CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

operational-enterprise-ai

Create or redesign enterprise AI, automation, security, and operations product pages that explain system boundaries, approvals, auditability, exceptions, and rollback. Use for dark cinematic heroes, hairline grids, metric pauses, expandable solution rows, case-study evidence, security proof, and qualified demo or waitlist handoffs.

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 disciplined, well-structured instruction-only skill: every section is dense with specific, verifiable design direction and closes with a validation checklist. The gaps are consistency-level — minor duplication in "Avoid", no concrete markup or copy examples, and no explicit fix-and-revalidate loop — rather than structural ones.

Suggestions

Add a small concrete artifact to the solution-row or hero sections — a sample row markup skeleton or a short copy pattern showing boundary/approval/rollback phrasing — to lift actionability from directive to executable.

Turn the Validate checklist into a feedback loop: state that on any failed check, fix and re-run the check before proceeding (and what to do when evidence cannot be verified).

Deduplicate the "Avoid" section against earlier sections (glowing orbs and fake metrics are already covered) and consider moving the detailed state-model lists for solution rows into a one-level-deep reference file.

DimensionReasoningScore

Conciseness

The body is lean and imperative throughout — no explanations of concepts Claude already knows, no padded prose — but the "Avoid" section largely restates guidance already given (glowing orbs and fake metrics appear in both "Build the Visual System" and "Avoid"), a minor inefficiency keeping it below the every-token-earns-its-place anchor.

4 / 5

Actionability

Guidance is unusually specific for an instruction-only skill: exact durations ("160–220ms for controls and 500–760ms for section entrances", "parallax below 5%"), a section-by-section page composition, and enumerated states (loading, denied approval, rollback). Not a 5 because there are no concrete examples — no sample markup, component skeleton, or copy pattern to anchor directives like "one restrained spectral treatment" or "metric pauses".

4 / 5

Workflow Clarity

"Establish the Story" gives a clear 5-step sequence and a dedicated "Validate" checklist (metrics vs. evidence, keyboard/touch testing, contrast, reduced motion) covering most checkpoints. Missing the explicit fix-and-revalidate feedback loop of the 5 anchor, though it is well above the sequence-without-validation anchors at 3 and below.

4 / 5

Progressive Disclosure

Well-organized sections with nothing buried and no unnecessary references; the skill is self-contained. Not a 5: at roughly 76 lines it exceeds the under-50-line simple-skill case, and detailed material (the full state-model lists for solution rows and the motion/interaction specs) could be split into one-level-deep reference files to keep SKILL.md a tighter overview.

4 / 5

Total

16

/

20

Passed

Description

83%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 strong description: concrete, third-person capability statement paired with an explicit and itemized "Use for" trigger clause. Its main weakness is trigger vocabulary that favors design jargon over the everyday phrases (landing page, website, marketing site) users would naturally say.

DimensionReasoningScore

Specificity

"Create or redesign enterprise AI, automation, security, and operations product pages that explain system boundaries, approvals, auditability, exceptions, and rollback" names several concrete actions and content dimensions in third person. Falls short of the 5 anchor's comprehensive coverage because it never states the deliverable format (e.g., HTML page, design mockup) and omits validation/maintenance actions; clearly above anchor 3, which allows only 1-2 concrete actions.

4 / 5

Completeness

Explicitly answers both: "what" — create or redesign enterprise product pages that explain system boundaries, approvals, auditability, exceptions, and rollback — and "when" — "Use for dark cinematic heroes, hairline grids, metric pauses, expandable solution rows, case-study evidence, security proof, and qualified demo or waitlist handoffs" with concrete trigger phrases. Matches the 5 anchor's pattern of a clear what plus an explicit, itemized when-clause.

5 / 5

Trigger Term Quality

Includes natural phrases a user might say such as "product pages", "dark cinematic heroes", "case-study evidence", and "security proof", giving good keyword coverage. Not a 5: it misses common variations users actually say — "landing page", "website", "marketing site", "SaaS" — and leans on design jargon ("metric pauses", "hairline grids") over user vocabulary.

4 / 5

Distinctiveness Conflict Risk

The operational-evidence niche (approvals, auditability, exceptions, rollback, qualified handoffs) is a distinct positioning unlikely to grab unrelated skills. Only a 4 rather than 5 because the visual triggers (dark cinematic hero, metric sections) overlap with generic dark-tech landing page skills, creating minor conflict risk.

4 / 5

Total

17

/

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

MengTo/Skills

Path

agent-skills/web-design/operational-enterprise-ai/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.