sora

Generate, remix, and manage short video clips via OpenAI's Sora API. Useful for cinematic shots, b-roll, and rapid concept video iteration.

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/sora/SKILL.md

Quality

Content

42%

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

The body is a thin catalogue stub: well-organized and concise, but it offers almost no actionable or operational guidance, relying entirely on the upstream repository. Its core weakness is actionability, with workflow clarity also limited by absent validation steps.

Suggestions

Add a concrete install command or example invocation of the skill instead of only pointing at the upstream README, so a user/agent can act directly.

If the skill performs multi-step video operations, include a short numbered workflow with a validation checkpoint (e.g., verify the generated clip meets the requested duration/format) to raise workflow clarity.

Tighten the 'How to use' explanatory prose to remove narrative padding ('This catalogue entry advertises the skill...') and keep only the directive steps.

Dimension	Reasoning	Score
Conciseness	The body is brief and does not explain concepts Claude already knows, but the 'How to use' prose is somewhat loose ('advertises the skill in Open Design so the agent discovers it') and could be tightened; it does not reach the lean-and-every-token-earns-its-place anchor because the stub says little of operational value.	2 / 3
Actionability	Beyond `open https://github.com/openai/skills` there is no executable code or specific command; guidance is abstract ('install the upstream bundle', 'ask the agent to invoke this skill'), describing rather than instructing, matching the vague/abstract anchor.	1 / 3
Workflow Clarity	A loose sequence exists (inspect README -> install upstream bundle -> ask agent to invoke) but there are no validation checkpoints or feedback loops; it is not level 1 because steps are present, and not level 3 because no explicit validation/checklist is given.	2 / 3
Progressive Disclosure	No bundle files exist and the body is under 50 lines with clear, well-organized sections ('What it does', 'Source', 'How to use') and a single signaled external link; per the simple-skills note this satisfies the well-organized anchor without nested references.	3 / 3
	Total	8 / 12 Passed

Description

82%

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, distinct, and rich in natural trigger terms, but it lacks an explicit 'Use when...' clause, which caps its completeness at the middle level. Adding a concrete usage-trigger sentence would lift the weakest dimension.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user wants to create or edit short videos, cinematic shots, or b-roll') to satisfy the completeness anchor for explicit triggers.

Consider adding 'video generation' or 'text-to-video' as additional trigger terms users might naturally say beyond the current list.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ('Generate, remix, and manage') tied to a specific domain ('short video clips via OpenAI's Sora API'), matching the multiple-specific-actions anchor; not the level below which only names a domain and some actions incompletely.	3 / 3
Completeness	'What' is explicit but 'when' is only implied via 'Useful for...' with no explicit 'Use when...' clause, so per the judging guidelines completeness is capped at 2 rather than reaching the level-3 explicit-trigger anchor.	2 / 3
Trigger Term Quality	Frontmatter triggers ('sora', 'openai video', 'short video', 'b roll', 'cinematic clip') give good coverage of the natural terms a user would actually say, matching the anchor; it is not level 2 because common variations are well represented rather than partially missing.	3 / 3
Distinctiveness Conflict Risk	Targets a clearly distinct named-product niche (Sora) with specific triggers unlikely to overlap with other skills, matching the clear-niche anchor; not level 2 because the scope is sharply bounded rather than broadly overlapping.	3 / 3
	Total	11 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/sora/SKILL.md
Commit: a2ba3ee

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.