video-transcripts

Generate structured video transcripts from local files or video URLs using Gemini Files API. Use when a GitHub or Linear tracker item, comment, or attachment includes a screen recording, .mov, .mp4, or tracker-hosted video and you need a <video-transcripts> block instead of hand-written notes.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

Highly actionable content with executable commands, explicit output contract, and real feedback loops. The main weakness is redundancy: caching and auth-retry rules are restated across multiple sections and could be consolidated for better token efficiency and workflow clarity.

Suggestions

Consolidate the caching rules currently spread across 'Workflow' steps 3-6 and 14-15 into a single 'Caching' section to remove redundancy and improve conciseness.

State the Linear/GitHub auth fallback chain once (either in Quick Start or Notes) rather than describing retry behavior in both places.

Add an explicit validation checkpoint in the caching sub-workflow (e.g., 'confirm normalized video keys match before reusing cache') to lift workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept-explanation padding, but auth-retry behavior and caching rules are repeated across 'Quick Start', 'Workflow' (steps 3-6, 14-15), and 'Notes', so it could be tightened; not yet at the 'lean, every token earns its place' level.	3 / 5
Actionability	Provides copy-paste-ready executable bash commands for all three input cases, the exact output XML shape, concrete env-var fallback chains, and model-override commands — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced 17-step workflow with explicit feedback loops (model fallback on malformed/thin output, a quality gate that rejects low-signal transcripts); capped just below 5 because the caching/matching sub-workflow is convoluted with overlapping rules rather than a clean validate-then-proceed checkpoint.	4 / 5
Progressive Disclosure	Well-organized into clear sections (Quick Start, Use This When, Workflow, Output Contract, Model Strategy, Notes) and offloads heavy implementation to the bundled generate_video_transcript.sh script referenced by path, with no nested multi-level references; not a 5 because most guidance is inlined rather than split into dedicated reference files.	4 / 5
	Total	16 / 20 Passed

Description

90%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 description with explicit what/when structure, comprehensive natural trigger terms including file extensions, and a distinct niche. The only weakness is that the 'what' is essentially a single action with input variants rather than a list of several capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Generate structured video transcripts') with input-source variants ('from local files or video URLs using Gemini Files API'), but does not list multiple distinct actions, so it stops at the '1-2 concrete actions' anchor rather than the 'several specific actions' level above.	3 / 5
Completeness	Explicitly states what it does ('Generate structured video transcripts...') and when to use it ('Use when a GitHub or Linear tracker item... includes a screen recording... and you need a <video-transcripts> block'), with a clear explicit 'Use when' clause and concrete triggers; third-person voice is maintained.	5 / 5
Trigger Term Quality	Covers natural user phrases and file extensions comprehensively — 'screen recording, .mov, .mp4, or tracker-hosted video' plus 'GitHub or Linear tracker item, comment, or attachment' — matching the 'synonyms and file extensions' top anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (transcripts of tracker-hosted screen recordings) with distinct, specific triggers tied to GitHub/Linear attachments, giving minimal overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing, 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/video-transcripts/SKILL.md
Commit: d76efae

Reviewed: 3 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.