spreadsheet-proof-gate

Edit Excel workbooks only after anchored preflight audit, then require deterministic Python/openpyxl post-write proof that every requested criterion is satisfied or explicitly reconciled before finalizing.

Quality

68%

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-audit-edit-validate-merged/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 a strong, well-validated multi-phase workflow and executable verification code, but it is verbose from structural redundancy and monolithic where detail could be split into bundle files.

Suggestions

Consolidate the repeated finalization/no-go rules into a single authoritative section and cross-reference it instead of restating across Core rule, Phase 6, Finalization gate, Decision rules, and Practical checklist.

Move the verification script template into a scripts/ file (e.g., verify_workbook.py) and reference it, and offload detailed criteria examples to a references/ file to improve progressive disclosure.

Trim the 'Why this skill exists', 'Anti-patterns', and restated 'Practical checklist' sections to the non-redundant essentials to raise conciseness.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows, but the finalization gate and no-go rules are restated four-to-five times across Core rule, Phase 6, Finalization gate, Decision rules, and Practical checklist, so it could be tightened rather than earning the lean-and-efficient top level.	2 / 3
Actionability	It provides a complete, executable openpyxl verification script template plus concrete criteria examples and a rigid CRITERION\|name\|status\|reason checklist format, reaching the copy-paste-ready anchor rather than the pseudocode level below.	3 / 3
Workflow Clarity	Phases 1–6 are clearly sequenced with explicit go/no-go gates, pre-edit audit, post-write proof, and repair-then-re-run feedback loops, matching the clear-sequence-with-validation anchor rather than the missing-checkpoint level.	3 / 3
Progressive Disclosure	Sections are well organized, but the ~590-line file is monolithic with the long script template and repeated checklists inline and no bundle files (references/, scripts/) to offload detail, so it is not the well-signaled one-level-deep reference structure above.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 concrete, distinctive capabilities clearly but omits an explicit 'Use when ...' trigger clause and natural user phrasings, leaving trigger-term quality and completeness at the mid level.

Suggestions

Append a trigger clause such as 'Use when editing or validating Excel workbooks (.xlsx, .xls) where the result must be proven against a specification' to lift completeness and trigger-term quality.

Add natural user terms ('spreadsheets', '.xlsx', 'Excel files') alongside 'Excel workbooks' to improve trigger-term coverage.

Soften the technical phrasing ('anchored preflight audit', 'deterministic post-write proof') so a user's request language more naturally matches the description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Edit Excel workbooks', 'anchored preflight audit', 'deterministic Python/openpyxl post-write proof', and 'criterion ... satisfied or explicitly reconciled' — matching the multiple-specific-actions anchor rather than the partial domain-only anchor below.	3 / 3
Completeness	The 'what' is clear, but there is no 'Use when ...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2 rather than reaching the explicit-both-what-and-when level.	2 / 3
Trigger Term Quality	'Excel workbooks' is a natural term, but the phrasing leans technical ('anchored preflight audit', 'deterministic ... proof') and omits common variations like 'spreadsheets', '.xlsx', or 'Excel files', so it is not the full-coverage level above.	2 / 3
Distinctiveness Conflict Risk	The proof-gated niche is specific, yet without explicit trigger terms it could still overlap generic Excel-editing skills, matching the 'somewhat specific but could overlap' anchor rather than the distinct-triggers level.	2 / 3
	Total	9 / 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 (593 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/spreadsheet-audit-edit-validate-merged/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.