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'.
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description with explicit trigger guidance, clear 'what' and 'when' clauses, and strong distinctiveness through the Kling AI brand name. Its main weakness is that the capability descriptions could be more concrete—listing specific actions like configuring video parameters, choosing aspect ratios, or iterating on prompts would strengthen specificity.
Suggestions
Add more concrete actions beyond 'generate videos from text prompts', such as 'configure video resolution and duration', 'refine prompts for better output', or 'set camera motion and style parameters' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Kling AI text-to-video) and some actions ('generate videos from text prompts', 'learning prompt techniques', 'building T2V pipelines'), but the actions are not deeply concrete—e.g., it doesn't specify what aspects of video generation it handles (resolution, style, parameters, etc.). | 2 / 3 |
Completeness | Clearly answers both 'what' (generate videos from text prompts with Kling AI) and 'when' (explicit 'Use when...' clause with scenarios and a 'Trigger with phrases like...' section providing concrete trigger terms). | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms: 'kling ai text to video', 'klingai prompt', 'generate video from text', 'text2video kling'. These cover brand-specific terms, common abbreviations, and natural user phrasing variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Kling AI' and the narrow focus on text-to-video generation. Unlikely to conflict with other skills unless another Kling AI skill exists. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that provides comprehensive, actionable guidance for Kling AI text-to-video generation. The code examples are complete and executable, the parameter reference is concise, and the progressive structure from basic to advanced use cases is well done. The main weakness is that the async workflow (create task → poll → handle result) could be more explicitly called out as a numbered sequence with validation checkpoints.
Suggestions
Add an explicit numbered workflow summary (e.g., '1. Authenticate → 2. Submit task → 3. Poll every 15s → 4. Check status → 5. Handle success/failure') before the code example to make the async pattern immediately clear.
Add a pre-submission validation note (e.g., check prompt length < 2500 chars, verify model_name is valid) to create a feedback loop before the API call.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose — no explanations of what video generation is or how APIs work in general. The tables are compact, and the code examples contain only what's needed. | 3 / 3 |
Actionability | Fully executable Python code with authentication, task creation, and polling. Multiple concrete examples cover the main use cases (basic, camera control, native audio). Copy-paste ready with environment variable configuration. | 3 / 3 |
Workflow Clarity | The polling workflow is present in the code example with status checking and error handling, but there's no explicit validation checkpoint or feedback loop for common issues like prompt length validation before submission. The async nature of the API (submit → poll → result) is shown but not called out as a clear numbered workflow. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from overview to basic usage to advanced features (camera control, audio). External resources are linked at the end for deeper reference. Content is appropriately scoped for a single SKILL.md file without being monolithic. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
c8a915c
- 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.