ls
List directory contents. Use when you need to view files in a directory, check permissions, sizes, timestamps, or sort/filter file listings.
72
64%
Does it follow best practices?
Impact
74%
1.08xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.flox/pkgs/skill-coreutils/skills/ls/SKILL.mdQuality
Discovery
89%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 well-crafted skill description that clearly communicates its purpose and when to use it. It includes an explicit 'Use when' clause with relevant trigger terms that users would naturally employ. The only minor weakness is that the capability description could list more distinct concrete actions beyond the single core action of listing directory contents.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (directory contents) and some actions (view files, check permissions, sizes, timestamps, sort/filter), but the actions are more like attributes to check rather than distinct concrete operations. It's between 2 and 3 — it lists several specific things but they're all facets of one action (listing directories). | 2 / 3 |
Completeness | Clearly answers both 'what' (list directory contents) and 'when' (explicit 'Use when' clause covering viewing files, checking permissions/sizes/timestamps, sorting/filtering). The trigger guidance is explicit and well-structured. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'directory contents', 'files in a directory', 'permissions', 'sizes', 'timestamps', 'sort', 'filter', 'file listings'. These are terms users naturally use when asking about listing files. | 3 / 3 |
Distinctiveness Conflict Risk | The description is clearly scoped to directory listing operations with specific triggers like permissions, sizes, timestamps, and file listings. This is a distinct niche unlikely to conflict with other skills like file editing, file search, or file creation. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a man page copy for the `ls` command, which Claude already knows thoroughly. The exhaustive flag tables waste significant token budget without adding value. The Gotchas section is the only genuinely useful part, containing non-obvious pitfalls that could prevent errors.
Suggestions
Remove the exhaustive flag tables entirely — Claude already knows ls flags. Keep only the Gotchas section and a few non-obvious examples.
Focus the skill on what Claude might get wrong: the 'do not parse ls output' warning, locale-dependent sorting, and symlink behavior are the high-value content.
If a comprehensive flag reference is desired, move it to a separate REFERENCE.md and keep SKILL.md to under 30 lines with just the essential guidance and gotchas.
Add actionable guidance for common tasks like 'when the user asks to list files, prefer find over ls for scriptable output' rather than just listing flags.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is essentially a man page reproduction. Claude already knows the ls command and all its flags. The exhaustive flag tables (60+ flags) add no value that Claude doesn't already have. Only the Gotchas section and perhaps the examples add marginal new information. | 1 / 3 |
Actionability | The examples section provides concrete, executable commands which is good. However, the bulk of the content is a reference table rather than actionable guidance for specific tasks. There's no guidance on when to choose one approach over another or how to solve common problems. | 2 / 3 |
Workflow Clarity | This is a simple, single-purpose skill (listing directory contents) with no multi-step process or destructive operations. The examples are clear and unambiguous, and the Gotchas section provides important caveats. For a single-command skill, this level of clarity is sufficient. | 3 / 3 |
Progressive Disclosure | The content is a monolithic wall of flag tables that could easily be condensed. There's no progressive structure — everything is dumped at the same level. The massive flag reference tables should either be omitted entirely (Claude knows them) or placed in a separate reference file with only the most important/surprising flags highlighted in the main skill. | 1 / 3 |
Total | 7 / 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
- flox/floxenvs
- Commit
bb1f07d
- 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.