klingai-async-workflows
Build async video generation workflows with Kling AI using queues, state machines, and event-driven patterns. Trigger with phrases like 'klingai async', 'kling ai workflow', 'klingai pipeline', 'async video generation'.
59
70%
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-async-workflows/SKILL.mdQuality
Discovery
75%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 establishes a clear niche and provides explicit trigger guidance, which is good for completeness and distinctiveness. However, the specific capabilities could be more concrete (listing actual actions rather than architectural patterns), and the trigger terms feel artificially constructed rather than reflecting natural user language.
Suggestions
Add concrete actions like 'submit video generation jobs, poll for status, handle completion callbacks, retry failed generations' instead of abstract architectural terms.
Include more natural trigger terms users would actually say, such as 'kling video', 'video queue', 'background video generation', 'kling API', or 'batch video generation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (async video generation with Kling AI) and mentions some architectural patterns (queues, state machines, event-driven patterns), but doesn't list specific concrete actions like 'submit generation jobs', 'poll for completion', 'handle callbacks', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (build async video generation workflows with Kling AI using queues, state machines, and event-driven patterns) and 'when' (explicit trigger phrases provided with 'Trigger with phrases like...'). | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'klingai async', 'kling ai workflow', 'klingai pipeline', 'async video generation', but these feel more like engineered trigger phrases than natural terms a user would say. Missing natural variations like 'kling video', 'background video generation', 'video queue', or 'kling AI API'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche combining Kling AI + async workflows + video generation. Unlikely to conflict with other skills due to the highly specific domain and tool combination. | 3 / 3 |
Total | 10 / 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 skill provides solid, actionable code for async Kling AI video workflows with multiple useful patterns (queue, state machine, pipeline, webhook). Its main weaknesses are the lack of validation/error-handling checkpoints in the workflows and the somewhat monolithic structure that could benefit from splitting detailed implementations into separate files. The content is mostly efficient but could trim some explanatory text.
Suggestions
Add explicit validation checkpoints: verify API response status codes after submission, validate downloaded video file size/integrity, and add error handling for network failures in the queue worker.
Add a retry feedback loop in the Redis queue worker (e.g., re-enqueue failed jobs with backoff) rather than just pushing to a failed queue.
Consider splitting the state machine and Redis queue implementations into separate bundle files, keeping SKILL.md as a concise overview with links to detailed patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with executable code examples, but includes some unnecessary framing (e.g., 'This skill covers production patterns for integrating this into larger systems using queues, state machines, and event-driven architectures') and the overview paragraph explains what async means, which Claude already knows. Some sections like the state machine are quite lengthy for what they convey. | 2 / 3 |
Actionability | All code examples are concrete, executable Python with real API endpoints, proper authentication, and complete implementations. The Redis queue worker, state machine, and pipeline patterns are all copy-paste ready with specific Kling AI API details. | 3 / 3 |
Workflow Clarity | The multi-step pipeline has a clear sequence, and the Redis worker has a well-defined loop. However, there are no explicit validation checkpoints — no error handling for API submission failures, no verification that downloaded videos are valid, and the poll_task function is referenced but not defined (deferred to another skill). Missing feedback loops for retry logic in the queue worker. | 2 / 3 |
Progressive Disclosure | The content is well-sectioned with clear headers, and references external resources and another skill ('klingai-webhook-config', 'job-monitoring skill'). However, with no bundle files, the inline content is quite long (~150 lines of code) and some patterns (like the full state machine implementation) could be split into separate reference files for better organization. | 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
8a9cd04
- 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.