CtrlK
BlogDocsLog inGet started
Tessl Logo

excel-subtotal-audit

Audit generated Excel reports by enumerating populated output rows, exposing formulas, and checking that each subtotal range includes all visible detail rows.

59

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/excel-subtotal-audit/SKILL.md
SKILL.md
Quality
Evals
Security

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 content is a well-sequenced, actionable validation workflow with strong checkpoints, but it is hurt by redundant restatements of the same procedure and by lack of progressive disclosure for the longer code and example material.

Suggestions

Collapse the redundant restatements: keep one workflow sequence and one code example (Python or pseudocode), removing the overlapping 'Practical procedure' / 'Example audit logic' / 'Example pseudocode' sections.

Move the full Python sketch, adaptation notes, and extended formula-parsing guidance into a reference file (e.g. references/audit-patterns.md) linked from a short 'Advanced patterns' section, so SKILL.md stays a lean overview.

Tighten prose throughout by pruning restated 'Why' rationales that duplicate earlier sections.

DimensionReasoningScore

Conciseness

The body is focused and avoids explaining basic concepts Claude already knows, but it restates the same procedure across 'Workflow 1–7', 'Practical procedure A–C', 'Example pseudocode', and the 'Example Python sketch', which is more than minor padding and could be tightened.

3 / 5

Actionability

Provides an executable openpyxl Python sketch, a concrete failure-message example, and a specific defect taxonomy, but the code is labeled a generic sketch to adapt and only parses simple SUM ranges, leaving minor gaps.

4 / 5

Workflow Clarity

A clear 7-step sequence is paired with explicit validation checkpoints ('Fail loudly on any mismatch', 'Minimum acceptance criteria', 'Definition of done') and checklists; this skill is itself a validation workflow so the missing-validation cap does not apply.

5 / 5

Progressive Disclosure

There are no bundle files and the ~430-line skill is entirely inline; it is well-sectioned, but content that could live in references (the Python sketch, pseudocode, and adaptation notes) is inlined, and the under-50-line simple-skill exception does not apply.

3 / 5

Total

15

/

20

Passed

Description

66%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 action-oriented with a clear narrow niche, but it omits any 'Use when…' trigger guidance, which caps completeness and slightly weakens trigger-term quality and distinctiveness.

Suggestions

Add an explicit 'Use when…' clause naming natural triggers, e.g. 'Use when generating or modifying Excel workbooks with subtotal/total formulas, or when validating .xlsx rollups for correct row coverage.'

Include common synonyms and the file extension (e.g. 'spreadsheets', '.xlsx') to improve trigger-term coverage.

Tie the trigger phrasing to the audit-specific framing to further reduce overlap with generic Excel skills.

DimensionReasoningScore

Specificity

Names the domain (generated Excel reports) and three concrete actions — 'enumerating populated output rows, exposing formulas, and checking that each subtotal range includes all visible detail rows' — which matches the several-specific-actions anchor; not a 5 because coverage of the full audit space is solid rather than exhaustive.

4 / 5

Completeness

It clearly states what the skill does but provides no 'Use when…' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Contains good natural keywords ('Excel reports', 'subtotal', 'formulas', 'detail rows') but omits common synonyms and file extensions like 'spreadsheets' or '.xlsx', so it falls at the good-but-not-comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The subtotal-range-audit niche is narrow and distinct, but it could overlap with a general Excel-reporting skill and lacks explicit triggers to disambiguate, placing it at mostly-distinct rather than minimal-conflict.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
Reviewed

Table of Contents

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.