spreadsheet-validated-exec

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

Quality

60%

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

62%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 content excels at workflow clarity and is highly actionable, but it is significantly over-long for a SKILL.md, with heavy code repetition and no progressive disclosure into bundle files. Consolidating the repeated validation logic and splitting reference material into separate files would improve both conciseness and structure.

Suggestions

Factor the repeated file-exists/empty-check into a single reusable helper shown once, then reference it in examples instead of re-pasting the block.

Move the Common Libraries table, Data Access Failure Protocols, and Troubleshooting sections into referenced files (e.g. references/troubleshooting.md) and link to them from SKILL.md.

Trim explanatory prose about why validation matters and what openpyxl/pandas do — Claude already knows these — keeping only the validation workflow and code templates.

Dimension	Reasoning	Score
Conciseness	At ~575 lines the body is noticeably verbose: the same Path.exists() + file-size check is repeated in Phase 0, Pattern 1, and Examples 1–3, and the Common Libraries table explains basics Claude already knows.	2 / 5
Actionability	Provides mostly executable, copy-paste-ready Python across multiple complete examples; only minor gaps such as `process_data` leaving `pass` and "Your operations here" placeholders.	4 / 5
Workflow Clarity	Clear Validate → Process → Report sequence with a REQUIRED Phase 0, a pre-execution checklist, explicit "Do NOT proceed" gating, and feedback loops (retry-with-backoff, fallback sourcing).	5 / 5
Progressive Disclosure	Section headers are well organized, but all 575 lines are inlined with no bundle files or references; the reusable validation helpers, failure protocols, and troubleshooting could each live in separate referenced files.	3 / 5
	Total	14 / 20 Passed

Description

58%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 is concise and third-person with a clear purpose, but it lacks an explicit usage trigger and omits the most natural spreadsheet keywords (Excel, .xlsx). Adding a "Use when…" clause and common file-extension/library terms would materially raise completeness and trigger-term quality.

Suggestions

Append a trigger clause, e.g. "Use when processing Excel/spreadsheet files (.xlsx) with Python where data sources must be verified first."

Add natural user keywords and extensions — "Excel", ".xlsx", "openpyxl", "pandas" — to improve trigger-term coverage.

Optionally name the core operations (read, write, format, transform) to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Execute Python scripts", "prerequisite data validation", and "source accessibility checks" — with only minor coverage gaps (no read/write/format specifics).	4 / 5
Completeness	Clearly states what the skill does, but provides no "Use when…" trigger clause, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ("spreadsheets", "Python scripts") but is missing the most common user-facing synonyms and extensions such as Excel, .xlsx, openpyxl, and pandas.	3 / 5
Distinctiveness Conflict Risk	The validation-and-accessibility-check framing carves a mostly distinct niche, with only minor overlap risk against generic spreadsheet execution skills.	4 / 5
	Total	14 / 20 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: 3827781

Reviewed: 8 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.