CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hig-components-dialogs

Apple HIG guidance for presentation components including alerts, action sheets, popovers, sheets, and digit entry views.

Quality

72%

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/hig-components-dialogs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 overview skill: lean principle summaries, an excellent one-level-deep reference table pointing at real files, and specific actionable rules with a defined output format. Its main weaknesses are an implicit rather than explicit workflow sequence and a pointless boilerplate 'When to Use' section at the end.

Suggestions

Add an explicit numbered workflow, e.g.: 1. Check .claude/apple-design-context.md for existing context; 2. Ask the listed questions to fill gaps; 3. Consult the relevant reference(s) from the index; 4. Produce output in the defined format.

Delete the boilerplate 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview.') — it is generic filler that adds no information.

Add one worked example of a full recommendation (scenario → chosen component → rationale → sample alert/sheet text) to make the output format concrete.

DimensionReasoningScore

Conciseness

The body is efficient: ten principles each stated in 1–2 sentences with no padding and no explanation of concepts Claude already knows; detail is correctly deferred to references. Minor trimming targets keep it from anchor 5 — the boilerplate closing section 'This skill is applicable to execute the workflow or actions described in the overview' earns nothing, and the attribution footer plus 'Related Skills' cross-listing add tokens with marginal value.

4 / 5

Actionability

The guidance is concrete and executable for an instruction-only skill: 'Button labels should be specific verbs ("Delete", "Save"), not "OK"', 'Destructive button style (red text)', 'On action sheets, cancel appears at the bottom, separated', plus a defined four-part output format and a question checklist. It is not anchor 5 because there is no worked example of a complete recommendation (e.g., a sample scenario mapped to a chosen component and alert text), leaving minor gaps in covering common cases.

4 / 5

Workflow Clarity

A workflow exists in pieces — 'Check for .claude/apple-design-context.md before asking questions', 'Questions to Ask', 'Reference Index', 'Output Format' — but it is never sequenced into an explicit ordered process (ask first or consult references first?), and there are no validation checkpoints (e.g., verifying a recommendation against the relevant reference before answering). This matches anchor 3: sequence present but implicit, checkpoints missing. No destructive/batch cap applies since the skill is advisory.

3 / 5

Progressive Disclosure

The body is a lean overview with a well-signaled reference index table ('[alerts.md](references/alerts.md)' etc.) giving topic and key content for each of five references; all five files exist, are one level deep, and contain no nested references. This matches anchor 5: clear overview, well-signaled one-level-deep references, content appropriately split, easy navigation.

5 / 5

Total

16

/

20

Passed

Description

61%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.

A well-scoped, domain-specific description that clearly identifies its subject matter through five concrete component names, but it is a noun phrase rather than a capability statement: it contains no action verbs and no 'Use when' trigger clause. Adding explicit usage triggers would move it from adequate to strong.

Suggestions

Add an explicit trigger clause, e.g. 'Use when designing or reviewing iOS, iPadOS, macOS, or visionOS interfaces that present alerts, action sheets, popovers, sheets, or PIN/digit entry, or when choosing among presentation components.'

State the skill's actions, e.g. 'Evaluates and recommends Apple HIG presentation components...' rather than the bare noun 'guidance'.

Include common synonyms users say — 'dialogs', 'modals', 'prompts', 'confirmation dialogs', 'PIN entry' — to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ('Apple HIG guidance for presentation components') and enumerates five concrete component categories ('alerts, action sheets, popovers, sheets, and digit entry views'), giving clear scope. However, it states no concrete actions — only the generic noun 'guidance' — so it does not reach anchor 4's 'several specific actions', while the five named components lift it above anchor 2's minimal/generic coverage.

3 / 5

Completeness

The 'what' is clear (HIG guidance for the five listed presentation components), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description — the 'when' is entirely absent, which per the judging guidelines caps completeness at 3. This matches anchor 3 ('clear what but when missing or only weakly implied') and is not anchor 4, which requires both present.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'alerts', 'action sheets', 'popovers', 'sheets', 'digit entry views', 'Apple HIG'. Common variations a user might say are missing — 'dialog', 'modal', 'prompt', 'confirmation dialog', 'PIN entry' — so it stops short of anchor 5's comprehensive synonym coverage, but coverage is clearly better than anchor 3's partial keyword set.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche with distinct component-name triggers (alerts, action sheets, popovers, sheets, digit entry), largely matching anchor 5. It scores 4 rather than 5 because the broad phrase 'Apple HIG guidance' overlaps with sibling HIG skills (modality patterns, menus, controls) that cover adjacent territory, leaving minor overlap risk with closely related skills — exactly anchor 4.

4 / 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/hig-components-dialogs/SKILL.md

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.