klingai-sdk-patterns

Production SDK patterns for Kling AI: client wrapper, retry logic, async polling, and error handling. Use when building robust integrations. Trigger with phrases like 'klingai sdk', 'kling ai client', 'klingai patterns', 'kling ai wrapper'.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/klingai-pack/skills/klingai-sdk-patterns/SKILL.md

Quality

Content

65%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 content is actionable, mostly lean code with little padding, but it inlines large client implementations that duplicate existing reference files and never links to them. Async/batch submission also lacks validation checkpoints.

Suggestions

Reference the existing bundle files from the body (e.g. 'See references/python-client-pattern.md for the full client') instead of inlining the complete implementations, moving SKILL.md toward an overview.

Add a validation/verification checkpoint for async batch submission (e.g. how to confirm a task_id was accepted and how to detect/handle a failed task_status beyond raising).

Complete the Node.js client to match the Python surface (image_to_video, extend_video) or explicitly note it is a minimal example pointing to references/typescript-client-pattern.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable code with a single-sentence overview and no padding about concepts Claude already knows; only minor instances (e.g. redundant 'Production-ready' restatement, commented '# Apply to client methods') could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready Python and Node.js client code plus usage examples, but the Node.js client covers only text-to-video (no image/extend), and the retry decorator block omits its own imports and applies to an instance method in a fragile way.	4 / 5
Workflow Clarity	The usage section distinguishes synchronous vs fire-and-forget submission, but there are no validation/verification checkpoints for the async batch submission path, capping this dimension at 3 per the batch-operations guidance.	3 / 5
Progressive Disclosure	The body has clear section headers, but the full client implementations are inlined while sibling bundle files exist in references/ (python-client-pattern.md, typescript-client-pattern.md, examples.md, errors.md, error-handling-pattern.md) yet are never referenced or signaled from SKILL.md.	3 / 5
	Total	14 / 20 Passed

Description

83%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 states what the skill does and when to use it, with concrete, distinct trigger phrases. It is held back only by minor coverage gaps and a slightly generic 'when' condition.

Suggestions

Fix the malformed YAML: the description field has stray newlines splitting words (e.g. 'error' / 'handling', 'klingai sdk'', / ''kling ai client''), which fragments the rendered text and risks parsing issues.

Add the auto-refreshing JWT/token-auth pattern to the 'what' list so the description reflects the full capability set shown in the body.

Tighten the 'when' clause to reference Kling AI specifically rather than the generic 'building robust integrations'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Kling AI') and lists several concrete actions — 'client wrapper, retry logic, async polling, and error handling' — but omits other patterns present in the body (e.g. auto-refreshing JWT), leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (production SDK patterns: client wrapper, retry, async polling, error handling) and 'when' ('Use when building robust integrations') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Provides four natural trigger phrases ('klingai sdk', 'kling ai client', 'klingai patterns', 'kling ai wrapper') that a user might say, but is missing common synonyms or a file/extension-style term; good but not exhaustive coverage.	4 / 5
Distinctiveness Conflict Risk	The 'Kling AI' niche is specific and the trigger phrases are distinct, but the 'when' clause ('building robust integrations') is somewhat generic, leaving minor overlap risk with general SDK-pattern skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/klingai-pack/skills/klingai-sdk-patterns/SKILL.md
Commit: 8585d6d

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.