CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-animations

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

Quality

69%

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/review-animations/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 lean, opinionated, highly actionable review skill with a rigid output contract — no padding, no explanations of known concepts, concrete values throughout. Its main weaknesses are the dangling STANDARDS.md reference that the body depends on for every recommended value, and a review sequence that is implied by structure rather than stated explicitly.

Suggestions

Ship STANDARDS.md in the bundle (or inline the key duration/easing tables) so the repeated instruction to pull exact values from it can actually be executed.

Add a short numbered review sequence up front (enumerate animations in the diff → apply the ten standards → check escalation triggers → produce the two-part output) to make the workflow explicit rather than implied.

Verify the ../choreograph/SKILL.md cross-reference resolves in the installed layout, or describe the 30–80ms stagger rule inline and drop the link.

DimensionReasoningScore

Conciseness

The body is dense and imperative and explains nothing Claude already knows — no definition of easing, transitions, or CSS animation; every section states rules ("UI animations stay under 300ms", "Never animate from `scale(0)`"). Minor trimmable instances exist: the Aggressive Escalation Triggers list restates standards 3, 5, 7, and 8, and the canned "Initial Response" greeting adds tokens. Fits anchor 4 (efficient, minor instances that could be trimmed); not 5 because of that duplication and boilerplate.

4 / 5

Actionability

Guidance is highly concrete for an instruction-only skill: exact thresholds (sub-300ms, 400ms `ease` toasts, `scale(0.9–0.97)`), exact properties and media queries (`@media (hover: hover) and (pointer: fine)`), a filled-in Before/After/Why example table, an ordered remedial hierarchy with specific swaps, and explicit Block/Approve criteria. It stops short of anchor 5 because every recommended value (curves, duration tables, spring configs) is deferred to STANDARDS.md, which is not present in the bundle, so "pull the exact one from STANDARDS.md" cannot be executed as provided.

4 / 5

Workflow Clarity

The review flow is legible through section order (posture → standards → on-sight triggers → fix hierarchy → required output), with one explicit checkpoint ("Read it before you write the verdict") and a rigid two-part output format capped by an explicit Block/Approve decision protocol that validates the verdict. Fits anchor 4 (clear sequence, most checkpoints present); not 5 because the sequence is never stated as explicit numbered steps for entering the review (e.g., enumerate animations in the diff first).

4 / 5

Progressive Disclosure

The design intent is textbook progressive disclosure — an overview SKILL.md deferring the full rule catalog to a clearly signaled, one-level-deep [STANDARDS.md](STANDARDS.md) — but the actual bundle contains no STANDARDS.md (and no ../choreograph/SKILL.md), so the central reference that carries the skill's values is dangling. Scoring against the actual bundle structure, this fits anchor 3 (references present, structure undermined); not 4 because the most important referenced path does not resolve, and not 2 because the inline content is genuinely overview-level rather than inlined reference material.

3 / 5

Total

15

/

20

Passed

Description

53%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.

The description is clearly written in third person with a precise domain and a distinct personality, but it describes only one action and omits any trigger guidance. Adding a "Use when..." clause covering terms like transitions, easing, and springs would address its two weakest dimensions at once.

Suggestions

Add an explicit trigger clause, e.g. "Use when reviewing animations, transitions, easing, springs, or micro-interactions in CSS/Motion/Framer code."

Enumerate the concrete review actions (easing curves, durations, transform-origin, interruptibility, reduced-motion) so the "what" is comprehensive rather than a single verb.

Include the natural synonyms users say ("transition", "micro-interaction", file/framework names like CSS and Motion) to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Reviews animation and motion code" names the domain and one concrete action (review), elaborated only by posture ("against a high craft bar", "Default to flagging; approval is earned") — it never enumerates what aspects are reviewed (easing, duration, origin, a11y). This matches anchor 3 (domain + 1-2 concrete actions, not comprehensive); it falls short of anchor 4 because no list of several specific actions is given, and exceeds anchor 2 because the action and domain are concrete.

3 / 5

Completeness

The "what" is clear (reviews animation and motion code against a craft bar) but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3, exactly matching anchor 3 (clear 'what', 'when' missing).

3 / 5

Trigger Term Quality

"animation", "motion code", and "craft" are natural terms, but common variations a user would actually say — "transition", "easing", "spring", "micro-interaction", "CSS animation" — are absent. Fits anchor 3 (some relevant keywords, missing common variations); not 4 because coverage is narrow beyond the two core terms.

3 / 5

Distinctiveness Conflict Risk

The niche is narrow — animation/motion code review only — with only minor overlap risk against a general code-review skill, fitting anchor 4 (mostly distinct, minor overlap with closely related skills). Not 5 because no explicit distinct triggers are stated and the philosophy/craft framing could overlap with other design-review skills.

4 / 5

Total

13

/

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

relative_links

Relative link issues: 1 possibly missing (STANDARDS.md)

Warning

Total

15

/

16

Passed

Repository

emilkowalski/skills

Path

skills/review-animations/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.