CtrlK
BlogDocsLog inGet started
Tessl Logo

meta-refresh

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Avoid meta refresh redirects. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

62

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/meta-refresh/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A well-structured, compact instruction-only skill: the check and fix are specific and unambiguous, the body stays within token budget, and details are appropriately pushed to a single verified reference file. The main weakness is the generic 'Code Review' boilerplate about roles, focus, and keyboard interactions, which is misaligned with a meta-refresh rule and could be cut.

DimensionReasoningScore

Conciseness

The body is lean and well-budgeted ('Check the HTML for any meta tags that use `http-equiv="refresh"`'), but the boilerplate 'Code Review' section ('flag exact elements, roles, labels, focus behavior, or keyboard interactions') is largely irrelevant to a meta refresh rule and the one-line intro restates a concept Claude already knows, so a trim is possible.

4 / 5

Actionability

The check is fully concrete — a grep-able pattern ('meta tags that use `http-equiv="refresh"`') — and the fix names concrete alternatives ('server-side redirects (301 or 302)', 'clear, user-initiated links'), though no inline markup or redirect-config example is given (those live in references/rule.md), leaving minor gaps.

4 / 5

Workflow Clarity

This is a simple, single-purpose skill under 50 lines and the single action is unambiguous: Check ('Check the HTML for any meta tags that use `http-equiv="refresh"`') then Fix ('Replace meta refresh redirects with server-side redirects or clear, user-initiated links'), with an Explain step and verification guidance deferred to the reference — the simple-skill exception applies since no destructive or batch operations are involved.

5 / 5

Progressive Disclosure

The body is a concise overview that clearly signals one exactly-one-level-deep reference ('For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`'), and the bundle structure matches: references/rule.md exists and carries the code example, why-it-matters detail, and verification steps.

5 / 5

Total

18

/

20

Passed

Description

63%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 has an explicit trigger clause and several concrete-sounding actions, but it reads like a generic accessibility-review template wrapped around the rule name: the stated actions (keyboard, focus, accessible names) do not match the skill's actual purpose of detecting and replacing meta refresh redirects. This weakens trigger-term quality and distinctiveness against sibling accessibility skills.

Suggestions

Rewrite the 'what' to match the skill's actual capability, e.g. 'Detects `<meta http-equiv="refresh">` tags in rendered HTML and guides replacement with server-side 301/302 redirects or user-initiated links.'

Add the natural trigger terms users would actually say — 'meta refresh', 'auto redirect', 'page refreshes itself', 'http-equiv refresh' — instead of the generic 'interactive components' and 'design-system patterns' phrasing.

Replace the boilerplate 'Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output' sentence, which is shared across sibling accessibility skills, with rule-specific language so this skill does not fire for unrelated a11y checks.

DimensionReasoningScore

Specificity

It lists several concrete actions — 'Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output' — but the coverage is misaligned with what the skill actually does (detect and replace `<meta http-equiv="refresh">`), so it falls short of the comprehensive 5 anchor while exceeding the 1-2-action 3 anchor.

4 / 5

Completeness

Both parts are explicitly present: a 'Use when reviewing rendered HTML...' trigger clause and a what-portion ('Check native semantics first, then inspect keyboard behavior, focus flow...'), but the 'when' is boilerplate-generic and the 'what' mischaracterizes the skill, so it sits at the 'both present, could be more explicit and specific' anchor rather than 5.

4 / 5

Trigger Term Quality

'meta refresh redirects' and 'rendered HTML' are relevant keywords, but the natural phrases a user would actually say for this rule ('page keeps refreshing', 'auto redirect', 'http-equiv', 'redirect tag') are missing, and the generic 'interactive components, or design-system patterns' terms dominate the trigger surface.

3 / 5

Distinctiveness Conflict Risk

Only the embedded rule name ('related to Avoid meta refresh redirects') distinguishes this description; the rest — 'Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output' — reads as a template shared by every sibling accessibility-rule skill, so it could trigger for the wrong skill in the same family.

3 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
thedaviddias/Front-End-Checklist
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.