CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-video

Short-form, explainer, and demo video generation via a key-optional 3-tier router. Composes scripts, oma-voice narration, oma-image/oma-slide/stock visuals, key-free captions, and a vendored Remotion compositor into reproducible run directories. Routes three modes — shorts/reels (9:16), explainer (16:9 README/code/data), and demo/walkthrough (screen capture, incl. supervised headed web-app capture of any URL). Use for video, shorts, reels, short-form, demo, explainer, walkthrough, screencast, web capture, video generation, 영상, 숏폼, 쇼츠, 릴스, 데모, 설명 영상.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A highly actionable, well-sequenced skill body with strong command coverage and explicit validation checkpoints, weakened by verbosity (implementation arcana inline) and progressive-disclosure gaps (referenced bundle files absent, detail that belongs in them kept inline). The operational core is excellent; the architecture-spec framing inflates token cost.

Suggestions

Move the Strudel music internals (−14 LUFS normalization, AGPL licensing, oscillator determinism) into a referenced resources/music.md and keep SKILL.md to the preset list plus install/fallback behavior.

Trim architecture-spec sections that describe internals rather than instruct execution — the 'Logical Operations' SSL-primitive table and 'Resource scope' table — or relocate them to a resources/architecture.md.

Provide the referenced resources/ bundle files (execution-protocol.md, vendor-matrix.md, prompt-tips.md, checklist.md, script-schema.md) so the one-level-deep references resolve, and pull the 14-item guardrails list and Clarification Protocol into them instead of inlining.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands and flag tables, but retains implementation arcana Claude does not need to execute the skill (Strudel -14 LUFS normalization, AGPL licensing rationale, oscillator-only determinism, the "SSL primitive" Logical Operations table) that could be trimmed. Not a 1 because the operational content genuinely earns its tokens, but not a 3 because the architecture-spec detail is over-elaborated for a SKILL.md overview.

2 / 3

Actionability

Fully executable canonical commands ("oma video generate ...", "oma video doctor --install"), a complete CLI flag listing, an output-layout tree, and copy-paste invocation examples for every mode.

3 / 3

Workflow Clarity

Clear PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE scene sequence with an explicit VERIFY validation checkpoint (schema/manifest-hash/exit-code), a dedicated failure-and-recovery feedback loop, and a Clarification Protocol checklist before invocation.

3 / 3

Progressive Disclosure

References are one-level-deep and well-signaled in a dedicated References section, but the body is monolithic — Strudel music internals, the 14-item guardrails list, and the Clarification Protocol that should live in the referenced resources are inline, and the referenced resources/ files are not present as bundles. Not a 3 because content is not appropriately split; not a 1 because the references that do exist are clearly signaled and shallow.

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.

A strong, content-dense description that names concrete actions, covers natural trigger terms (including Korean variants), and explicitly states both what it does and when to use it in third person. Its only weakness is verbosity — it is long for a description — but every clause earns its place rather than padding.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "Composes scripts, oma-voice narration, oma-image/oma-slide/stock visuals, key-free captions, and a vendored Remotion compositor" plus three routed modes with aspects; third-person voice throughout ("Composes", "Routes").

3 / 3

Completeness

Explicitly answers both "what" (composes scripts/narration/visuals/captions/compositor into reproducible run directories, routes three modes) and "when" via the explicit "Use for ..." trigger clause.

3 / 3

Trigger Term Quality

"Use for video, shorts, reels, short-form, demo, explainer, walkthrough, screencast, web capture, video generation" plus Korean variants (영상, 숏폼, 쇼츠, 릴스) gives broad coverage of natural terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

Clear video-generation niche with distinct video trigger terms; naming sibling oma-voice/oma-image/oma-slide skills is contextual composition detail, not a routing conflict.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
first-fluke/oh-my-agent
Reviewed

Table of Contents

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.