bash

How to use the shell successfully

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/bash/SKILL.md

Quality

Content

100%

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

The body is an exemplary lean, actionable single-purpose skill: it gives one concrete executable pattern with no padding. The only defect is a wording error ("makes sure the shell is polluted" should read "isn't polluted"), which does not affect the rubric dimensions but should be corrected.

Dimension	Reasoning	Score
Conciseness	The body is six lines, assumes Claude's competence, and contains no unnecessary explanation — every token earns its place, matching the score-3 lean anchor.	3 / 3
Actionability	It gives the concrete, executable pattern `bash -c 'command'` that is copy-paste ready, matching the score-3 anchor for fully executable commands.	3 / 3
Workflow Clarity	This is a simple single-purpose skill whose single action (run a command in its own bash shell) is unambiguous, so per the simple-skills scoring note it qualifies for score 3 without a multi-step workflow.	3 / 3
Progressive Disclosure	The skill is under 50 lines and needs no external references, and the bundle directories (references/scripts/assets) are absent, so per the scoring note well-organized inline content is sufficient for score 3.	3 / 3
	Total	12 / 12 Passed

Description

15%

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 too vague to function as an effective skill trigger: it states no concrete capabilities, provides no usage triggers, and is indistinguishable from generic shell guidance. The body is strong, but the frontmatter description fails to communicate what the skill does or when to invoke it.

Suggestions

Rewrite the description to list concrete actions, e.g. "Runs shell commands in an isolated bash subprocess so execution is unaffected by the parent shell's state. Use when running shell commands, scripts, or CLI tools that must not inherit outside environment or shell state."

Add an explicit "Use when..." clause with natural trigger terms such as "bash", "shell commands", "terminal", "command line", and "isolated environment".

Tighten the wording so the skill is clearly distinguishable from general shell-usage skills — name the isolation/isolation-from-state behavior that makes this skill unique.

Dimension	Reasoning	Score
Specificity	"How to use the shell successfully" names no concrete actions — it is as vague as "Helps with documents", so it matches the lowest anchor rather than the score-2 anchor that names a domain plus some actions.	1 / 3
Completeness	The "what" is only weakly stated ("use the shell") and the "when" is entirely absent with no "Use when..." clause, matching the score-1 anchor where both are very weak or missing; it cannot reach score 2 because there is no real trigger guidance.	1 / 3
Trigger Term Quality	"shell" is a natural keyword, but the description omits common variations a user would actually say ("bash", "commands", "terminal", "command line"), matching the score-2 anchor rather than the broad coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	"How to use the shell successfully" is generic enough to overlap with many shell-adjacent skills and lacks a distinct niche, matching the score-1 anchor rather than the somewhat-specific score 2.	1 / 3
	Total	5 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pgdogdev/pgdog
Path: .claude/skills/bash/SKILL.md
Commit: c4f63fd

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.