klingai-text-to-video

Generate videos from text prompts with Kling AI. Use when creating videos from descriptions, learning prompt techniques, or building T2V pipelines. Trigger with phrases like 'kling ai text to video', 'klingai prompt', 'generate video from text', 'text2video kling'.

Quality

80%

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

78%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 content is highly actionable with complete, runnable code and a clear create-and-poll workflow, but it underuses its own bundle: six reference files exist and are entirely unlinked, while their content is duplicated inline, hurting both conciseness and progressive disclosure.

Suggestions

Replace the inlined Prompt Engineering Tips, Cost Reference, and Error Handling tables with pointers to the existing references/prompt-engineering.md, and references/errors.md so the body stays a lean overview.

Add a 'References' section linking the six files in references/ (e.g., basic-text-to-video.md, advanced-parameters.md, batch-generation.md, examples.md) with one-line descriptions so each topic is one level deep and clearly signaled.

Add an explicit error-recovery feedback loop after the polling example (on 'failed': inspect task_status_msg, simplify prompt or remove restricted content, then re-create the task) to reach the top workflow_clarity anchor.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly efficient — parameter tables and executable code with no over-explanation of concepts Claude already knows — but inlines a Prompt Engineering Tips table, Cost Reference, and Error Handling table that duplicate content in the references/ files and could be trimmed. This is 'efficient with minor instances that could be trimmed', not the lean top anchor.	4 / 5
Actionability	Provides fully executable, copy-paste-ready Python covering JWT auth header construction, task creation, polling, camera control, and native audio — complete enough to run with environment keys and covering the common cases.	5 / 5
Workflow Clarity	The create-task → poll-for-completion sequence is clear with status checkpoints (succeed/failed/submitted/processing) in the polling loop, but there is no explicit error-recovery feedback loop (fix-and-retry) or checklist, falling short of the top anchor.	4 / 5
Progressive Disclosure	Six well-organized reference files exist (advanced-parameters, basic-text-to-video, batch-generation, errors, examples, prompt-engineering) but the body never links to or signals any of them, instead inlining the parameter/prompt/error/cost content that those files duplicate — 'references present but not clearly signaled; content that should be separate is inline'.	3 / 5
	Total	16 / 20 Passed

Description

82%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, well-scoped description that clearly states what the skill does, when to use it, and provides concrete natural-language triggers tied to a specific platform. The only weakness is specificity, which lists one primary action rather than a comprehensive set of capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('Kling AI') and the primary concrete action ('Generate videos from text prompts'), with adjacent activities ('learning prompt techniques', 'building T2V pipelines') rather than a list of several distinct actions; this matches 'names domain and 1-2 concrete actions' rather than the 'lists several specific actions' anchor above.	3 / 5
Completeness	Explicitly answers both 'what' (generate videos from text prompts with Kling AI) and 'when' (Use when creating videos, learning prompt techniques, or building T2V pipelines) with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Provides natural phrases users would say ('kling ai text to video', 'klingai prompt', 'generate video from text', 'text2video kling') including synonyms, but misses a few common variants like 'ai video generation' — good but not comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The 'Kling AI' platform niche and platform-specific trigger phrases ('klingai prompt', 'text2video kling') make this clearly distinct from other video/generation skills with minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/klingai-pack/skills/klingai-text-to-video/SKILL.md
Commit: 8585d6d

Reviewed: 13 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.