Name: krillinai-render-vertical
Rating: 75.2 (1 reviews)
Author: krillinai

krillinai-render-vertical

Use when rendering portrait videos with KrillinAI CLI, including converting source video to vertical format, adding short bilingual subtitles, rendering dubbed vertical videos, and checking vertical subtitle readability.

Quality

93%

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

Quality

Content

93%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.

A concise, highly actionable skill body with executable commands for both variants and concrete verification steps. The only gap is the lack of an explicit retry/fix loop when verification flags a problem.

Suggestions

Add a short feedback loop under Verification, e.g. 'If subtitles stack as two Chinese lines or titles are garbled, re-run render-vertical with adjusted subtitle segmentation and re-check the preview.'

The reference to vertical_srt.py in Subtitle Behavior points to a file not present in any bundle; either add it to references/ or clarify it is an internal upstream source so the reference is not misleading.

Dimension	Reasoning	Score
Conciseness	Lean body of commands plus a tight bulleted subtitle-behavior spec; no padding or explanations of concepts Claude already knows, and every section earns its place.	5 / 5
Actionability	Two copy-paste-ready command blocks covering the common cases (bilingual short-subtitle and dubbed) with all flags filled in, plus concrete executable verification commands.	5 / 5
Workflow Clarity	A clear verification checkpoint is present (rg + ffmpeg preview, with what to check for), but there is no explicit fix/retry feedback loop if subtitles are garbled or stacked, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections (Bilingual, Dubbed, Subtitle Behavior, Outputs, Verification) and self-contained with no external references needed, satisfying the simple-skill exception.	5 / 5
	Total	19 / 20 Passed

Description

92%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.

A strong, specific description that states concrete capabilities and an explicit 'Use when' trigger, scoped to a distinct CLI niche. Only minor weakness is the absence of synonyms/file extensions in the trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'converting source video to vertical format, adding short bilingual subtitles, rendering dubbed vertical videos, and checking vertical subtitle readability' — giving comprehensive coverage of the render-vertical capability.	5 / 5
Completeness	Explicitly answers both: the 'what' (convert, subtitle, render dubbed, check readability) and the 'when' via the opening 'Use when rendering portrait videos with KrillinAI CLI' trigger clause.	5 / 5
Trigger Term Quality	Good natural-term coverage ('rendering portrait videos', 'vertical format', 'bilingual subtitles', 'dubbed vertical videos'), but lacks synonyms and file extensions (e.g. .mp4) that anchor 5 expects.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to a named tool and subcommand (KrillinAI CLI render-vertical) with vertical/bilingual/dubbed triggers, creating a clear niche with minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: krillinai/KrillinAI
Path: skills/krillinai-render-vertical/SKILL.md
Commit: 0a16abf

Reviewed: 1 day 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.