klingai-reference-architecture

Production reference architecture for Kling AI video generation platforms. Use when designing scalable systems. Trigger with phrases like 'klingai architecture', 'kling ai system design', 'video platform architecture', 'klingai production setup'.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

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

The body is concrete and specific with real code, endpoints, and tables, but it is a monolith that inlines content duplicated in the bundle's reference files while never linking to any of them, and its code is not self-contained nor accompanied by an error-recovery feedback loop. The main gaps are progressive disclosure and workflow completeness.

Suggestions

Signal the existing bundle files from the body — e.g., under Docker Compose point to references/docker-compose-setup.md, and add an Advanced section linking architecture-patterns.md, kubernetes-deployment.md, errors.md, and examples.md — so the inline content can be trimmed and navigation is one level deep.

Make the code examples runnable or explicitly justify the abstraction: define or stub estimate_credits/budget_guard and the kling/storage clients (or note they are interfaces), add the missing os import, and link to complete-reference-implementation.md for the full version.

Add an explicit error-recovery feedback loop for failed jobs — describe how the kling:jobs:failed queue is inspected, retried, or dead-lettered — so the workflow includes a validate/fix/retry checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is code- and table-forward without padding known concepts, but it inlines a full docker-compose that duplicates references/docker-compose-setup.md and reproduces full implementation code that overlaps references/complete-reference-implementation.md, so tokens do not all 'earn their place' — matching the level-2 'mostly efficient but could be tightened' anchor rather than level 3.	2 / 3
Actionability	It provides real, specific Python and YAML with concrete endpoints ('https://api.klingai.com/v1/videos/text2video', 'kling-v2-master', 2500-char limit, tier concurrency numbers), but the code is not runnable as-is — undefined helpers (estimate_credits, budget_guard, self.kling, self.storage) and a missing os import — and the abstraction is not explicitly justified, matching level-2 'concrete guidance but incomplete / missing key details' rather than the copy-paste-ready level 3.	2 / 3
Workflow Clarity	The diagram and numbered API steps ('# 1. Validate', '# 2. Estimate cost', '# 3. Enqueue') give a clear sequence with API-layer validation, but there is no validate->fix->retry feedback loop: failed jobs are pushed to a failed queue with no redrive/retry described, matching level-2 'sequence present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	Six reference files exist (architecture-patterns, complete-reference-implementation, docker-compose-setup, errors, examples, kubernetes-deployment) but none are linked or signaled from the body, while content that belongs in them (docker-compose, full implementation) is inlined and duplicated — matching level-2 'references present but not clearly signaled; content that should be separate is inline' rather than the well-signaled level 3.	2 / 3
	Total	8 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that clearly answers both what and when, with explicit natural-language triggers and a distinct niche. The only weakness is that it describes an abstract deliverable ('reference architecture') rather than enumerating concrete actions.

Dimension	Reasoning	Score
Specificity	It names a sharp domain ('Kling AI video generation platforms') and a use case ('Use when designing scalable systems'), but 'reference architecture' is an abstract deliverable rather than a list of multiple concrete actions like 'extract', 'fill', 'merge' — so it falls short of the level-3 anchor without being vague enough for level 1.	2 / 3
Completeness	It explicitly states what it does ('Production reference architecture for Kling AI video generation platforms') and when to use it ('Use when designing scalable systems. Trigger with phrases like...'), satisfying both halves with explicit triggers per the level-3 anchor.	3 / 3
Trigger Term Quality	It supplies several natural phrases a user would say ('klingai architecture', 'kling ai system design', 'video platform architecture', 'klingai production setup') with good variation, matching the level-3 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	The Kling AI video-generation niche plus klingai-specific trigger phrases make it clearly distinguishable and unlikely to fire for unrelated skills, matching the level-3 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 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
Commit: 3022dd3

Reviewed: 1 day 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.