remotion
Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory
82
81%
Does it follow best practices?
Impact
80%
1.50xAverage score across 3 eval scenarios
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.
The description is well-structured with an explicit 'Use when' clause and distinctive trigger terms that clearly carve out a niche around Remotion video development. Its main weakness is that the 'what' portion is somewhat generic — it says 'generating or modifying Remotion video code' without listing specific capabilities like composition setup, animation, rendering, or asset management. Overall it's a solid, functional description.
Suggestions
Add more specific concrete actions, e.g., 'Generates Remotion compositions, configures animations, manages sequences, and renders video output' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Remotion video code, demo videos) and some actions (generating, modifying, creating), but doesn't list specific concrete capabilities like 'add animations', 'configure compositions', 'render sequences', etc. | 2 / 3 |
Completeness | Explicitly answers both what (generating/modifying Remotion video code, creating demo videos) and when ('Use when...') with clear trigger conditions including directory-based matching. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Remotion', 'video code', 'demo videos', 'demo-video/' directory. These are specific and cover the likely terms a user would mention when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Remotion', 'demo-video/ directory', and 'demo videos' are very specific triggers unlikely to conflict with other skills. The directory reference adds a concrete, unambiguous selector. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent executable code examples and clear critical rules that distinguish correct from forbidden patterns. The main weaknesses are a lack of validation checkpoints in the pipeline workflow (especially around the render step) and some minor verbosity in structural descriptions. The progressive disclosure and organization are strong.
Suggestions
Add validation/verification steps to the auto-generation flow (e.g., 'Verify output exists and file size > 0', 'If render fails, check ffmpeg installation and re-run')
Trim the 'When This Skill Applies' section—this is metadata that belongs in frontmatter or can be inferred from context, not instruction content
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good code examples, but includes some unnecessary context like explaining when the skill applies and the project structure listing every component file with brief descriptions. The common patterns section is useful but adds length; some patterns (fade in/out, staggered animation) could be more tightly presented. | 2 / 3 |
Actionability | Provides fully executable TypeScript code examples throughout, concrete CLI commands for rendering and debugging, a clear props schema interface, and copy-paste ready animation patterns. The CORRECT/FORBIDDEN pattern in critical rules is immediately actionable. | 3 / 3 |
Workflow Clarity | The auto-generation flow lists steps clearly but lacks validation checkpoints or error recovery between steps. The manual rendering section provides commands but doesn't include verification steps (e.g., checking output file exists, validating the rendered video). For a pipeline involving file generation and rendering, missing feedback loops cap this at 2. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from structure to rules to integration to debugging to patterns. References at the bottom point to external docs and READMEs with one-level-deep links. Content is appropriately organized for discovery without being monolithic. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
e437c3c
- 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.