CtrlK
BlogDocsLog inGet started
Tessl Logo

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'.

56

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/klingai-pack/skills/klingai-performance-tuning/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is action-oriented with real code and a useful config matrix, but it over-explains basics, omits validation checkpoints for batch operations, and critically fails to surface the five bundled reference files it ships with.

Suggestions

Link the existing reference files from the body (e.g., 'See [performance-profiler.md](references/performance-profiler.md)' and a caching-layer.md pointer) and move the inlined caching/profiling code out to them.

Add validation/feedback checkpoints to the benchmark and batch workflows: a poll timeout/max-retries guard, cache-key sanity checks, and a 'verify output' step before declaring a render final.

Trim re-teaching of basics (connection-pooling rationale, fast-vs-slow prompt explanation) and make code self-contained by defining or stubbing BASE, get_headers(), and the client so snippets are copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient with tables, code, and a checklist, but it over-explains concepts Claude already knows (connection-pooling rationale, 'prompts that generate faster', fast-vs-slow prompt teaching), so it lands at anchor 3 rather than a lean 4.

3 / 5

Actionability

Substantial executable Python (benchmark, pooling, caching) and a concrete config matrix, but snippets have gaps (undefined BASE/get_headers/client, missing import in caching, in-memory cache unexplained), matching anchor 4 rather than fully copy-paste-ready 5.

4 / 5

Workflow Clarity

The optimization checklist gives a clear sequence, but batch/generation operations lack validation or feedback loops (no poll timeout, no cache-hit verification), and the rubric caps batch skills without validation at 3.

3 / 5

Progressive Disclosure

Five reference files exist (caching-layer, errors, examples, optimization-strategies, performance-profiler) but the body never links to any of them, inlining caching and profiling content that clearly belongs in those separate files.

2 / 5

Total

12

/

20

Passed

Description

75%Weight 40%Scale 1-5

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 clearly answers both what and when with natural trigger phrases and a well-scoped niche. It sits solidly at anchor 4 across all dimensions, falling short of 5 only in concreteness of the 'when' clause and action enumeration.

DimensionReasoningScore

Specificity

Names the Kling AI domain and several concrete optimization dimensions ('speed, quality, and cost efficiency', 'improving generation times', 'finding optimal settings'), landing at anchor 4 with minor gaps in enumerated actions.

4 / 5

Completeness

Explicitly states both what ('Optimize Kling AI for speed, quality, and cost efficiency') and when ('Use when improving generation times or finding optimal settings' plus trigger phrases), but the 'when' clause is less concrete than anchor 5.

4 / 5

Trigger Term Quality

Provides natural user phrasing ('klingai performance', 'kling ai optimize', 'faster klingai', 'klingai quality settings') including the klingai/kling ai synonym, giving good keyword coverage though it circles one product term.

4 / 5

Distinctiveness Conflict Risk

The Kling AI performance-tuning niche with product-specific trigger phrases is mostly distinct, with only minor overlap risk against a broader video-generation performance skill.

4 / 5

Total

16

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.