CtrlK
BlogDocsLog inGet started
Tessl Logo

fallback-file-ops

Use run_shell as fallback when execute_code_sandbox or shell_agent fail on filesystem operations

62

Quality

72%

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/fallback-file-ops/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is well-structured, actionable, and includes explicit verification checkpoints, with only minor redundancy across sections preventing a fully lean token profile.

Suggestions

Consolidate the failure-pattern list so it appears once (either in 'When to Apply' or 'Step 1') instead of being repeated in both.

Remove the duplicate 'mkdir -p for nested structures' guidance from Best Practices since it is already demonstrated in the Procedure and Example code.

DimensionReasoningScore

Conciseness

The body is mostly lean and assumes bash competence, but failure patterns are repeated across 'When to Apply' and 'Step 1', and 'mkdir -p' guidance recurs in examples and Best Practices, so it could be tightened.

2 / 3

Actionability

It provides fully executable commands (mkdir -p, echo redirection, heredoc, test -f/-d, ls -la) with concrete copy-paste-ready examples.

3 / 3

Workflow Clarity

The four-step procedure is clearly sequenced and includes an explicit 'Verify Creation' checkpoint with test commands, satisfying the validation requirement for batch filesystem operations.

3 / 3

Progressive Disclosure

The skill is self-contained, single-purpose, and well-organized into clearly labeled sections (Purpose, When to Apply, Procedure, Example, Best Practices, Pitfalls) with no need for external references.

3 / 3

Total

11

/

12

Passed

Description

60%

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 clearly conveys a narrow fallback niche with explicit what-and-when guidance, but its trigger terms are internal tool names rather than language a user would naturally invoke.

Suggestions

Rewrite the description around user-facing triggers (e.g., 'Use when filesystem operations fail or files/directories are not created as expected') instead of internal tool identifiers.

Add a brief note of the concrete actions covered (mkdir, file write, verify) to broaden specificity beyond a single 'fallback' verb.

DimensionReasoningScore

Specificity

The description names the domain ('filesystem operations') and a concrete action ('Use run_shell as fallback'), but lists only a single fallback action rather than multiple concrete capabilities.

2 / 3

Completeness

It explicitly states both what to do ('Use run_shell as fallback') and when ('when execute_code_sandbox or shell_agent fail on filesystem operations'), with an explicit trigger clause.

3 / 3

Trigger Term Quality

The trigger terms are internal tool identifiers ('run_shell', 'execute_code_sandbox', 'shell_agent') that a user would never naturally say; there are no user-facing natural keywords.

1 / 3

Distinctiveness Conflict Risk

It occupies a clear, narrow niche (fallback triggered by specific tool failures on filesystem ops) that is unlikely to conflict with other skills.

3 / 3

Total

9

/

12

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.