oma-video

Create short, explainer, or recorded-demo videos through the OMA video CLI. Use for scripts, narration, assets, composition, and video delivery.

Quality

85%

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

96%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 exemplar of operational writing: dense routing tables, executable commands for every mode, explicit validation checkpoints, and feedback loops for the compose/render cycle, with conditional references keeping the main file focused. The only notable gap is that the cited resources/ files are not present in the bundle to verify, leaving the reference structure unconfirmed.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational throughout — mode routing tables, guardrails, and command paths with no explanation of concepts Claude already knows — and nearly every token earns its place, fitting the lean-and-efficient anchor at 5 rather than the minor-trimming-needed anchor at 4.	5 / 5
Actionability	The "Canonical command path" gives copy-paste-ready commands covering all three modes (generate with --captions/--script/--seed/--dry-run/--capture, compose, render, doctor, provider list) plus the documented JSON envelope fields, and failure paths give executable recovery steps, matching the fully-executable anchor at 5.	5 / 5
Workflow Clarity	The sequence is explicit — infer mode and confirm defaults, generate the asset bus, compose/author, render, ffprobe-validate — with explicit validation checkpoints (manifest hash validation, encoded video stream, positive ffprobe duration, doctor) and a feedback loop ("Fix a reported composition or toolchain failure and re-run; return a failure report when it cannot render"), plus a pre-handoff checklist reference.	5 / 5
Progressive Disclosure	The "Conditional resources" section signals one-level-deep references with clear load conditions ("Load only what the task needs"), but none of the cited resources/*.md files are present in the provided bundle to verify, and the ~150-line body inlines some operational detail (guardrails, failure mapping) that the referenced execution-protocol.md presumably duplicates — good structure with minor gaps, matching anchor 4.	4 / 5
	Total	19 / 20 Passed

Description

73%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 clearly communicates a distinct niche (OMA CLI video creation across three modes) with mostly natural trigger terms and both what and use-for guidance. Its weaknesses are a single action verb with a noun-list of capabilities and the absence of explicit "use when" trigger phrasing and common synonyms like reel or walkthrough.

Suggestions

Rewrite the capability list with action verbs, e.g. "Write scripts, generate narration and captions, acquire visual assets, compose and render video, and validate the encoded output."

Add an explicit trigger clause with concrete phrases and synonyms, e.g. "Use when the user asks to make a video, reel, short, explainer, demo walkthrough, or screen recording."

Mention the human-recorded demo trigger explicitly (e.g. "or wants to turn a screen recording into a walkthrough") since 'recorded-demo' alone is an uncommon user phrase.

Dimension	Reasoning	Score
Specificity	"Create short, explainer, or recorded-demo videos through the OMA video CLI" names the domain and one concrete action, but "Use for scripts, narration, assets, composition, and video delivery" lists objects as nouns rather than concrete actions, leaving coverage short of the several-verbs anchors at 4 and 5.	3 / 5
Completeness	The what is clear (video creation via the OMA CLI) and "Use for scripts, narration, assets, composition, and video delivery" provides trigger guidance, but it is a scope list rather than an explicit "Use when the user asks for a video/reel/demo" clause, so the when-side could be more explicit — matching anchor 4, not the concrete trigger phrases of 5 or the weakly-implied-when of 3.	4 / 5
Trigger Term Quality	Natural terms like "short", "explainer", "recorded-demo", and "videos" match what users would say, but common variations such as "reel", "clip", "walkthrough", or "screen recording" are missing, which fits the good-coverage-with-a-few-gaps anchor at 4 rather than the comprehensive synonym coverage of 5.	4 / 5
Distinctiveness Conflict Risk	"Create short, explainer, or recorded-demo videos through the OMA video CLI" carves out a clear niche with distinct triggers (specific CLI, three named modes) and minimal overlap with adjacent image/slide/voice skills.	5 / 5
	Total	16 / 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: first-fluke/oh-my-agent
Path: .agents/skills/oma-video/SKILL.md
Commit: ce19702

Reviewed: 4 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.