spreadsheet-struct-verified

Create and modify Excel workbooks with mandatory deterministic Python verification of workbook structure, required sheets, populated columns, and sample counts before reporting completion.

Quality

75%

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-enhanced/SKILL.md

Quality

Content

73%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 is a well-sequenced workflow with strong validation checkpoints and a fully executable verification script, penalized mainly for repetition of the modify/create distinction and for inlining a large script rather than splitting it into a referenced file.

Suggestions

Consolidate the repeated modify-vs-create guidance into one authoritative section and remove redundant per-phase restatements to tighten the token budget.

Move the full verification script into a scripts/ bundle file (e.g., scripts/verify_workbook.py) and reference it from the body, keeping only a short invocation example inline.

Either fully implement the sampling-criteria verification or clearly label the in-script heuristic as a stub to avoid implying it is production-ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but repeats the modify-vs-create distinction many times across the table, 'When to use', 'Core principle', per-phase callouts, and explanatory 'Why deterministic Python verification' bullets, adding padding that could be tightened.	3 / 5
Actionability	It provides a complete, executable verification script with concrete invocation commands and a JSON spec schema, with only minor gaps (the sampling-criteria check is admittedly a simplified heuristic in-line).	4 / 5
Workflow Clarity	Phases are explicitly sequenced with go/no-go decision gates, a mandatory validation phase, and an explicit validate-fix-re-run feedback loop ('If verification fails: fix the workbook, re-run verification'), satisfying the destructive/batch feedback-loop requirement.	5 / 5
Progressive Disclosure	Structure is good with clear phase headings and a single inline verification script that doubles as a runnable template, but the large code block is inlined rather than placed in a referenced scripts/ file, leaving minor organization gaps given no bundle files exist.	4 / 5
	Total	16 / 20 Passed

Description

67%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 specific and clear about the verification-centric niche, but lacks an explicit "Use when..." trigger clause and natural user phrasings/file extensions that would maximize trigger-term quality and completeness.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when creating or modifying .xlsx/.xlsm workbooks where required tabs, columns, or sample counts must be verified').

Include natural user phrasings and file extensions such as .xlsx, .xlsm, tabs, row counts alongside the technical terms.

Expand the action list slightly (e.g., 'verify sheet names, column headers, row counts, and marked-sample counts') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions ("Create and modify Excel workbooks", "deterministic Python verification of workbook structure, required sheets, populated columns, and sample counts") but the verification framing leans abstract rather than enumerating several distinct actions, leaving minor coverage gaps.	4 / 5
Completeness	It clearly states the "what" (create/modify Excel workbooks with verification) and implies the "when" via "before reporting completion", but the trigger is not phrased as an explicit "Use when..." clause with concrete trigger phrases, so it does not reach 5.	4 / 5
Trigger Term Quality	It surfaces some relevant terms ("Excel workbooks", "sheets", "columns", "sample counts") but omits natural user phrasings and file extensions like .xlsx/.xlsm, missing common variations a user would actually say.	3 / 5
Distinctiveness Conflict Risk	The mandatory deterministic Python verification and structure-checking niche is fairly distinct from generic spreadsheet skills, with only minor overlap risk against general Excel-authoring skills.	4 / 5
	Total	15 / 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 (565 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/spreadsheet-audit-edit-validate-enhanced/SKILL.md
Commit: 3827781

Reviewed: 9 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.