transitions-polish

Polish and refine existing motion against the transitions.dev motion-token scale — duration, distance, scale, blur, and easing — plus the rules for WHEN each token applies (open/close asymmetry, hover-in vs hover-out, stagger offsets, and intent delays). An add-on to the transitions-dev skill, focused on tuning what already animates rather than adding new transitions. Use when the user asks to "polish my transitions", "refine the motion", "tune the timing / easing", "make the animation feel better / less janky", "tighten the durations", "fix the stagger", "align to the motion tokens", "audit the motion", "review my animations", "scan for ad-hoc transitions", "tokenize my animations", or runs the commands transitions review or transitions polish. Also drives the Refine panel's Small refinement feature. Triggers on "motion polish", "transition polish", "refine motion", "timing feels off", "too slow / too fast", "stagger", "delay", "open close timing", "hover in out".

Quality

96%

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

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body built on project-specific token data and explicit command workflows with confirmation checkpoints. Its main weakness is progressive disclosure: it references _root.css, _refine-rules.md, and the sibling transitions-dev skill, but none of those bundle files are actually present.

Suggestions

Add the missing bundle files _root.css and _refine-rules.md (or remove the links) so the referenced one-level-deep paths resolve instead of dangling.

Consider moving the five token tables into a reference file (e.g. tokens.md) referenced from SKILL.md to reduce inline bulk and improve progressive disclosure.

Trim or drop the "Future expansion" section — aspirational feature lists add tokens without adding executable value.

Dimension	Reasoning	Score
Conciseness	Domain-specific token tables and usage rules (which Claude does not already know) are compressed into compact tables, with no padding explaining basic CSS or transition concepts; nearly every token earns its place. The only soft spots are the philosophical "Core doctrine" prose and the aspirational "Future expansion" list, but these are minor.	3 / 3
Actionability	Provides concrete namespaced commands (transitions review, transitions polish), numbered behaviours, and literal copy-paste output-line examples ("path/to/Component.css:L42 — modal close: 300ms → var(--duration-quick) (150ms)") that are fully executable guidance.	3 / 3
Workflow Clarity	Both commands have clearly numbered sequences (review steps 1-5, polish steps 1-5), and the source-editing polish command includes an explicit confirmation checkpoint ("Ask for confirmation before editing") and a keep-diff-small guard, satisfying the validation-checkpoint requirement for a batch/source-mutating operation.	3 / 3
Progressive Disclosure	The body links to bundle files ([_root.css](./_root.css), [_refine-rules.md](./_refine-rules.md), and ../transitions-dev/SKILL.md) but none of these files exist in the skill bundle, so the references are broken; additionally ~80 lines of token tables are inlined rather than split into a reference file. It is below 3 because the signaled one-level-deep references do not resolve, and above 1 because section organization is clear.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 high-quality description: it states concrete capabilities, supplies an explicit Use-when clause with many natural trigger phrases, and clearly distinguishes itself from a sibling skill. Voice is third-person throughout, so no specificity penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the five named motion dimensions ("duration, distance, scale, blur, and easing") plus specific WHEN-rules ("open/close asymmetry, hover-in vs hover-out, stagger offsets, and intent delays"), matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what it does ("Polish and refine existing motion against the transitions.dev motion-token scale") and when to use it via a clear "Use when the user asks to..." clause with concrete triggers.	3 / 3
Trigger Term Quality	Quotes a broad set of natural phrases a user would actually say ("polish my transitions", "make the animation feel better / less janky", "too slow / too fast", "fix the stagger"), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche by contrasting itself with transitions-dev ("focused on tuning what already animates rather than adding new transitions") and uses namespaced command triggers ("transitions review or transitions polish"), making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing, 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: Jakubantalik/transitions.dev
Path: skills/transitions-polish/SKILL.md
Commit: 67d5c67

Reviewed: 3 days 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.