klingai-reference-architecture
Production reference architecture for Kling AI video generation platforms. Use when designing scalable systems. Trigger with phrases like 'klingai architecture', 'kling ai system design', 'video platform architecture', 'klingai production setup'.
48
52%
Does it follow best practices?
Impact
—
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-reference-architecture/SKILL.mdQuality
Discovery
40%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 identifies a narrow domain (Kling AI video generation) but fails to specify what concrete actions the skill performs, relying on vague terms like 'reference architecture' and 'scalable systems'. The trigger phrases feel manufactured rather than natural, and the lack of concrete capabilities makes it hard for Claude to confidently select this skill over alternatives.
Suggestions
Replace 'Production reference architecture' with specific actions the skill performs, e.g., 'Generates infrastructure diagrams, API integration code, queue configurations, and deployment manifests for Kling AI video generation platforms.'
Use more natural trigger terms that users would actually say, such as 'Kling AI app', 'Kling video API', 'build video generation service', 'Kling AI integration', or 'video generation backend'.
Strengthen the 'what' portion by listing 2-4 concrete deliverables or outputs the skill produces, rather than relying on abstract concepts like 'reference architecture' and 'scalable systems'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'Production reference architecture for Kling AI video generation platforms' and 'designing scalable systems' but never lists concrete actions like 'generates architecture diagrams', 'configures API endpoints', or 'sets up queue workers'. The language is abstract and buzzword-heavy ('reference architecture', 'scalable systems'). | 1 / 3 |
Completeness | It has a 'Use when' clause ('Use when designing scalable systems') and trigger phrases, but the 'what' is extremely vague—'production reference architecture' doesn't explain what the skill actually does (e.g., does it generate diagrams, write infrastructure code, produce documentation?). The 'when' is present but the 'what' is too weak for a score of 3. | 2 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'klingai architecture', 'kling ai system design', 'video platform architecture', and 'klingai production setup'. However, these feel artificially constructed rather than natural user phrases—users are more likely to say 'build a Kling AI video app' or 'Kling API integration' than 'klingai architecture'. | 2 / 3 |
Distinctiveness Conflict Risk | The Kling AI specificity helps distinguish it from generic architecture skills, but 'video platform architecture' and 'designing scalable systems' are broad enough to overlap with general system design or other video platform skills. The niche is somewhat defined but not sharply bounded. | 2 / 3 |
Total | 7 / 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 reference architecture with concrete code examples, deployment configuration, and useful scaling guidelines. Its main weaknesses are the lack of explicit validation/error recovery workflows and the monolithic structure that inlines all implementation details rather than using progressive disclosure. The content would benefit from splitting detailed implementations into separate files and adding retry/validation checkpoints.
Suggestions
Add explicit error recovery and retry workflows for failed video generation jobs (e.g., retry with backoff, dead letter queue handling, validation of downloaded videos before upload)
Split the worker implementation, Docker Compose setup, and scaling tables into separate referenced files (e.g., WORKER.md, DEPLOYMENT.md) to keep SKILL.md as a concise architectural overview
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with concrete code examples and tables, but includes some unnecessary detail like the full Docker Compose setup and worker implementation that could be in separate files. The architecture diagram and component details are useful but the overall length (~150 lines) is heavy for a reference architecture overview. | 2 / 3 |
Actionability | Provides fully executable FastAPI code, a concrete worker implementation, Docker Compose configuration, and specific scaling tables with concrete numbers. The code is copy-paste ready and includes real API endpoints, environment variables, and deployment configuration. | 3 / 3 |
Workflow Clarity | The architecture diagram provides a clear sequence of steps from user request to video delivery, and the code shows the flow. However, there are no explicit validation checkpoints or error recovery feedback loops — the worker's exception handling just pushes to a failed queue with no retry mechanism or verification steps documented. | 2 / 3 |
Progressive Disclosure | The content includes external links to API reference and developer portal, but all implementation details (API layer, worker, Docker Compose, scaling tables) are inline rather than split into separate reference files. The Docker Compose and worker code would be better as separate referenced files, keeping SKILL.md as a concise overview. | 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
d41e58e
- 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.