Avoid common mistakes when using Kling AI API. Use when troubleshooting or learning best practices. Trigger with phrases like 'klingai pitfalls', 'kling ai mistakes', 'klingai gotchas', 'klingai best practices'.
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-known-pitfalls/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 clear niche (Kling AI API pitfalls) and includes explicit trigger phrases, which is good. However, it fails to describe any specific capabilities or concrete actions—what mistakes does it help avoid? What best practices does it teach? The vagueness of the 'what' significantly undermines its usefulness for skill selection.
Suggestions
Replace 'avoid common mistakes' with specific examples of what the skill covers, e.g., 'Covers authentication setup, rate limit handling, callback URL configuration, and response parsing for Kling AI API'.
Add concrete actions the skill performs, e.g., 'Diagnoses common error codes, provides correct request formatting, and explains API parameter constraints'.
Expand trigger terms to include natural user phrases like 'Kling API error', 'Kling API not working', 'Kling API debugging', or 'Kling video generation issues'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'avoid common mistakes' and 'learning best practices' but never specifies what those mistakes or practices are. No concrete actions like 'handle authentication errors', 'configure rate limits', or 'format API requests correctly' are mentioned. | 1 / 3 |
Completeness | The 'when' clause is present ('Use when troubleshooting or learning best practices') with explicit trigger phrases, but the 'what' is extremely vague—'avoid common mistakes' doesn't tell Claude what the skill actually does or what content it provides. The what is too weak to earn a 3. | 2 / 3 |
Trigger Term Quality | Includes some relevant trigger terms like 'klingai pitfalls', 'kling ai mistakes', 'klingai gotchas', 'klingai best practices', and 'troubleshooting'. However, it misses natural variations users might say like 'Kling API errors', 'Kling API not working', 'Kling API help', or 'Kling AI debugging'. | 2 / 3 |
Distinctiveness Conflict Risk | The Kling AI API focus is fairly niche and unlikely to conflict with most skills, but 'troubleshooting' and 'best practices' are generic enough that it could overlap with a general Kling AI API usage skill or other API troubleshooting skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent troubleshooting skill that is lean, actionable, and well-structured. Each pitfall follows a consistent symptom/wrong/correct pattern with executable code examples. The quick reference table provides efficient scanning, and the content avoids unnecessary explanation while covering real-world integration issues comprehensively.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every pitfall is presented with minimal explanation—just symptom, wrong/correct code, and a one-line root cause. No unnecessary preamble or concepts Claude already knows. The quick reference table is a compact summary that earns its place. | 3 / 3 |
Actionability | Each pitfall includes executable Python code showing both the wrong and correct approach. The fixes are copy-paste ready with specific parameter values, timeout durations, and concrete patterns. | 3 / 3 |
Workflow Clarity | This is a reference/troubleshooting skill rather than a multi-step workflow, so sequential process isn't the primary concern. Each pitfall clearly sequences symptom → root cause → fix, and pitfalls involving risky operations (polling, token refresh) include explicit validation/timeout patterns. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers per pitfall, a summary table for quick scanning, and external links to API reference and developer portal. For a standalone skill with no bundle, the structure is appropriately flat and navigable. | 3 / 3 |
Total | 12 / 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 | |
70e07c0
Table of Contents
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.