CtrlK
BlogDocsLog inGet started
Tessl Logo

oversized-cursor

House-style oversized macOS cursor technique for HyperFrames launch videos. Load whenever a scene involves cursors or a pointer-led action, when kicking off a UI scene, when igniting a morph/transition/typing run with a click, or when a scene reads as static, dead, or stale and needs a cheap high-yield source of motion to carry the viewer's eye and segment them out of the stale state. Covers cursor size/look (incl. brand-motif cursors), the off-screen entry law, tip-targeting and the click tap, click-ignites-the-next-beat, and exit / cross-scene handoff.

70

Quality

85%

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

82%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 tight, highly actionable technique guide with executable GSAP/CSS snippets and a clearly sequenced entry→click→exit lifecycle capped by a checklist. The main weaknesses are mild editorial color that could be trimmed and the absence of an explicit error-recovery loop or overview index.

Suggestions

Trim editorial flourishes (e.g. "the power play", "feel like it entered the room", "a cursor nobody recognizes is just a weird arrow") to tighten conciseness without losing the technique specifics.

Add a short validate/review checkpoint or note pairing the final Checklist with a quick render-check step so workflow_clarity reflects an explicit feedback loop.

Lead with a one-line overview or mini-TOC before the first section to aid navigation now that the file is over 50 lines.

DimensionReasoningScore

Conciseness

The body is dense, opinionated, and assumes competence (no explanations of what GSAP or a cursor is), with terse rationale like "Bigger is better — an actual-size cursor disappears at video scale." It is 4 not 5 because a few editorial flourishes ("the power play", "feel like it entered the room", "a cursor nobody recognizes is just a weird arrow") could be trimmed, and 4 not 3 because the bulk is genuinely efficient with no padded concept explanations.

4 / 5

Actionability

Provides copy-paste-ready, complete GSAP and CSS snippets with exact values — `width: 7cqw`, `transformOrigin: '21% 14%'`, `duration: 0.85, ease: 'power3.out'`, the cut-the-curve handoff `gsap.set`/`tl.to` pair — covering the common cases. It is 5 not 4 because the code is fully executable rather than pseudocode with minor gaps.

5 / 5

Workflow Clarity

A clear sequenced lifecycle is laid out across sections (Size & look → Entry law → Tip-targeting & click → Click ignites next beat → Exit & handoff) and a final Checklist provides verification. It is 4 not 5 because there is no explicit validate→fix→retry error-recovery loop, and 4 not 3 because the sequence and a checkpoint (the checklist) are clearly present.

4 / 5

Progressive Disclosure

A single self-contained technique doc with clear section headers and no buried or nested external references (no references/scripts/assets bundle exists), so navigation is easy. It is 4 not 5 because the file exceeds 50 lines and lacks an explicit overview/index or one-level-deep reference pointers, and 4 not 3 because the structure is good rather than merely present with inline clutter.

4 / 5

Total

17

/

20

Passed

Description

87%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, highly specific description that clearly states both what the skill covers and when to load it, with natural trigger phrases and minimal conflict risk. The only soft spot is light domain jargon and the omission of implementation tooling from the capability list.

DimensionReasoningScore

Specificity

Names the technique and enumerates several concrete facets — "cursor size/look (incl. brand-motif cursors), the off-screen entry law, tip-targeting and the click tap, click-ignites-the-next-beat, and exit / cross-scene handoff" — which is comprehensive coverage with only a minor gap (no mention of the GSAP/CSS implementation). It sits at 4 rather than 5 because the facets are governed aspects of a technique rather than a fully exhaustive action list, and at 4 rather than 3 because it lists far more than 1-2 concrete actions.

4 / 5

Completeness

Explicitly answers both halves: the "what" ("House-style oversized macOS cursor technique... Covers cursor size/look... entry law, tip-targeting... exit / cross-scene handoff") and the "when" with concrete "Load whenever..." trigger clauses. It is 5 not 4 because the triggers are concrete and multiple rather than a single weak clause.

5 / 5

Trigger Term Quality

Natural trigger phrases a user would voice are present — "whenever a scene involves cursors or a pointer-led action", "when igniting a morph/transition/typing run with a click", "when a scene reads as static, dead, or stale" — giving good keyword coverage. It is 4 not 5 because some phrasing is jargon-laden ("HyperFrames launch videos", "segment them out of the stale state") and a few plain synonyms are missing, and 4 not 3 because the core terms (cursor, pointer, click, stale) are exactly what a user would say.

4 / 5

Distinctiveness Conflict Risk

A narrow, well-bounded niche — an oversized macOS cursor technique for launch videos — with distinct triggers (cursor/pointer-led scenes, stale scenes), giving minimal overlap risk with other skills. It is 5 not 4 because the triggers are specific enough to avoid firing for unrelated motion or UI skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
heygen-com/hyperframes
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.