klingai-sdk-patterns
Production SDK patterns for Kling AI: client wrapper, retry logic, async polling, and error handling. Use when building robust integrations. Trigger with phrases like 'klingai sdk', 'kling ai client', 'klingai patterns', 'kling ai wrapper'.
64
77%
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-sdk-patterns/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 solid description that clearly identifies its niche (Kling AI SDK patterns) and provides explicit trigger terms. Its main weakness is that the capabilities listed are somewhat abstract pattern categories rather than concrete actions, and it doesn't clarify what Kling AI itself does, which could help with broader trigger matching. Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions like 'generate videos', 'create images', or whatever Kling AI's core functionality is, to improve specificity and help users who describe the task rather than the SDK name.
Consider adding file type or technology triggers (e.g., 'video generation API', 'AI video SDK') to capture users who may not know the product name but are working in the same domain.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Kling AI SDK) and lists some actions (client wrapper, retry logic, async polling, error handling), but these are more like pattern categories than concrete actions. It doesn't specify what the SDK actually does (e.g., generate videos, create images). | 2 / 3 |
Completeness | Clearly answers both 'what' (production SDK patterns for Kling AI including client wrapper, retry logic, async polling, error handling) and 'when' (when building robust integrations, with explicit trigger phrases). | 3 / 3 |
Trigger Term Quality | Explicitly lists natural trigger phrases like 'klingai sdk', 'kling ai client', 'klingai patterns', 'kling ai wrapper'. These cover common variations a user would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Kling AI' and SDK-specific patterns. Unlikely to conflict with other skills given the narrow niche of Kling AI SDK integration patterns. | 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 strong, actionable skill with production-quality executable code covering JWT auth, polling, retries, and error handling for the Kling AI API. Its main weaknesses are token efficiency (the Node.js near-duplicate and minor verbosity) and missing explicit error recovery/validation workflows beyond what's embedded in the code itself. The monolithic structure could benefit from splitting into referenced files for the secondary language and utility patterns.
Suggestions
Consider moving the Node.js client to a separate referenced file (e.g., NODEJS.md) to reduce the main skill's token footprint while preserving the information.
Add a brief troubleshooting/error recovery section: what to do on auth failures, how to verify API keys are set, and how to handle common generation failures.
Remove the overview paragraph since the heading and code structure already communicate the skill's purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable code, but includes some unnecessary elements: the docstring 'Production Kling AI client with auto-refreshing JWT' and the overview paragraph restate what the skill title already conveys. The Node.js client is a near-duplicate of the Python client pattern, adding significant token cost for marginal value. | 2 / 3 |
Actionability | Fully executable Python and Node.js code with complete client implementations, usage examples, retry decorator, and error classes. The code is copy-paste ready with real API endpoints, proper JWT handling, and concrete usage patterns showing both sync and async modes. | 3 / 3 |
Workflow Clarity | The polling workflow with exponential backoff is well-implemented in code, and the usage section shows sync vs fire-and-forget patterns. However, there's no explicit guidance on error recovery workflows (what to do when generation fails), no validation steps for inputs, and no guidance on checking API key setup before first use. | 2 / 3 |
Progressive Disclosure | The content is organized into logical sections (client, usage, Node.js, retry, resources), but it's a monolithic file with ~200 lines of code that could benefit from splitting the Node.js client and retry patterns into separate referenced files. The external resource links at the end are helpful but minimal. | 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.