bun-shell
Bun shell scripting with Bun.$, Bun.spawn, subprocess management. Use for shell commands, template literals, or command execution.
60
70%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/bun/skills/bun-shell/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is functional and well-structured with both 'what' and 'when' clauses, and it carves out a clear niche around Bun-specific shell APIs. Its main weakness is that it could be more specific about the concrete actions it enables (e.g., piping output, reading stdout, handling exit codes) and could include more natural trigger terms users might use.
Suggestions
Add more concrete actions like 'pipe output between commands, read stdout/stderr, handle exit codes, manage child processes'
Expand trigger terms to include variations users might say: 'run a command', 'exec', 'child process', 'CLI', 'pipe', 'stdin', 'stdout'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Bun shell scripting) and some specific APIs (Bun.$, 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 accomplish with them. | 2 / 3 |
Completeness | Clearly answers both 'what' (Bun shell scripting with Bun.$, Bun.spawn, subprocess management) and 'when' (Use for shell commands, template literals, or command execution). The 'Use for...' clause provides explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'shell commands', 'template literals', 'command execution', 'Bun.$', 'Bun.spawn', and 'subprocess'. However, it misses common variations users might say like 'run a command', 'exec', 'child process', 'pipe', 'stdin/stdout', or 'CLI'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to Bun-specific shell scripting APIs (Bun.$, Bun.spawn), which creates a distinct niche unlikely to conflict with general shell scripting or Node.js subprocess skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, executable Bun shell scripting examples with good section organization. Its main weakness is excessive length — much of the content (git operations, file operations, common patterns) could be moved to reference files, and some patterns are ones Claude would already know. The references to non-existent bundle files undermine the progressive disclosure structure.
Suggestions
Move the 'Common Patterns' (npm/bun scripts, git operations, file operations) and 'Complex Script' sections into a separate reference file to reduce the main SKILL.md to core API patterns only.
Remove or consolidate redundant examples — e.g., the Output Types section repeats patterns already shown in Basic Usage, and multiple git examples could be condensed into one block.
Either include the referenced files (references/advanced-scripting.md, references/cross-platform.md) in the bundle or remove the 'When to Load References' section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly code examples with minimal prose, which is good. However, it's quite long with many sections that cover patterns Claude already knows (basic error handling, git operations, file operations). The inline comments like '// Run command', '// Get output', '// Safe interpolation (escaped)' add some unnecessary narration but are relatively brief. | 2 / 3 |
Actionability | All examples are fully executable TypeScript code with concrete, copy-paste ready snippets. The skill covers Bun.$, Bun.spawn, Bun.spawnSync with real commands and complete code blocks including imports, error handling patterns, and output type methods. | 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 'When to Load References' section references files that don't exist in the bundle, and there are no validation checkpoints for shell command execution patterns that could fail. | 2 / 3 |
Progressive Disclosure | The content has clear section headers (Bun.$, Bun.spawn, Shell Scripts, Common Patterns, etc.) and references advanced files at the end. However, the main body is very long with extensive inline content that could be split into separate reference files, and the referenced files (references/advanced-scripting.md, references/cross-platform.md) don't exist in the bundle. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- secondsky/claude-skills
- Commit
5e92b71
- 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.