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

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/review-animations/SKILL.md

The canonical home for this skill is review-animations in emilkowalski/skills

Quality

Content

77%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.

The body is a strong, concrete review playbook with clear sequencing, checklists, and explicit approval criteria, but it leans on a STANDARDS.md file that is not present in the bundle, which both breaks progressive-disclosure navigation and leaves the 'pull exact values' instruction unexecutable. Minor motivational prose slightly reduces conciseness.

Suggestions

Ship the missing STANDARDS.md (easing curves, duration tables, spring configs, gesture/clip-path/perf/a11y values) so the deferred references resolve and precise values are actually retrievable — this would lift both progressive_disclosure and actionability.

Trim the 'Operating Posture' identity paragraph and drop the duplicated 'Default to flagging. Approval is earned' (already in the description) to tighten conciseness toward a 5.

If STANDARDS.md cannot be bundled, inline the essential exact values (a compact easing/duration table) directly in SKILL.md so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its tokens — concrete standards with exact values (300ms, scale(0.9-0.97), transform-origin) and no 'what is an animation' padding — but the 'Operating Posture' identity prose and the repeated 'Default to flagging. Approval is earned' (already in the description) are minor over-explanation that could be trimmed.	4 / 5
Actionability	Guidance is highly concrete — specific properties (transform, opacity), exact values, a Before/After fix table, and explicit flag patterns — but it repeatedly directs Claude to 'pull the exact one from STANDARDS.md' for curves/durations/spring configs, and STANDARDS.md is absent from the bundle, leaving a real executable gap; substantial copy-paste-ready guidance is present, so it sits above the midpoint but short of fully executable.	4 / 5
Workflow Clarity	The review process is clearly sequenced (measure against the Ten Standards -> apply Aggressive Escalation Triggers -> propose fixes via the Remedial Hierarchy -> emit findings table -> tiered verdict with explicit Block/Approve criteria), with the standards and escalation triggers functioning as checklists and the Block/Approve rules serving as the explicit validation checkpoint; a validate-retry loop is N/A for a non-mutating review skill.	5 / 5
Progressive Disclosure	Structure is well-intentioned and clearly signaled — the body stays at principle level and points to [STANDARDS.md](STANDARDS.md) for the detailed rule catalog — but STANDARDS.md does not exist in the bundle (no references/ dir, no such file), so the one-level-deep reference is a dangling link and the deferred precise values are simply missing.	3 / 5
	Total	16 / 20 Passed

Description

61%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 clearly states what the skill does and carves out a specific motion-craft niche, but it omits an explicit 'Use when ...' trigger clause in the description field itself (relying on the separate triggers list), which caps completeness. Trigger-term coverage is good but not exhaustive.

Suggestions

Add an explicit 'Use when ...' clause to the description (e.g., 'Use when reviewing animation or motion code, or when the user asks to audit easing, transitions, or motion craft.') so completeness is not capped at 3.

Include a few more natural trigger variations or the relevant file/property tokens (e.g., 'transitions', 'easing', 'Framer Motion', 'CSS animations') to push trigger-term coverage toward comprehensive.

Consider naming 1-2 more concrete review actions (e.g., 'flags easing, duration, origin, and GPU-property violations') to move specificity from one action toward several.

Dimension	Reasoning	Score
Specificity	Names a specific domain ('animation and motion code') and one concrete action ('Reviews ... against a high craft bar') plus a posture ('Default to flagging; approval is earned'), but does not list several distinct capabilities, so it sits at 'domain + 1-2 concrete actions' rather than comprehensive.	3 / 5
Completeness	The 'what' is clear ('Reviews animation and motion code against a high craft bar'), but there is no explicit 'Use when ...' trigger clause in the description field — trigger guidance lives only in the separate `triggers` list, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms a user would say are present ('animation', 'motion', 'motion code', 'review', 'flagging', 'approval'), with 'animation' and 'motion' covering the main synonyms; only a few natural variations are missing, so it is above the midpoint but short of comprehensive coverage with extensions.	4 / 5
Distinctiveness Conflict Risk	The 'animation and motion code' niche is mostly distinct and unlikely to fire for unrelated skills, with only minor overlap risk against a general code-review skill; it is not a fully conflict-free niche because 'review' is a shared verb.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: nexu-io/open-design
Path: skills/review-animations/SKILL.md
Commit: f580271

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.