CtrlK
BlogDocsLog inGet started
Tessl Logo

code-runner

Execute code in multiple programming languages. Use when the user asks to run, test, or debug code in Python, JavaScript, shell, or other languages.

68

Quality

83%

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.

A concise, actionable, well-organized simple skill with executable examples and a clear error-recovery loop. Its only weakness is minor redundant restatement in the error-handling section.

Suggestions

Trim the 'Common issues' line to non-obvious guidance only, since missing packages / syntax errors / permission paths are already covered by the Guidelines and are knowledge Claude has.

DimensionReasoningScore

Conciseness

The body is mostly lean and code-forward, but the error-handling list ('Common issues: missing packages (install them), syntax errors (fix them), permission denied (use appropriate paths)') restates obvious knowledge Claude already has and could be tightened.

2 / 3

Actionability

Provides concrete, copy-paste-ready commands for Python, Shell, and Node (e.g. `python3 -c "print('hello')"`, `node -e "console.log('hello')"`) plus specific install guidance.

3 / 3

Workflow Clarity

A simple single-action skill with an unambiguous action and an explicit fix-then-retry feedback loop ('Always retry at least once after fixing the issue'), which the simple-skills note allows to score 3.

3 / 3

Progressive Disclosure

Under 50 lines with no bundle files and well-organized sections (Available Languages, Guidelines, Error Handling); per the scoring notes this earns a 3 with no external references needed.

3 / 3

Total

11

/

12

Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A clear, well-triggered description that answers both what and when with natural user terms. It is held back from the top tier by generic action verbs and a broad 'other languages' clause that raises overlap risk.

Suggestions

Replace generic verbs with more concrete operations to lift specificity, e.g. 'Run scripts, execute one-liners, install packages, and debug errors' across the named languages.

Tighten 'or other languages' or list the additional languages to reduce overlap with dedicated language-specific or debugging skills.

DimensionReasoningScore

Specificity

Names the domain ('Execute code in multiple programming languages') and verbs ('run, test, or debug') plus named languages, but the actions are generic verbs rather than the distinct concrete operations (e.g. extract/fill/merge) the top anchor requires.

2 / 3

Completeness

Explicitly answers what ('Execute code in multiple programming languages') and when via a clear 'Use when...' trigger clause, matching the top anchor.

3 / 3

Trigger Term Quality

'run, test, or debug code in Python, JavaScript, shell' covers natural terms a user would actually say when they need this skill.

3 / 3

Distinctiveness Conflict Risk

The niche is mostly distinct, but the broad 'or other languages' and generic run/test/debug verbs could overlap with language-specific or dedicated debugging skills.

2 / 3

Total

10

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
fastclaw-ai/fastclaw
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.