Name: remotion-captions
Rating: 58.4 (1 reviews)
Author: remotion-dev

Blog Docs Log inGet started

remotion-captions

Transcribing, displaying and animating captions

Quality

68%

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 ./packages/skills/skills/remotion-captions/SKILL.md

The canonical home for this skill is remotion-captions in remotion-dev/skills

Quality

Content

78%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 routing document: a clear JSON-first rule, the essential Caption type, and three well-labeled task sections each pointing to one reference file. Its main defect is that all three referenced files are missing from the bundle, so the progressive-disclosure structure it advertises cannot actually be navigated.

Suggestions

Ship the three referenced files (transcribe-captions.md, display-captions.md, import-srt-captions.md) in the bundle so the body's pointers resolve instead of dead-ending.

Add a fourth section (or fold into display-captions) covering the "animating captions" capability named in the description, so every advertised action has a routing path.

Optionally inline one minimal usage snippet (e.g., a parseCaptitions or <Captions> usage example) so the skill remains actionable even before a reference file is loaded.

Dimension	Reasoning	Score
Conciseness	"All captions must be processed in JSON" plus the complete Caption type definition is lean with zero padding; the type definition is custom package knowledge Claude cannot be assumed to know. Every token earns its place, matching the anchor 5 example rather than anchor 4's minor trimmable over-explanation.	5 / 5
Actionability	The body gives a copy-paste-ready TS type definition, an explicit import statement, and unambiguous per-task pointers, but the executable steps for each task live entirely in the referenced files. Matches "mostly executable guidance with minor gaps" rather than 5's fully covered common cases.	4 / 5
Workflow Clarity	The three task paths ("Generating captions", "Displaying captions", "Importing captions") are cleanly separated with one pointer each — unambiguous routing for a simple skill. Not 5 because "animating", named in the frontmatter description, has no corresponding section, leaving a small routing gap.	4 / 5
Progressive Disclosure	References are clearly signaled and one level deep, but scoring against the actual bundle structure, the three referenced files (transcribe-captions.md, display-captions.md, import-srt-captions.md) do not exist in the bundle — only assets/remotion-icon.svg is present. Navigation is broken, fitting "some structure but could be better organized" rather than 4.	3 / 5
	Total	16 / 20 Passed

Description

58%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 concise and names three concrete caption actions, but it entirely lacks a "when to use" trigger clause and misses natural synonyms like "subtitles" and "SRT" that users would say. It reads more like a category label than a discovery-oriented description.

Suggestions

Add an explicit trigger clause, e.g., "Use when working with captions, subtitles, or .srt files in Remotion videos, or when the user mentions transcribing audio/video or adding subtitles."

Include natural synonyms and file extensions — "subtitles", "SRT", ".srt", "captions" — so the skill triggers on the phrases users actually say.

Mention importing captions from .srt files (a documented capability in the body) to round out the coverage of what the skill does.

Dimension	Reasoning	Score
Specificity	"Transcribing, displaying and animating captions" lists three concrete actions in a named domain, matching the anchor for several specific actions with minor coverage gaps (e.g., importing .srt files, a documented capability, is not mentioned). It falls short of 5 because coverage is not comprehensive.	4 / 5
Completeness	The description has a clear "what" (transcribing, displaying, animating captions) but no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. Not 2 because the "what" is clear and specific, not vague.	3 / 5
Trigger Term Quality	Relevant keywords like "captions", "transcribing", and "animating" are present, but common variations users would naturally say — "subtitles", "SRT", ".srt", "video", "audio" — are missing. Not 4, since keyword coverage is thin rather than merely missing a few natural terms.	3 / 5
Distinctiveness Conflict Risk	The three-action combination around captions carves a mostly distinct niche with only minor overlap risk against generic transcription or video-editing skills. Not 5 because omitting the video/Remotion context leaves some ambiguity about scope.	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: remotion-dev/remotion
Path: packages/skills/skills/remotion-captions/SKILL.md
Commit: 6f4e0d5

Reviewed: 5 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.