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'.
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/klingai-pack/skills/klingai-text-to-video/SKILL.mdQuality
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 excellent trigger terms and clear 'what/when' guidance. Its main weakness is that the specific capabilities beyond basic video generation are somewhat vague—'learning prompt techniques' and 'building T2V pipelines' could be more concrete. Overall, it would perform well in a multi-skill selection scenario due to its distinctive branding and explicit trigger phrases.
Suggestions
Make the capabilities more concrete by specifying actions like 'craft effective Kling AI prompts for cinematic styles, camera movements, and scene composition' instead of the vague 'learning prompt techniques'.
| 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 beyond generation are somewhat vague and not fully concrete (e.g., what does 'learning prompt techniques' entail specifically?). | 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' section listing specific trigger terms). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'kling ai text to video', 'klingai prompt', 'generate video from text', 'text2video kling'. These cover brand-specific terms, common phrasing variations, and abbreviations users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific tool name 'Kling AI' and the narrow focus on text-to-video generation. The brand-specific triggers ('kling ai', 'klingai') make it very unlikely to conflict with other video or AI skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with executable Python examples covering the main use cases (basic generation, camera control, native audio). Its main weaknesses are the lack of response validation and timeout handling in the polling workflow, and the fact that all content is in a single file without supporting bundle files for the more detailed reference material. The prompt engineering tips and cost tables are useful additions but contribute to a slightly long single-file skill.
Suggestions
Add response validation after the initial POST (check HTTP status code, handle missing 'data'/'task_id' keys) and add a timeout/max-retries to the polling loop to prevent infinite loops.
Consider extracting the parameter reference table, prompt engineering tips, and cost/error tables into a separate REFERENCE.md bundle file, keeping SKILL.md focused on the quick-start workflow and key examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables for parameters, costs, and errors. However, the prompt engineering tips table and cost reference, while useful, add bulk. The code examples are well-structured but the full JWT auth boilerplate is repeated conceptually across examples (via get_headers()) which is reasonable. Some minor verbosity in descriptions but mostly tight. | 2 / 3 |
Actionability | Provides fully executable Python code including JWT authentication, task creation, polling loop, camera control, and native audio examples. All code is copy-paste ready with real endpoint URLs, specific parameter values, and complete error handling in the polling loop. | 3 / 3 |
Workflow Clarity | The main example shows a clear create-then-poll workflow with status checking for success/failure. However, there's no explicit validation of the initial POST response (checking for HTTP errors or malformed responses before accessing task_id), and the polling loop lacks a timeout or max-retry mechanism, which are important for API-based workflows. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and headers, and external resource links are provided at the bottom. However, for a skill of this length (~120 lines of substantive content), the parameter reference table and detailed examples could benefit from being split into separate files. No bundle files exist to offload detail into, so everything is inline. | 2 / 3 |
Total | 9 / 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
3a2d27d
- 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.