Tessl • The management layer for AI agent skills

SkillPublic

ltx2

AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.

Quality

87%

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

82%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.

Excellent actionable reference for a single-command tool: copy-paste commands, complete parameter documentation, and honest limitations with recovery guidance. Remaining improvements are minor — a validation habit after generation and moving the prompt/use-case library to a reference file.

Suggestions

Add a brief post-generation verification step (e.g. spot-check the clip for training-data logos/text before use, re-run with a new --seed if present) to close the workflow validation gap.

Move the 'Good Prompts' examples and 'Video Production Use Cases' recipes to a one-level reference file to slim the always-loaded body.

Deduplicate the max-duration and quality/steps facts between 'Technical Details', 'Known Limitations', and the parameter table.

Dimension	Reasoning	Score
Conciseness	Efficient and information-dense: every section carries model-specific knowledge Claude would not know (frame-count formula, costs, cold start, valid resolutions), with no padding of known concepts. Not a 5 due to minor trims available, e.g. max duration is stated in both 'Technical Details' and 'Known Limitations', and '--quality fast' overlaps with the '--steps' override.	4 / 5
Actionability	Fully executable throughout: copy-paste CLI commands in 'Quick Reference', a complete parameter table with defaults and constraints, enumerated valid frame counts, resolutions, concrete good/bad prompt examples, and exact setup commands. Matches the anchor for copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	The setup section is a clearly numbered 4-step sequence ending in an explicit test command, and 'Known Limitations' provides a recovery loop for the main failure mode ('re-run with different --seed'). Not a 5 because the generation flow itself has no verification checkpoint (e.g. confirming the output clip is usable before proceeding).	4 / 5
Progressive Disclosure	A self-contained single-file skill with well-organized sections (Quick Reference, Parameters, Prompting Guide, Use Cases, Technical Details, Setup) and no nested references. Not a 5 because the ~170-line body exceeds the short-skill exception and keeps the prompt-example library and use-case recipes inline where a one-level reference file would reduce context cost.	4 / 5
	Total	17 / 20 Passed

Description

86%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.

A strong description that explicitly covers what the skill does and when to use it, with an unusually thorough set of natural trigger phrases. The only notable gap is that the capability list is thin beyond the two core modes, slightly understating what the tool can do.

Suggestions

Expand the capability list beyond the two core modes, e.g. mention controllable resolution, duration (up to ~8s), and seed-reproducible output as concrete actions in the first sentence.

Consider trimming the near-duplicate 'Triggers include' line, since the 'Use when' clause already lists most of the same natural phrases.

Dimension	Reasoning	Score
Specificity	Names the domain ('AI video generation with LTX-2.3 22B') and two concrete actions ('text-to-video, image-to-video clips'), matching the anchor for 1-2 concrete actions. It is not a 4 because the capability list stops at two actions rather than 'several specific actions' with minor gaps.	3 / 5
Completeness	Explicitly answers both 'what' (AI video generation with LTX-2.3 22B, text-to-video and image-to-video clips) and 'when' ('Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content') with concrete trigger phrases. Matches the anchor requiring both what and when with concrete triggers.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and variations: 'video generation', 'animate image', 'b-roll', 'motion', 'video clip', 'text-to-video', 'image-to-video', plus use-case phrases like 'generating video clips' and 'animating images'. Matches the top anchor's breadth of synonyms.	5 / 5
Distinctiveness Conflict Risk	A clear video-generation niche with model-specific trigger terms, mostly distinct from other skills. Not a 5 because broad terms like 'motion' and 'b-roll' carry minor overlap risk with closely related video/animation tools.	4 / 5
	Total	17 / 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: calesthio/OpenMontage
Path: .agents/skills/ltx2/SKILL.md
Revision: d21f5d4

Reviewed: 22 days ago

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.

ltx2

Table of Contents

Is this your skill?