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

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/klingai-pack/skills/klingai-reference-architecture/SKILL.md

Quality

Content

61%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 concise and actionably concrete with runnable code, tables, and a clear architecture diagram. Its main weakness is progressive disclosure: it inlines content that duplicates orphaned reference files and never navigates the reader to the bundle it ships.

Suggestions

Replace the inlined Docker Compose and full implementation blocks with short summaries that link to references/docker-compose-setup.md, references/complete-reference-implementation.md, and references/kubernetes-deployment.md so the bundle is actually used.

Add a 'References' or 'Dig deeper' section that lists all six files in references/ with one-line descriptions and links, giving one-level-deep navigation.

Insert an explicit validation/checkpoint note in the worker flow (e.g. verify task_id was received, retry on failure via the failed queue) to lift workflow clarity above 3.

Dimension	Reasoning	Score
Conciseness	The body is lean: a one-sentence overview, an ASCII diagram, compact code blocks, and tight tables, with only minor inline comments that could be trimmed; it avoids explaining concepts Claude already knows and is just below the fully lean 5.	4 / 5
Actionability	Provides concrete, mostly executable FastAPI/worker/docker-compose code and specific scaling tables, but relies on undefined abstractions (estimate_credits, budget_guard, kling_client, storage_client) and a missing os import, leaving minor gaps short of fully copy-paste-ready 5.	4 / 5
Workflow Clarity	The architecture diagram gives a clear request lifecycle sequence (User -> API -> Queue -> Worker -> Webhook -> Storage -> CDN), but there are no explicit validation checkpoints or feedback loops in the component steps, matching the 'sequence present but checkpoints missing' anchor; this is a reference architecture rather than a destructive runbook, so the batch cap is not the binding factor.	3 / 5
Progressive Disclosure	A bundle of six reference files exists (architecture-patterns, complete-reference-implementation, docker-compose-setup, errors, examples, kubernetes-deployment), but the body never links to any of them and instead inlines the docker-compose setup and full implementations that clearly belong in those separate files; 'Resources' points only to external URLs, leaving the references orphaned and signaling minimal disclosure structure.	2 / 5
	Total	13 / 20 Passed

Description

70%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 is a solid, third-person statement that answers what and when with concrete, natural trigger phrases scoped to a clear Kling AI niche. It is held back from the top band by a generic 'when' clause ('designing scalable systems') and a thin action list.

Suggestions

Tighten the 'when' clause to be more specific, e.g. 'Use when designing or scaling a Kling AI video-generation backend' instead of the generic 'designing scalable systems'.

Add 1-2 concrete capabilities beyond 'reference architecture' (e.g. 'covers API gateway, job queue, worker pool, storage, and monitoring layers') to lift specificity toward the comprehensive anchor.

Drop or qualify the broad trigger 'video platform architecture' to reduce overlap with non-Kling video skills, or pair it with 'kling' to keep the niche distinct.

Dimension	Reasoning	Score
Specificity	Names the domain ('Kling AI video generation platforms') and a concrete use ('designing scalable systems'), but the action set is limited to architecture/design rather than a comprehensive list of capabilities; it sits at the 'names domain and 1-2 concrete actions' anchor and is not yet at the 'several specific actions' level (4).	3 / 5
Completeness	Explicitly answers both 'what' ('Production reference architecture for Kling AI video generation platforms') and 'when' ('Use when designing scalable systems') with concrete trigger phrases, matching the 'has both what and when' anchor; the 'when' clause is generic enough that it does not fully reach the precise, comprehensive 5 anchor.	4 / 5
Trigger Term Quality	Provides four trigger phrases including a synonym pair ('klingai architecture' / 'kling ai system design') and natural terms a user would say, giving good keyword coverage; it falls short of 5 only because the set is phrase-based without broader synonym/extension variations.	4 / 5
Distinctiveness Conflict Risk	The Kling-specific triggers ('klingai architecture', 'kling ai system design', 'klingai production setup') carve a clear niche, but the broader phrase 'video platform architecture' could overlap with non-Kling video platform skills, leaving minor overlap risk rather than the minimal-conflict 5.	4 / 5
	Total	15 / 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-reference-architecture/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.