create-motion
Generate motion specification annotations from After Effects timeline data. Use when the user mentions "motion", "motion spec", "animation spec", "timeline", or wants to document a component's animation properties.
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with explicit trigger guidance and a clear niche. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed beyond just 'generate annotations' — listing sub-tasks like parsing keyframes, documenting easing, or outputting timing tables would strengthen it. Overall, it performs well on completeness and distinctiveness.
Suggestions
Expand the capability description with more specific actions, e.g., 'Generate motion specification annotations from After Effects timeline data, including keyframe timing, easing curves, and property transitions.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (After Effects timeline data, motion specification annotations) and one core action (generate), but doesn't list multiple specific concrete actions like parsing keyframes, documenting easing curves, exporting timing values, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate motion specification annotations from After Effects timeline data) and 'when' (explicit 'Use when...' clause with specific trigger terms and use cases). | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms: 'motion', 'motion spec', 'animation spec', 'timeline', and 'animation properties' — these cover the common variations a user would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of After Effects, motion specs, and animation annotations creates a very clear niche that is unlikely to conflict with other skills. The domain is highly specific. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill with a clear 15-step workflow, executable code for every step, and proper validation checkpoints including visual verification with retry loops. Its main weakness is length — the repeated font-loading boilerplate and inline code blocks make it verbose, though most content is genuinely necessary for the complex Figma rendering task. The progressive disclosure could be improved by extracting some code templates into separate files.
Suggestions
Extract the repeated font-loading boilerplate into a shared utility pattern or reference file, and reference it from each step rather than duplicating it in every code block.
Consider moving the large code blocks for Steps 9-13 into a referenced file (e.g., motion-code-templates.md) and keeping only the step descriptions and placeholder instructions in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400+ lines) with extensive code blocks that are largely necessary for the task, but there's some redundancy in font-loading boilerplate repeated across nearly every code block. The MCP adapter table is useful but verbose. The skill assumes Claude's competence in most areas but could be tightened in places like the repeated font-loading pattern. | 2 / 3 |
Actionability | Every step includes fully executable JavaScript code with clear placeholder conventions (__PLACEHOLDER__). The code is copy-paste ready with specific node selectors, return values, and error handling. The MCP adapter table provides concrete operation mappings for both providers. | 3 / 3 |
Workflow Clarity | The 15-step workflow is clearly sequenced with a progress checklist, explicit validation in Step 14 (visual validation with up to 3 fix iterations), audit step (Step 7), and clear error handling throughout (e.g., template key missing, MCP connection failures). The feedback loop for visual validation is well-defined. | 3 / 3 |
Progressive Disclosure | The skill references an external instruction file (agent-motion-instruction.md) for detailed rules and validation, which is good progressive disclosure. However, the SKILL.md itself is very long with all code blocks inline. The MCP adapter table and extensive code could potentially be split into referenced files to keep the main skill leaner. | 2 / 3 |
Total | 10 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- redongreen/uSpec
- Commit
4eae941
- 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.