CtrlK
BlogDocsLog inGet started
Tessl Logo

run-shell-fallback

Use run_shell with inline Python as a reliable fallback when execute_code_sandbox or read_file fail

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/run-shell-fallback/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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, copy-paste-ready fallback snippets and clean section organization. Its main weaknesses are redundant code examples that inflate token usage and a decision flow lacking explicit verification that the fallback succeeded.

Suggestions

Consolidate the redundant one-liner and heredoc examples; keep one canonical example of each pattern and drop the near-duplicate blocks in the 'Examples' section.

Add an explicit validation step to the decision flow (e.g., 'Check run_shell stdout/stderr; if it failed, fall back to writing a temporary script file') to close the verification gap.

Consider trimming the 'Best Practices' list, which restates information already implied by the code examples.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but it repeats near-identical heredoc and one-liner blocks across the 'How to Implement' and 'Examples' sections, which could be tightened, matching anchor 2.

2 / 3

Actionability

It provides concrete, executable, copy-paste-ready run_shell(command=...) snippets for both one-liners and heredocs, matching the fully-executable anchor 3.

3 / 3

Workflow Clarity

The 'Decision Flow' lists a sequenced process, but there is no explicit validation/verification that the run_shell fallback actually succeeded before proceeding, so it sits at anchor 2 rather than the checkpointed anchor 3.

2 / 3

Progressive Disclosure

No bundle files exist and the single self-contained file is organized into clearly labeled sections (When to Use, How to Implement, Best Practices, Examples, Limitations), which for a simple single-purpose skill meets the anchor 3 bar.

3 / 3

Total

10

/

12

Passed

Description

67%

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 answers both what it does and when to use it with an explicit trigger, but it relies on technical tool names rather than natural user language and names only one concrete action. It is distinct enough but could conflict with general shell-coding skills.

Suggestions

Add natural-language trigger terms a user might actually say (e.g., 'when the code tool errors out' or 'can't read a file') alongside the tool names.

Mention a second concrete action (e.g., parsing output, writing results to a file) to lift specificity from a single action to multiple.

Tighten the distinctiveness by scoping the niche, e.g., noting it is a fallback specifically for 'unknown error' failures rather than general shell execution.

DimensionReasoningScore

Specificity

It names a concrete action ('Use run_shell with inline Python as a reliable fallback') but only a single action rather than multiple specific ones, fitting anchor 2 rather than the multi-action anchor 3.

2 / 3

Completeness

It explicitly answers what ('Use run_shell with inline Python as a reliable fallback') and when ('when execute_code_sandbox or read_file fail'), matching the both-what-and-when anchor 3.

3 / 3

Trigger Term Quality

It surfaces relevant trigger keywords ('execute_code_sandbox', 'read_file', 'run_shell'), but these are API/tool identifiers rather than natural terms a user would say, so it lands at anchor 2 rather than the natural-coverage anchor 3.

2 / 3

Distinctiveness Conflict Risk

The failure-triggered fallback niche is somewhat specific, but 'run_shell with inline Python' is broadly applicable and could overlap with many general coding skills, so it sits at anchor 2 rather than a clearly non-conflicting anchor 3.

2 / 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.