spreadsheet-direct-verification

Use a deterministic Python/openpyxl inspection pass to verify workbook structure, counts, marked rows, and output-file existence when delegated spreadsheet summaries seem inconsistent.

Quality

80%

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-verification/SKILL.md

Quality

Content

75%

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

The skill body is highly actionable with complete executable scripts and a clear, validated workflow. It is weaker on token efficiency (repetitive sections and a long domain-specific code block) and progressive disclosure (a monolithic single file with no external references for the bulkier material).

Suggestions

Consolidate the repeated 'verify from disk and trust the script' guidance — the core principle, minimum checklist, final response pattern, decision rule, and anti-patterns all restate the same idea; keep one authoritative version.

Move the production-planning validation section and its large code block into a referenced file (e.g. references/production-validation.md) and link to it from the body, keeping SKILL.md a lean overview.

Trim or make optional the production-specific content unless the skill's primary purpose is production planning, since it roughly doubles the file's size for a sub-case.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids re-explaining basic concepts, but it repeats the same guidance several times (verification checklist vs. core principle vs. final response pattern vs. anti-patterns all restate 'verify from disk, trust the script'), and the long production-planning code block bloats a skill that is conceptually simple.	2 / 3
Actionability	Provides complete, executable Python/openpyxl scripts (the base inspection script and the production-constraint validator) plus explicit 'How to adapt' guidance naming the exact variables to change, making it copy-paste ready.	3 / 3
Workflow Clarity	The numbered workflow is clearly sequenced with a comparison/feedback loop ('If they differ, treat the script as authoritative'), explicit checklists, and an 'If the workbook layout is unusual' section covering error-recovery cases.	3 / 3
Progressive Disclosure	Content is well organized into sections, but everything is inline in a single 370-line SKILL.md with no bundle files; the large production-planning script and its validator are strong candidates for a separate reference file rather than the main body.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 specific, complete, and distinct, naming concrete verification actions and an explicit trigger. Its main weakness is the trigger phrase using internal jargon ('delegated summaries') rather than natural user language.

Suggestions

Reword the 'when' clause toward user-facing phrasing, e.g., 'Use when a spreadsheet summary seems wrong, incomplete, or inconsistent with what is actually in the file.'

Add common natural trigger terms such as 'verify spreadsheet,' 'workbook counts,' or 'check what's really in the file' to broaden recall.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'verify workbook structure, counts, marked rows, and output-file existence,' with the tool named ('deterministic Python/openpyxl inspection pass'), all in third person.	3 / 3
Completeness	Clearly states what ('deterministic Python/openpyxl inspection pass to verify workbook structure, counts, marked rows, and output-file existence') and when ('when delegated spreadsheet summaries seem inconsistent'), so both what and when are explicit.	3 / 3
Trigger Term Quality	Relevant terms ('workbook,' 'spreadsheet summaries,' 'inconsistent') appear, but the trigger 'when delegated spreadsheet summaries seem inconsistent' is agent-internal jargon users would rarely say, and common natural variations like 'spreadsheet doesn't match' or 'verify spreadsheet' are missing.	2 / 3
Distinctiveness Conflict Risk	Targets a narrow niche — verifying delegated spreadsheet summaries against disk state via openpyxl — making it unlikely to trigger for general spreadsheet editing or unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/spreadsheet-direct-verification/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.