CtrlK
BlogDocsLog inGet started
Tessl Logo

livewire-development

Vendor-overridden Livewire skill

50

1.00x
Quality

23%

Does it follow best practices?

Impact

100%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/Fixtures/vendor-skills/livewire-development/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

26%Weight 40%Scale 1-5

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

The SKILL.md body is a two-sentence placeholder containing only harness metadata about vendor discovery and override behavior. It is token-lean but provides zero actionable guidance, no workflow, and no structure — there is no actual skill content to evaluate.

Suggestions

Replace the metadata paragraph with actual Livewire development guidance: concrete examples for common tasks like component creation, actions, properties, and validation, with executable code or commands.

If the skill covers multi-step workflows (e.g., component generation, testing, asset publishing), sequence them as numbered steps with explicit validation checkpoints (e.g., 'run php artisan livewire:check' or equivalent) before proceeding.

Either add real reference files under references/ (e.g., LIVEWIRE_API.md) with clearly signaled links from the body, or — if the skill is genuinely simple — organize the body into well-labeled sections (Quick start, Common patterns) so structure exists without external files.

DimensionReasoningScore

Conciseness

The body is two sentences ('This skill was discovered from a vendor package and should override the built-in .ai/ version.'), with no padding or over-explanation of concepts Claude already knows. The vendor-override metadata is arguably content that belongs elsewhere, but the token cost is trivially small, so it is efficient with minor waste rather than verbose.

4 / 5

Actionability

The body contains no code, commands, or guidance of any kind — it only describes provenance metadata ('discovered from a vendor package', 'should override the built-in .ai/ version') and never instructs the reader on how to do anything. This matches the anchor 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs'.

1 / 5

Workflow Clarity

There is no multi-step process, sequence, or checklist anywhere in the body — it is a single meta-statement. This matches the anchor 'Steps missing or incoherent; no sequence'.

1 / 5

Progressive Disclosure

Structure is minimal: one heading and one paragraph, with no sections, no referenced files, and no bundle files present (references/, scripts/, assets/ do not exist). It is not a wall of text, but it also provides no organization or navigation for any real content, matching 'Minimal structure'.

2 / 5

Total

8

/

20

Passed

Description

20%Weight 40%Scale 1-5

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 'Vendor-overridden Livewire skill' is provenance metadata rather than a capability statement: it names the Livewire domain but conveys no actions, no trigger guidance, and no 'use when' conditions. It is only saved from the lowest scores by the specificity of the word 'Livewire' itself.

Suggestions

Rewrite the description to state concrete capabilities in third person, e.g., 'Develops and debugs Livewire components: actions, properties, validation, events, and JavaScript interop.'

Add an explicit trigger clause, e.g., 'Use when working on Laravel/Livewire code, Livewire components, wire: directives, or Volt classes.'

Drop the 'Vendor-overridden' phrasing from the description — override behavior is harness metadata, not a capability, and consumes the description's entire budget without helping a user decide when to invoke the skill.

DimensionReasoningScore

Specificity

The phrase 'Vendor-overridden Livewire skill' names the domain (Livewire) but describes no actions whatsoever — 'Vendor-overridden' is provenance metadata, not a capability. It falls between anchor 1 ('no concrete actions; pure abstract language') and anchor 2 ('names the domain but actions are minimal or generic'), and since the domain is named it sits at 2.

2 / 5

Completeness

The description answers neither 'what does this do' (no capability is stated — only that it is a vendor override) nor 'when should Claude use it' (no 'Use when...' clause or equivalent). Per the guidelines, a missing trigger clause caps completeness at 3, and here even the 'what' is absent, matching anchor 1 'Missing both what and when, or both are extremely vague'.

1 / 5

Trigger Term Quality

'Livewire' is one relevant keyword a user might say, but there are no natural phrases, variations, or synonyms (e.g., 'Livewire components', 'wire:', 'Volt', 'actions'), and no use-when phrasing. This matches 'One or two... keywords; missing the natural phrases users say' rather than anchor 3, which expects 'some relevant keywords' plus merely missing variations.

2 / 5

Distinctiveness Conflict Risk

'Livewire' is a specific PHP framework, giving a clear niche beyond generic skill descriptions. However, the description does not differentiate this skill from other Livewire-related skills (the body itself notes it overrides a built-in Livewire version, indicating direct naming overlap), matching anchor 3 'Somewhat specific but could still overlap with similar skills'.

3 / 5

Total

8

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
laravel/boost
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.