klingai-webhook-config
Configure webhook callbacks for Kling AI task completion. Use when building event-driven pipelines or replacing polling. Trigger with phrases like 'klingai webhook', 'kling ai callback', 'klingai notifications', 'video completion webhook'.
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-webhook-config/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 with clear 'what' and 'when' clauses, good trigger terms, and a distinct niche. The main weakness is that the capability description could be more specific about the concrete actions involved (e.g., registering endpoints, handling callback payloads, configuring retry logic).
Suggestions
Add more specific concrete actions beyond 'configure webhook callbacks' — e.g., 'register callback endpoints, verify webhook signatures, parse completion payloads' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Kling AI webhook callbacks) and mentions a couple of actions (configure webhook callbacks, replacing polling), but doesn't list multiple concrete actions like registering endpoints, verifying signatures, handling payloads, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (configure webhook callbacks for Kling AI task completion) and 'when' (building event-driven pipelines, replacing polling) with explicit trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'klingai webhook', 'kling ai callback', 'klingai notifications', 'video completion webhook'. These cover common variations and are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche — Kling AI webhooks — with distinct trigger terms that are unlikely to conflict with other skills. The combination of 'Kling AI' and 'webhook' creates a clear, narrow scope. | 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 code examples covering task submission, webhook receiving, payload structure, and a reliability fallback pattern. Its main weaknesses are moderate verbosity (dual framework examples, JWT boilerplate tangential to webhooks, unused hmac import suggesting incomplete security guidance), and missing validation checkpoints like webhook signature verification and endpoint health checks before task submission.
Suggestions
Remove the unused hmac/hashlib imports or implement actual webhook signature verification—the current state implies security handling that doesn't exist, which is misleading.
Trim the JWT auth boilerplate into a one-line reference (e.g., 'Use get_headers() from the auth skill') since it's not webhook-specific and consumes significant tokens.
Add an explicit validation step: verify your webhook endpoint is reachable and returns 2xx before submitting tasks with callback_url.
Consider picking one framework for the receiver example (Flask) and noting Express.js as an alternative pattern in a referenced file to reduce inline length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary verbosity. The 'How It Works' section restates what's already clear from the overview. Providing both Flask and Express examples is borderline—useful for coverage but adds tokens. The JWT auth boilerplate in the task creation example is tangential to the webhook topic. | 2 / 3 |
Actionability | Fully executable code examples for both sending tasks with callbacks and receiving webhooks in two frameworks. The payload shape is documented, the reliability fallback pattern is concrete and copy-paste ready, and the requirements table gives specific constraints. | 3 / 3 |
Workflow Clarity | The 'How It Works' section outlines the sequence clearly, and the reliability pattern provides a fallback mechanism. However, there are no explicit validation checkpoints—no guidance on verifying the webhook endpoint is reachable before submitting tasks, no signature/HMAC verification step despite importing hmac/hashlib (unused), and no error recovery loop for the webhook receiver itself. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but it's somewhat monolithic for its length (~130 lines of content). The WebhookManager class and dual-framework examples could be split into referenced files. External links to API docs are provided, but there are no bundle files to offload detailed content. | 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
a04d1a2
- 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.