excel-creation-fallback

Use shell_agent as fallback when execute_code_sandbox fails for Excel file operations

Quality

65%

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/excel-creation-fallback/SKILL.md

Quality

Content

67%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 clear, actionable fallback workflow with executable code and concrete delegation templates, plus useful error-recovery guidance. Its main weakness is conciseness: a justificatory comparison table and three overlapping examples add tokens without proportional value.

Suggestions

Trim or remove the "Why This Pattern Works" comparison table; Claude already understands the tradeoffs between a sandbox and a shell agent, and the When-to-Use bullets already convey the decision criteria.

Collapse the three Example Task Descriptions into one canonical example plus a one-line note on variations, reducing redundant tokens.

Promote the buried "Confirm the file was created successfully" bullet into an explicit Step 4 validation checkpoint (e.g., verify the file exists and opens) to strengthen the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with clear sections, but the "Why This Pattern Works" comparison table explains concepts Claude already knows and the three Example Task Descriptions overlap redundantly, so it could be tightened; not verbose enough for a 2 nor lean enough for a 4.	3 / 5
Actionability	Step 1 provides copy-paste-ready openpyxl code and Step 2 gives a concrete delegation task template with worked examples, leaving only minor gaps (the delegation prompt is a template, not literal code), which fits the 'mostly executable' anchor.	4 / 5
Workflow Clarity	Steps 1-3 are clearly sequenced (try sandbox, delegate to shell_agent, let it handle the environment) with a verification mention ("Confirm the file was created successfully") and a Troubleshooting error-recovery section, but the validation checkpoint is implicit in a sub-bullet rather than an explicit step, capping it below 5.	4 / 5
Progressive Disclosure	Content is well-organized under clear section headers with no bundle files to navigate; at roughly 100 lines it exceeds the under-50-line exception for a 5, and the inlined example/task-description bulk could conceivably be split out, so it sits at 'good structure, minor organization gaps'.	4 / 5
	Total	15 / 20 Passed

Description

62%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 cleanly states both purpose and trigger condition in one line, with a distinct niche. It is held back by thin keyword coverage (missing spreadsheet/.xlsx synonyms) and a single concrete action rather than comprehensive capability listing.

Suggestions

Add natural user-facing trigger terms and synonyms, e.g. "Excel files, spreadsheets, .xlsx" so the description matches how users actually phrase the need.

Broaden the capability statement beyond the single fallback action to enumerate what gets done (create, modify, format Excel files) for stronger specificity.

Consider framing the when-clause around the user's goal (creating/modifying Excel files when the sandbox path fails) rather than only the internal tool failure, to improve triggerability.

Dimension	Reasoning	Score
Specificity	Names the domain ("Excel file operations") and one concrete action ("Use shell_agent as fallback"), but offers only that single action rather than a comprehensive set; fits the '1-2 concrete actions' anchor and is not minimal enough for a 2.	3 / 5
Completeness	Explicitly states both what (use shell_agent as fallback) and when ("when execute_code_sandbox fails for Excel file operations"), but the when is a single trigger condition rather than the multiple concrete trigger phrases that define a 5.	4 / 5
Trigger Term Quality	"Excel file operations" is a relevant keyword, but natural synonyms users say ("spreadsheets", ".xlsx") are absent and the rest ("execute_code_sandbox", "shell_agent") is internal tool jargon rather than user-spoken triggers.	3 / 5
Distinctiveness Conflict Risk	The tool-failure fallback trigger is a distinct niche unlikely to fire for unrelated skills, though the broad "Excel file operations" domain keeps minor overlap risk with a general Excel skill, holding it below 5.	4 / 5
	Total	14 / 20 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/excel-creation-fallback/SKILL.md
Commit: 3827781

Reviewed: 22 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.