excel-creation-fallback

Use shell_agent as fallback when execute_code_sandbox fails for Excel file operations

Quality

76%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable code, clear delegation templates, and a well-sequenced workflow including verification and recovery. The main weaknesses are some redundancy in the examples/table and the lack of any progressive disclosure for a moderately long single-file skill.

Suggestions

Trim the redundant example task descriptions and the "Why This Pattern Works" table, or move them to a separate EXAMPLES.md reference to reduce inline tokens while preserving detail.

Consolidate the three example task templates into a single parameterized template covering basic, formatted, and tiered cases to reduce repetition.

If the skill grows further, split the example/troubleshooting material into clearly signaled one-level-deep reference files so the main SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with actionable sections, but the "Why This Pattern Works" comparison table and three largely overlapping example task descriptions add length that could be trimmed, fitting the 'Mostly efficient but includes some unnecessary explanation or could be tightened' anchor rather than the lean top level.	2 / 3
Actionability	Step 1 provides executable openpyxl code ("from openpyxl import Workbook ... wb.save('output.xlsx')") and Step 2 supplies copy-paste delegation templates, matching the 'Fully executable code/commands; copy-paste ready' anchor; it is not 2 because the guidance is concrete rather than pseudocode.	3 / 3
Workflow Clarity	The Step 1 -> Step 2 -> Step 3 sequence is explicit, with a verification checkpoint ("Confirm the file was created successfully") and error-recovery guidance in Troubleshooting, matching the 'Clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	3 / 3
Progressive Disclosure	The skill is a single ~100-line file with well-organized sections but no external references, and the example templates could plausibly live in a separate file; at over 50 lines it does not qualify for the simple-skill exemption, fitting the 'Some structure but could be better organized; content that should be separate is inline' anchor rather than the top level.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 concise and clearly states both what it does and an explicit when trigger, with a distinct niche. It is held back only by relying on internal tool names and a single named action rather than richer, user-natural trigger terms.

Suggestions

Add user-natural trigger terms alongside the internal tool names, e.g. "spreadsheets", ".xlsx", "openpyxl", or "create Excel files", so users' phrasing matches the skill.

Expand the action list beyond the single "fallback" action to concrete capabilities, such as installing dependencies, writing and running Excel code, and verifying the file was created.

Consider framing the trigger from the user's perspective (e.g. "Use when Excel file creation or editing fails in the sandbox") to broaden natural-language matching.

Dimension	Reasoning	Score
Specificity	Quotes "Use shell_agent as fallback" and "Excel file operations" name the domain and one concrete action, but only a single action is given rather than multiple, matching the 'Names domain and some actions, but not comprehensive' anchor and falling short of the 'Lists multiple specific concrete actions' level.	2 / 3
Completeness	"Use shell_agent as fallback" states what the skill does and "when execute_code_sandbox fails for Excel file operations" gives an explicit when trigger, clearly answering both what and when as the top anchor requires; it is not the level below because the when clause is explicit rather than merely implied.	3 / 3
Trigger Term Quality	"Excel file operations" is a relevant keyword, but the trigger leans on internal tool names ("execute_code_sandbox", "shell_agent") and omits common user variations like spreadsheets, .xlsx, or openpyxl, fitting the 'Some relevant keywords but missing common variations' anchor rather than the full-coverage level.	2 / 3
Distinctiveness Conflict Risk	The narrow fallback-for-Excel-sandbox-failures niche is distinct and unlikely to trigger competing skills, matching the 'Clear niche with distinct triggers' anchor; it is not 2 because the trigger is specific rather than broadly overlapping.	3 / 3
	Total	10 / 12 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: 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.