cut-the-curve

The technique catalog: five velocity-matched SEAMS (zoom-through, INVERSE zoom-through, cut-the-curve, waterfall cut, rack-focus blur-cut) plus the two in-scene techniques — waterfall ENTRY (staggered arrival cascades for title cards / segment openers) and the nudge curve (slow-fast-slow three-phase group slides). Covers partial-travel (~12% of frame) velocity matching via mirrored power4 eases, the Z scale-sign rule, size-scaled blur (10px text / 18-20px full-frame), word-by-word staggered cuts, cascade pacing by element weight, and the 10/65/25 slide ratio. Read before authoring any transition, text-beat handoff, kinetic text entry, or group reposition. [depth, zoom, inverse-zoom, scale-sign, mirrored-zoom, rack-focus, pacing, velocity, cut-the-curve, waterfall, stagger, cascade, kinetic-text, title-card, segment-opener, nudge, slide, easing, group-motion, z-depth, motion-graphics, cinematic, transition, blur, directional-continuity]

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/cut-the-curve/SKILL.md

Quality

Content

57%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-organized, parameter-rich reference catalog that assumes competence and avoids basic-concept padding, but it is not self-sufficient: all executable code and several referenced doctrine files are missing from the bundle, leaving the deferred content inaccessible.

Suggestions

Inline at least one complete, copy-paste GSAP code template (worker + registry) for the common cut-the-curve and zoom-through cases so the skill is actionable without the external file.

Bundle examples/gsap-implementation.md, motion-doctrine, and seam-craft, or remove the dangling references — the primary deferred code file is currently absent, breaking progressive disclosure.

Add an explicit authoring workflow with verification checkpoints (choose variant via the Choosing table → set parameters → verify velocity match at cut±0.1s against the Anti-Patterns checklist) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is dense and parameter-driven, assuming GSAP/motion-graphics competence without explaining basics, with every line carrying a value or rule; minor redundancy between the Catalog, per-technique, and Choosing-a-Variant tables plus a few evocative 'feel' phrases keep it just short of the lean anchor.	4 / 5
Actionability	Parameter tables are concrete and complete (scales 1→1.2 / 0.75→1, blur 10px, eases power3.in/expo.out, travel ±230px, stagger +0.022s, 0.05s×0.84 decay), but the body contains no assembled, executable code — all GSAP templates are deferred to a file that is not bundled, which is more than a minor gap for a code skill.	3 / 5
Workflow Clarity	A loose sequence exists (Catalog → per-technique detail → Choosing a Variant → Anti-Patterns) and the Anti-Patterns table acts as a soft checklist, but there is no explicit ordered authoring workflow with validation checkpoints; verification hints like 'verify at cut±0.1s' and 'Verify per Seam Gate rule 7' are implicit rather than framed as steps.	3 / 5
Progressive Disclosure	The SKILL.md is well-sectioned and the deferred reference is prominently signaled ('All GSAP code templates ... live in examples/gsap-implementation.md'), but no bundle files exist — examples/gsap-implementation.md, motion-doctrine, and seam-craft are all absent — so the one-level-deep reference the structure relies on is broken and navigation fails.	3 / 5
	Total	13 / 20 Passed

Description

92%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 explicitly covers both capability and trigger context with a rich keyword set. Its only weakness is a tilt toward technical jargon over the most natural user phrasings in the trigger-term list.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates all seven techniques with concrete parameters — 'partial-travel (~12% of frame) velocity matching via mirrored power4 eases', 'size-scaled blur (10px text / 18-20px full-frame)', 'the 10/65/25 slide ratio' — giving comprehensive, specific coverage rather than vague actions.	5 / 5
Completeness	It states both what ('The technique catalog: five velocity-matched SEAMS ... plus the two in-scene techniques ... Covers ...') and an explicit when ('Read before authoring any transition, text-beat handoff, kinetic text entry, or group reposition'), matching the anchor that requires concrete trigger phrases for both.	5 / 5
Trigger Term Quality	The bracketed keyword list is broad ('transition', 'kinetic-text', 'title-card', 'motion-graphics', 'cinematic', 'waterfall', 'rack-focus') with synonyms, but it leans heavily on technical jargon ('scale-sign', 'mirrored-zoom', 'z-depth', 'directional-continuity') over the most natural user phrasings, so it stops short of the comprehensive-natural-terms anchor.	4 / 5
Distinctiveness Conflict Risk	It occupies a clearly defined niche (cinematic motion-graphics seam/transition parameters) with distinctive triggers ('cut-the-curve', 'waterfall cut', 'rack-focus blur-cut', 'nudge curve') that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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: heygen-com/hyperframes
Path: .agents/skills/cut-the-curve/SKILL.md
Commit: a562946

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

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.