CtrlK
BlogDocsLog inGet started
Tessl Logo

robust-file-creation

Fallback to run_shell and write_file when execute_code_sandbox or shell_agent fail on filesystem operations

70

Quality

85%

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

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 content is well-structured and actionable with a clear validated workflow and concrete commands. Its only notable weakness is mild verbosity in the explanatory 'Why This Works' and best-practices sections.

Suggestions

Trim or remove the 'Why This Works' section since it explains concepts Claude already knows about direct shell execution and primitive file writes.

Condense the Best Practices and Anti-Patterns lists into a single tighter guidance block to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining basic filesystem concepts, but the 'Why This Works' section restates principles Claude already knows (run_shell executes directly, write_file is a primitive) and the Best Practices/Anti-Patterns lists add mild padding, so it does not fully meet the lean 'every token earns its place' anchor.

2 / 3

Actionability

It gives concrete, specific commands for each step ("run_shell command=\"mkdir -p /path/to/nested/directory\"" and "write_file path=\"/path/to/file.py\" content=\"...\"") plus a complete worked example flow, providing copy-paste-ready guidance.

3 / 3

Workflow Clarity

The four-step sequence (Detect failure, Create directories, Write files, Verify) is clearly ordered with an explicit validation checkpoint (Step 4 verify via ls/tree) and error-recovery guidance, matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

This is a single-purpose, self-contained skill with no bundle files and no external references; its content is organized into clear, well-labeled sections (When to Use, Fallback Procedure, Complete Example, Best Practices, Anti-Patterns), meeting the simple-skill well-organized criterion for full marks.

3 / 3

Total

11

/

12

Passed

Description

85%

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 distinct, clearly stating both the fallback action and the triggering failure condition. Its main weakness is that its trigger terms are internal tool jargon rather than natural user language.

Suggestions

Add natural-language trigger terms a user might actually say (e.g., 'unknown error', 'tool failure', 'cannot create files') alongside the internal tool names to broaden trigger_term_quality.

Consider a 'Use when...' phrasing to make the activation condition maximally explicit.

DimensionReasoningScore

Specificity

The description names multiple concrete actions ("run_shell and write_file") tied to specific failing tools ("execute_code_sandbox or shell_agent"), matching the anchor for listing multiple specific concrete actions.

3 / 3

Completeness

It explicitly states both what it does ("Fallback to run_shell and write_file") and when to use it ("when execute_code_sandbox or shell_agent fail on filesystem operations"), satisfying the equivalent-explicit-trigger criterion despite not using the literal "Use when..." phrasing.

3 / 3

Trigger Term Quality

The keywords are internal tool identifiers (execute_code_sandbox, shell_agent, run_shell, write_file) rather than natural terms a user would actually say; it has relevant keywords but misses common natural-language variations, so it sits at the middle anchor rather than 3, and is above the pure-jargon floor of 1 because the failing-tool names are recognizable.

2 / 3

Distinctiveness Conflict Risk

It targets a narrow, specific failure mode of two named internal tools, giving it a clear niche unlikely to trigger for unrelated skills.

3 / 3

Total

11

/

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.