CtrlK
BlogDocsLog inGet started
Tessl Logo

remotion-best-practices

Best practices for Remotion - Video creation in React

51

Quality

57%

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/remotion-best-practices/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 an exemplary lean index: it assumes Claude's competence, routes topics to clearly labeled rule files, and wastes no tokens. Its weaknesses are that the SKILL.md carries no standalone actionable content and that the referenced rules/ files are absent from the provided bundle, so the progressive-disclosure structure cannot be verified and the skill is inert as shipped.

Suggestions

Include the rules/ directory (or at least the highest-traffic rules like animations, sequencing, and captions) in the bundle so the ~30 references resolve — as shipped, the body points entirely at files that don't exist.

Fold the 'Captions' section into the index list and use one consistent path format (rules/subtitles.md vs ./rules/subtitles.md) so navigation is uniform.

Add one or two lines of the most critical Remotion-specific gotchas (e.g. the render-vs-preview determinism rule) inline, so the skill degrades gracefully even when the rule files aren't loaded.

DimensionReasoningScore

Conciseness

The body is a lean routing index — a two-line 'When to use', a captions pointer, and one descriptive line per rule file — with zero padding and no explanation of concepts Claude already knows. It fits 'lean and efficient; every token earns its place'; the slightly awkward 'to obtain the domain-specific knowledge' phrasing is a wording nit, not verbosity, so it does not drop to 4.

5 / 5

Actionability

The guidance is concrete pointers ('Read individual rule files', 'load the ./rules/subtitles.md file') but the body contains no executable content itself — every rule's actual instruction lives in the referenced files, and in the bundle as provided none of those files exist, so a reader here cannot act on anything. 'Some concrete guidance but incomplete' fits; 4 would require mostly executable guidance, which only holds if the rule files are present and useful.

3 / 5

Workflow Clarity

As a simple single-purpose routing skill under 50 lines, the flow is unambiguous: recognize Remotion work, pick the matching rule file, read it. Minor gaps keep it from 5 — the 'Captions' section is oddly separated from the 'How to use' list, the path styles are inconsistent ('./rules/subtitles.md' vs 'rules/3d.md'), and there is no hint of how to proceed when a topic spans multiple rules.

4 / 5

Progressive Disclosure

The structure matches the top anchor — a concise overview indexing ~30 one-level-deep references, each with a clear one-line label — but the actual bundle contains no rules/ directory, so every referenced file is unverifiable/missing and the split cannot be confirmed to pay off. 'Good structure; references mostly clear; minor organization gaps' fits better than 5, which requires the well-signaled references to actually resolve.

4 / 5

Total

16

/

20

Passed

Description

40%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 short and names a distinctive niche, but it only states a topic, not capabilities, and entirely lacks a 'when to use' trigger clause. It reads as a folder label rather than a skill description, leaving both routing and capability communication underserved.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing or editing Remotion code, or when the user mentions Remotion, programmatic video, or rendering videos from React.'

List the concrete capability areas instead of 'Best practices', e.g. 'Covers Remotion animations, sequencing, audio/video embedding, captions, transitions, and rendering — domain-specific rules for creating videos in React.'

Include natural synonyms users would say (animation, video rendering, Motion Canvas alternatives) so the skill surfaces for phrasings that don't include the word 'Remotion'.

DimensionReasoningScore

Specificity

The description names the domain ('Remotion - Video creation in React') but lists no concrete actions — 'Best practices for' is generic with respect to what the skill actually does. This matches the anchor 'Names the domain but actions are minimal or generic' rather than 3, which requires 1-2 concrete actions, and not 1, because the domain is named.

2 / 5

Completeness

The 'what' is vague ('Best practices for...') and there is no 'Use when...' clause or equivalent trigger guidance at all, which caps completeness at 3 per the guidelines. It sits at anchor 2 ('vague what and no when') rather than 3, because even the 'what' conveys no concrete capabilities.

2 / 5

Trigger Term Quality

'Remotion', 'Video creation', and 'React' are relevant natural terms a user working with this library would say, but common variations are missing (animation, rendering, .tsx/video, programmatic video). This parallels 'Works with PDF files' — some relevant keywords, missing synonyms — rather than 4, which expects good coverage of natural terms.

3 / 5

Distinctiveness Conflict Risk

Remotion is a clear niche — a user mentioning it almost certainly means this library — but the description offers no explicit trigger phrases, so generic 'React' or 'video' queries could plausibly overlap with other skills. Mostly distinct with minor overlap risk, rather than 5, which expects distinct explicit triggers.

4 / 5

Total

11

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 30 missing

Warning

Total

14

/

16

Passed

Repository
vercel-labs/json-render
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.