bun-shell

Bun shell scripting with Bun.$, Bun.spawn, subprocess management. Use for shell commands, template literals, or command execution.

Quality

66%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/bun/skills/bun-shell/SKILL.md

Quality

Discovery

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 is functional and covers both what and when, earning good marks for completeness. However, it leans on API names rather than describing concrete user-facing actions, and some trigger terms like 'template literals' and 'command execution' are generic enough to risk overlap with other skills. Adding more specific actions and Bun-specific trigger terms would strengthen it.

Suggestions

Add more concrete actions like 'run shell commands, pipe output between processes, read stdout/stderr, handle exit codes' to improve specificity.

Improve trigger term coverage by adding natural variations users might say: 'run a command', 'child process', 'CLI', 'pipe', 'exec in Bun'.

Clarify distinctiveness by emphasizing this is specifically for Bun's runtime APIs (not Node.js child_process or generic bash scripting) in the 'Use when' clause.

Dimension	Reasoning	Score
Specificity	Names the domain (Bun shell scripting) and some specific APIs (Bun.$, Bun.spawn, subprocess management), but doesn't list multiple concrete actions beyond naming the APIs. It tells you what tools are involved but not what you'd do with them (e.g., 'run shell commands', 'pipe output', 'handle exit codes').	2 / 3
Completeness	Clearly answers both 'what' (Bun shell scripting with Bun.$, Bun.spawn, subprocess management) and 'when' ('Use for shell commands, template literals, or command execution'). The explicit 'Use for...' clause provides trigger guidance.	3 / 3
Trigger Term Quality	Includes some relevant keywords like 'shell commands', 'template literals', 'command execution', 'Bun.$', 'Bun.spawn', and 'subprocess'. However, it misses common variations users might say like 'run a command', 'exec', 'child process', 'pipe', 'stdout', or 'CLI'.	2 / 3
Distinctiveness Conflict Risk	The Bun-specific APIs (Bun.$, Bun.spawn) provide some distinctiveness, but 'shell commands' and 'command execution' are generic enough to potentially conflict with general shell scripting or Node.js child_process skills. 'Template literals' is also ambiguous and could overlap with JavaScript string skills.	2 / 3
	Total	9 / 12 Passed

Implementation

64%

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

This skill provides comprehensive, executable coverage of Bun's shell scripting APIs with concrete code examples throughout. Its main weakness is excessive length—much of the content (stdio options, output types, common patterns) could be split into reference files, and there's redundancy in import statements and obvious comments. The error table and reference loading guidance at the end are useful additions.

Suggestions

Move detailed sections (Stdio Options, Output Types, Common Patterns like Git/File Operations) into a separate reference file and link to them, keeping SKILL.md as a concise overview with just the core Bun.$ and Bun.spawn basics

Remove repeated `import { $ } from "bun"` lines after the first occurrence—Claude can infer the import is needed

Remove obvious inline comments like `// Run command`, `// Get output`, `// Text`, `// JSON` that don't add information beyond what the code already shows

Dimension	Reasoning	Score
Conciseness	The content is mostly code-driven with minimal prose, which is good. However, it's quite long with some redundancy (e.g., multiple similar patterns for git operations, repeated `import { $ } from "bun"` statements, and some inline comments that state the obvious like `// Run command`, `// Get output`). The content could be significantly tightened.	2 / 3
Actionability	All examples are fully executable TypeScript code with concrete commands, real API calls, and copy-paste ready snippets. The code covers Bun.$, Bun.spawn, Bun.spawnSync, error handling, output types, and common patterns with specific, working examples.	3 / 3
Workflow Clarity	The content is organized as an API reference rather than a workflow, which is appropriate for this topic. However, the deploy script example shows a multi-step process with validation (checking uncommitted changes), which is good. The skill lacks guidance on when to use `$` vs `spawn` vs `spawnSync`, and the error handling section doesn't provide a clear feedback loop pattern for recovering from failed commands.	2 / 3
Progressive Disclosure	The content has good section structure (Bun.$, Bun.spawn, Shell Scripts, Common Patterns, etc.) and references external files at the end ('When to Load References'). However, the main body is very long with extensive inline content that could be split into separate reference files, and the references section at the bottom feels like an afterthought rather than well-integrated navigation.	2 / 3
	Total	9 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: secondsky/claude-skills
Commit: 88da5ff

Reviewed: 17 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.