gemini-omni

Generate and conversationally edit short videos with Google Gemini Omni Flash (`gemini-omni-flash-preview`). Use when: (1) iterating on a clip with natural-language edits instead of regenerating ("make the phone invisible, keep everything else the same"), (2) generating 3-10s 720p clips with synthesized audio, rendered on-screen text, or timecoded beats, (3) binding reference images to roles with <FIRST_FRAME>/<IMAGE_REF_N> prompt tags, (4) editing an existing uploaded video. Accessed via the `gemini_omni_video` tool using the project's GEMINI_API_KEY/GOOGLE_API_KEY — the same key as Imagen and Google TTS.

Quality

88%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-sequenced, with concrete prompting guidance and clearly flagged gotchas. The main weaknesses are inline time-sensitive/marketing framing and a monolithic single-file structure with no progressive disclosure.

Suggestions

Move time-sensitive details (I/O 2026 announcement, June 30 2026 access date, per-second pricing) into a clearly marked 'Preview / availability notes' or 'old patterns' section rather than the opening paragraph.

Trim the marketing-style framing in the opening paragraph (e.g., "Its differentiator in the OpenMontage fleet is...") to operator-relevant facts only.

Consider offloading the reference-image tag syntax examples and the hard-limitations list into a references/ file referenced from the body, leaving the SKILL.md as a tighter overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean and operator-focused, but the opening paragraph carries marketing framing ("Its differentiator in the OpenMontage fleet is...") and time-sensitive details (I/O 2026, June 30 2026, per-second pricing) are stated inline rather than isolated.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: real example prompts, timecode syntax, reference-image tag syntax, good/bad edit-prompt pairs, and explicit parameters (operation="edit_video", previous_interaction_id, store, input_video_path).	3 / 3
Workflow Clarity	The conversational-editing workflow is a clear four-step sequence with explicit gotchas (the store interaction_id requirement, regional limits on uploaded-video editing, unreliable ≤3s video refs).	3 / 3
Progressive Disclosure	Content is well-organized under clear section headers but everything lives in one ~100-line file with no bundle files or reference offloading; the prompt-tag details and hard-limitations section could be split out.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 specific, trigger-rich, and distinctive, with an explicit numbered "Use when:" clause that cleanly separates it from sibling video/image skills. It uses third-person voice throughout and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: "Generate and conversationally edit short videos", "iterating on a clip with natural-language edits", "generating 3-10s 720p clips with synthesized audio, rendered on-screen text, or timecoded beats", and "editing an existing uploaded video".	3 / 3
Completeness	Clearly states what it does (generate and conversationally edit short videos) and provides an explicit numbered "Use when:" trigger list covering four scenarios.	3 / 3
Trigger Term Quality	Embeds natural user phrases such as "make the phone invisible, keep everything else the same" alongside explicit triggers like "iterating on a clip with natural-language edits" and "editing an existing uploaded video".	3 / 3
Distinctiveness Conflict Risk	The Gemini Omni conversational-editing niche is sharply defined and explicitly distinguished from Imagen and Google TTS, so it is unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/gemini-omni/SKILL.md
Commit: 0af32ce

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.