klingai-performance-tuning
Optimize Kling AI for speed, quality, and cost efficiency. Use when improving generation times or finding optimal settings. Trigger with phrases like 'klingai performance', 'kling ai optimize', 'faster klingai', 'klingai quality settings'.
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-performance-tuning/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 is well-structured with clear 'what' and 'when' clauses and a distinct niche around Kling AI optimization. Its main weaknesses are that the specific capabilities could be more concrete (listing actual optimization actions rather than general goals) and the trigger terms feel somewhat mechanical rather than reflecting natural user language.
Suggestions
Add more specific concrete actions like 'tune resolution settings, configure batch processing, adjust model parameters, reduce API costs' to improve specificity.
Include more natural trigger term variations users would actually say, such as 'kling is slow', 'speed up kling', 'reduce kling costs', 'kling generation time', or 'kling settings'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Kling AI optimization) and mentions some actions ('optimize', 'improving generation times', 'finding optimal settings'), but doesn't list multiple specific concrete actions like tuning batch sizes, adjusting resolution parameters, or configuring caching. | 2 / 3 |
Completeness | Clearly answers both 'what' (optimize Kling AI for speed, quality, and cost efficiency) and 'when' (when improving generation times or finding optimal settings), with explicit trigger phrases provided. | 3 / 3 |
Trigger Term Quality | Includes some relevant trigger terms like 'klingai performance', 'kling ai optimize', 'faster klingai', 'klingai quality settings', but these feel somewhat formulaic and miss natural user phrasings like 'speed up kling', 'kling is slow', 'reduce kling costs', or 'kling generation taking too long'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Kling AI performance optimization; unlikely to conflict with other skills due to the highly specific product name and optimization focus. | 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 is a solid, actionable skill with concrete code examples and a useful speed/quality comparison matrix. Its main weaknesses are the lack of validation/error-handling steps in the workflows (especially the benchmarking tool silently including failed runs) and some verbosity in explaining concepts Claude would already know. The content would benefit from being split across files given its length.
Suggestions
Add error handling and validation to the benchmarking tool — filter out failed runs from timing averages and include a retry/diagnostic step when tasks fail.
Move the caching strategy and benchmarking tool code into separate referenced files to improve progressive disclosure and reduce the main skill's token footprint.
Remove explanatory comments that state the obvious to Claude (e.g., 'Without pooling: new TCP connection per request (slow)') to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and code, but includes some unnecessary commentary (e.g., 'Without pooling: new TCP connection per request (slow) / With pooling: reuse connections (fast)' is obvious to Claude). The caching class implementation is somewhat verbose for what it demonstrates, and the prompt optimization tips table explains concepts Claude already understands. | 2 / 3 |
Actionability | Provides fully executable Python code for benchmarking, connection pooling, and caching. The speed vs. quality matrix gives specific numbers for generation times and credits. Code examples are copy-paste ready with concrete model names and parameters. | 3 / 3 |
Workflow Clarity | The optimization checklist provides a clear sequence of recommendations, and the benchmarking tool has a clear submit-poll-measure flow. However, there are no validation checkpoints or error recovery steps — the benchmarking code doesn't handle failed tasks properly (they're included in timing averages), and there's no guidance on what to do when optimization doesn't achieve desired results. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear section headers and a logical flow from overview to specific techniques. However, the skill is fairly long with substantial inline code that could be split into referenced files (e.g., the benchmarking tool and caching strategy). The two external resource links at the end are helpful but the body itself is monolithic. | 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.