spreadsheet-create-verify-gate

Create or edit Excel workbooks with openpyxl-specific pitfall handling, anchored preflight audit, and deterministic post-write proof that every criterion is satisfied

Quality

64%

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-proof-gate-merged-fedf41/SKILL.md

Quality

Content

70%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 body delivers a well-sequenced, validation-heavy workflow with executable openpyxl code and strong error-recovery feedback loops, but it is somewhat repetitive and monolithic with no progressive disclosure into bundle files.

Suggestions

Consolidate the repeated merged-cell guidance into a single reference section to reduce redundancy across Rule 2, the pre-audit phases, and the error-handling section.

Make the Phase 6 verification script fully runnable by defining the `criteria` list and uncommenting a concrete criterion-check example.

Move the verification script template and shell_agent escalation template into separate files under scripts/ or references/ and link to them from SKILL.md for progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with useful openpyxl specifics, but merged-cell handling is repeated across Rule 2, Phase 2A.2, Phase 2B.2, Phase 6, and the Error handling section — more than minor redundancy that could be consolidated.	3 / 5
Actionability	Phases 5 and 2B.2 provide concrete, executable openpyxl code, but the Phase 6 verification script leaves the criterion loop commented out and references an undefined `criteria` variable, so it is not fully copy-paste ready.	4 / 5
Workflow Clarity	The six phases are clearly sequenced with explicit validation checkpoints (Phase 4 go/no-go gate, Phase 6 mandatory proof, Finalization gate), feedback loops (retry once, escalate to shell_agent), and checklists (criterion status vocabulary) for a destructive/batch operation.	5 / 5
Progressive Disclosure	The file has good internal section structure but is a monolithic ~530-line SKILL.md with no bundle files (references/, scripts/, assets/ absent), so content that could be split — the verification script template and shell_agent escalation template — is inlined rather than disclosed one level deep.	3 / 5
	Total	15 / 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 specific and clearly states what the skill does, with a distinct verification-gate niche, but it lacks an explicit 'Use when...' trigger clause and misses common natural synonyms like 'spreadsheet' and '.xlsx'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating or editing Excel spreadsheets (.xlsx) and the result must be verified against a specification.'

Include natural user synonyms such as 'spreadsheet' and the '.xlsx' extension alongside 'Excel workbooks'.

Clarify distinction from the sibling spreadsheet-proof-gate skill to reduce overlap ambiguity at trigger time.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Create or edit Excel workbooks', 'openpyxl-specific pitfall handling', 'anchored preflight audit', 'deterministic post-write proof' — but the actions lean toward methodology framing rather than a broad enumeration of distinct verbs, leaving minor coverage gaps.	4 / 5
Completeness	The 'what' is clearly stated (create/edit workbooks with pitfall handling, audit, and proof) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes 'Excel workbooks' and 'openpyxl' but omits common natural synonyms users actually say such as 'spreadsheet' and the '.xlsx' file extension, so keyword coverage is only partial.	3 / 5
Distinctiveness Conflict Risk	The verification-gate framing and 'openpyxl-specific' scope define a clear niche, but the body itself notes it 'extends the spreadsheet-proof-gate methodology', indicating minor overlap risk with a closely related sibling skill.	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 (537 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/spreadsheet-proof-gate-merged-fedf41/SKILL.md
Commit: 3827781

Reviewed: 5 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.