reference-driven-video-prompting

Use for image-to-video, reference-video continuity, keyframe-driven prompting, camera control, and consistency workflows based on official Runway, Kling, and character/style reference patterns.

Quality

61%

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 ./.nolanx/skills/reference-driven-video-prompting/SKILL.md

Quality

Content

72%

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

The body is concise, well-sectioned, and free of unnecessary explanation, with concrete rules and motion-language examples. Its main gap is actionability/workflow clarity: it lacks complete worked example prompts and an explicit step-by-step prompt-construction sequence.

Suggestions

Add 1-2 complete worked example prompts (e.g. an image-to-video prompt with a chosen camera move and motion language) showing the rules applied end-to-end.

Provide a short explicit sequence for assembling a prompt (pick reference from hierarchy -> separate subject vs camera motion -> apply motion language -> check Avoid list) to turn the rules into a clear workflow.

Consider a one-line "When no reference is provided, fall back to..." note to clarify the fallback path in the Reference Hierarchy.

Dimension	Reasoning	Score
Conciseness	The body is lean and bullet-driven with no padding or explanations of concepts Claude already knows; every section (Reference Hierarchy, Prompting/Consistency/Camera Control Rules, Good Motion Language, Avoid) earns its place.	3 / 3
Actionability	Concrete directives and example phrases are present ("focus text on desired motion and camera behavior", "sways gently in wind", "camera slowly pushes in as expression hardens"), but there are no complete worked example prompts demonstrating the rules applied end-to-end, leaving guidance concrete but incomplete.	2 / 3
Workflow Clarity	The ordered "Reference Hierarchy" (1-5) gives a priority sequence, and this non-destructive skill needs no validation checkpoint, but the steps for applying the rules into a finished prompt are not laid out as an explicit sequence with checkpoints.	2 / 3
Progressive Disclosure	At under 50 lines with no external references needed, the skill is well-organized into clearly headed sections (Source Basis, Reference Hierarchy, Prompting Rules, Consistency Rules, Camera Control Rules, Good Motion Language, Avoid), satisfying the simple-skill allowance for a top score on organization alone.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 and domain-appropriate with a clear "Use for" trigger and named platforms, but it lists capability categories rather than concrete actions and leaves the core "what" (video prompt generation) implied rather than stated distinctly. It is solid but not exemplary.

Suggestions

Lead with a concrete verb stating what the skill does, e.g. "Generate video prompts for image-to-video, reference-video continuity..." so the "what" is explicit and distinct from the "when" trigger.

Add common user phrasings such as "animate an image", "video from image", or "consistent character across shots" to broaden trigger-term coverage.

Tighten the niche framing (e.g. emphasize continuity/identity persistence) to reduce overlap with a generic video-generation skill.

Dimension	Reasoning	Score
Specificity	It names concrete capability areas ("image-to-video, reference-video continuity, keyframe-driven prompting, camera control, and consistency workflows") and source platforms (Runway, Kling), but these are workflow categories rather than discrete actions like "extract text, fill forms, merge documents," and it omits concrete output parameters.	2 / 3
Completeness	An explicit trigger clause exists ("Use for image-to-video..."), but the "what does this do" answer is fused into the trigger rather than stated as a distinct action; the prompting purpose is only implied by the word "prompting" rather than declared.	2 / 3
Trigger Term Quality	Natural terms users would say are present ("image-to-video", "keyframes", "camera control", "reference-video", "Runway", "Kling"), but common variations like "animate an image", "video generation", or "consistent character video" are missing, so coverage is good but not comprehensive.	2 / 3
Distinctiveness Conflict Risk	The reference-driven/continuity niche and named platforms give it a reasonably distinct identity, but it could still overlap with a more general video-generation or video-prompting skill, so conflict risk is not fully eliminated.	2 / 3
	Total	8 / 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: nolanx-ai/nolanx.ai
Path: .nolanx/skills/reference-driven-video-prompting/SKILL.md
Commit: 595d863

Reviewed: about 10 hours 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.