CtrlK
BlogDocsLog inGet started
Tessl Logo

bash

How to use the shell successfully

44

Quality

45%

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 ./.claude/skills/bash/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

66%Weight 40%Scale 1-5

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

The body is a brief, mostly executable single-purpose instruction that respects the token budget and needs no external references. Its main weakness is a slightly misleading closing justification and the use of a placeholder command rather than a concrete real-world example.

Suggestions

Replace the `'command'` placeholder with one or two concrete real examples (e.g. `bash -c 'ls -la /tmp'`) to lift actionability toward fully copy-paste-ready guidance.

Fix the inverted wording in the closing sentence: the goal is to avoid pollution, so phrase it as 'This keeps the command from being polluted by any outside shell state.'

Optionally drop 'like so' to tighten the prose further.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence, with only minor padding ('like so' and the brief trailing justification); it fits 'Efficient; minor instances of over-explanation that could be trimmed' rather than 5 because the closing sentence restates an obvious rationale.

4 / 5

Actionability

It provides concrete executable code (`bash -c 'command'`) rather than pseudocode, fitting 'Mostly executable guidance; concrete code or commands with minor gaps'; it is not 5 because `'command'` is a placeholder and no real common-case examples are shown.

4 / 5

Workflow Clarity

The single action (run commands via `bash -c`) is unambiguous, but the closing rationale is slightly muddled ('makes sure the shell is polluted' reads as the opposite of the intent), which keeps it just below the clean 5 a simple skill could earn; it is above 3 because the action is clear and no risky multi-step validation is needed.

4 / 5

Progressive Disclosure

This is a short single-purpose skill under 50 lines with no need for external references, and the single code block is well-organized, matching the simple-skill exception that allows a 5 when content is clear and well-organized.

5 / 5

Total

17

/

20

Passed

Description

25%Weight 40%Scale 1-5

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 a terse, generic statement that names the shell domain but conveys no concrete capabilities or usage triggers. It reads more like a category label than an activation prompt, leaving both the 'what' and 'when' underspecified.

Suggestions

Replace the generic phrasing with specific concrete actions, e.g. 'Run shell commands in an isolated bash subprocess to avoid environment pollution.'

Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g. 'Use when executing shell commands that must not inherit the parent shell's environment or aliases').

Narrow the scope so it is distinguishable from general command-execution skills and unlikely to trigger for unrelated shell tasks.

DimensionReasoningScore

Specificity

The description 'How to use the shell successfully' names the domain (shell) but provides no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'; it does not reach 3 because no specific capability is enumerated.

2 / 5

Completeness

It gives a vague 'what' ('use the shell') with no 'when' or 'Use when...' clause, matching 'Has a vague what and no when'; the missing trigger guidance caps completeness at 3 and this sits below that.

2 / 5

Trigger Term Quality

Only the single generic keyword 'shell' appears with no natural user phrasings or synonyms, fitting 'One or two generic keywords; missing the natural phrases users say'; it is above 1 only because a relevant domain term is present.

2 / 5

Distinctiveness Conflict Risk

'How to use the shell successfully' is very broad and would overlap with many general-purpose or coding skills, fitting 'Very broad; high overlap risk'; it is not 3 because nothing narrows the niche.

2 / 5

Total

8

/

20

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
pgdogdev/pgdog
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.