are relevant, but the description omits the most natural user terms ("Excel", ".xlsx", "openpyxl", "pandas") and includes non-conversational phrases like "source accessibility checks", fitting the score-2 anchor of some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	The validation-before-execution framing gives it a niche, but generic triggers like "Python scripts for spreadsheets" could still overlap with a plain spreadsheet skill, matching the score-2 anchor of somewhat specific but still overlapping.	2 / 3
	Total	8 / 12 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
skill_md_line_count	SKILL.md is long (580 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/spreadsheet-direct-python-enhanced-enhanced-f0b1db/SKILL.md
Commit: c5a9c4b

Reviewed: 2 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.