Strip last component from file name. Use when extracting the directory path from a full file path.
67
80%
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 ./.flox/pkgs/skill-coreutils/skills/dirname/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.
This is a concise, well-structured description for a very narrow skill. It correctly uses third person voice, includes an explicit 'Use when' clause, and clearly defines its niche. However, it could benefit from additional trigger terms that users might naturally use (e.g., 'dirname', 'parent directory') and slightly more detail about the specific action.
Suggestions
Add natural trigger terms users might say, such as 'dirname', 'parent directory', 'parent folder', or 'remove filename from path'.
Consider mentioning related variations like 'get directory from file path' or 'path without filename' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Describes one concrete action ('strip last component from file name') and one use case ('extracting the directory path'), but it's a single narrow action rather than multiple specific capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' ('Strip last component from file name') and 'when' ('Use when extracting the directory path from a full file path'), with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'directory path', 'file path', and 'file name', but misses common variations users might say such as 'dirname', 'parent directory', 'basename', 'path manipulation', or specific commands like 'dirname'. | 2 / 3 |
Distinctiveness Conflict Risk | Very narrow and specific niche — stripping the last component from a file path is a distinct operation unlikely to conflict with other skills. The trigger is precise enough to avoid false matches. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A solid reference skill for the `dirname` command with practical, executable examples and useful gotchas. The content is well-structured and actionable, though it could be slightly more concise by dropping obvious flags (--help, --version) and trimming some inline comments that Claude wouldn't need.
Suggestions
Remove the --help and --version flags from the table as these are universal and Claude already knows about them.
Trim inline comments in examples where the command output already makes the behavior obvious.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some content Claude already knows (basic synopsis format, flag table for --help and --version). The examples section is useful but slightly verbose with comments that could be trimmed. | 2 / 3 |
Actionability | All examples are concrete, executable bash commands with expected outputs. The shell scripting patterns (getting script directory, navigating to it) are copy-paste ready and practically useful. | 3 / 3 |
Workflow Clarity | This is a simple single-purpose skill (a single command), so no multi-step workflow is needed. The examples progress logically from basic to practical scripting use cases, and the gotchas section clearly addresses edge cases. | 3 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized into clear sections (synopsis, flags, examples, gotchas) that are easy to scan. | 3 / 3 |
Total | 11 / 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.
bb1f07d
Table of Contents
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.