klingai-job-monitoring
Track and monitor Kling AI video generation task status. Use when building dashboards, tracking batch jobs, or debugging stuck tasks. Trigger with phrases like 'klingai job status', 'kling ai monitor', 'track klingai task', 'klingai progress'.
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-job-monitoring/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 skill description with clear 'when' triggers and a distinctive niche around Kling AI task monitoring. The main weakness is that the specific capabilities could be more concrete—listing actual actions the skill performs (e.g., 'query task status APIs, display progress percentages, retry failed tasks') rather than just use cases. The trigger terms are well-chosen and the description is unlikely to conflict with other skills.
Suggestions
Add more specific concrete actions the skill performs, e.g., 'query task status, display progress, list failed tasks, retry stuck jobs' instead of just 'track and monitor'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Kling AI video generation) and a general action (track and monitor task status), but doesn't list multiple specific concrete actions beyond tracking/monitoring. 'Building dashboards, tracking batch jobs, debugging stuck tasks' are use cases rather than specific capabilities the skill performs. | 2 / 3 |
Completeness | Clearly answers both 'what' (track and monitor Kling AI video generation task status) and 'when' (building dashboards, tracking batch jobs, debugging stuck tasks) with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes multiple natural trigger phrases like 'klingai job status', 'kling ai monitor', 'track klingai task', 'klingai progress' as well as broader terms like 'dashboards', 'batch jobs', 'stuck tasks'. Good coverage of variations users might say. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Kling AI video generation task monitoring. The 'klingai' and 'kling ai' terms are highly distinctive and unlikely to conflict with other 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 code covering single-task polling, batch tracking, and stuck detection for Kling AI. Its main weaknesses are the lack of explicit error recovery workflows (what to do with stuck/failed tasks) and some verbosity in the class definitions that could be tightened. The progression from simple to complex monitoring is logical but could benefit from better progressive disclosure.
Suggestions
Add explicit error recovery guidance for stuck/failed tasks (e.g., retry logic, cancellation, or escalation steps) to improve workflow clarity.
Consider extracting the BatchTracker class and stuck detection into a separate reference file, keeping SKILL.md focused on the polling pattern and batch monitor loop with links to the full implementation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and avoids explaining basic concepts, but the batch tracker class and stuck detection could be tightened. The dataclass imports and some boilerplate add tokens without critical value. The task lifecycle table is useful and concise. | 2 / 3 |
Actionability | All code is fully executable with concrete implementations: polling with adaptive intervals, batch tracking with dataclasses, stuck detection, and a complete monitor loop. Code is copy-paste ready with real API endpoints and proper JWT auth. | 3 / 3 |
Workflow Clarity | The task lifecycle table and individual components are clear, but the overall workflow lacks explicit validation checkpoints. There's no guidance on what to do when stuck tasks are detected (retry? cancel? alert?), and the batch monitor loop has no error recovery or exit strategy for persistent failures. | 2 / 3 |
Progressive Disclosure | Content is well-sectioned with clear headers progressing from single task to batch monitoring, but the skill is fairly long and could benefit from splitting the BatchTracker class and examples into a separate reference file. 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
3e83543
- 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.