CtrlK
BlogDocsLog inGet started
Tessl Logo

klingai-async-workflows

Build async video generation workflows with Kling AI using queues, state machines, and event-driven patterns. Trigger with phrases like 'klingai async', 'kling ai workflow', 'klingai pipeline', 'async video generation'.

61

Quality

73%

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-async-workflows/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is concise and actionable with solid executable patterns, but batch workflows lack validation/feedback loops and progressive disclosure is weak: five substantial reference files are orphaned with no links from SKILL.md while their content is partially duplicated inline.

Suggestions

Add explicit validation checkpoints and a validate→fix→retry loop to the Redis queue worker and multi-step pipeline, especially before submitting jobs and after failures, to lift workflow clarity above the batch-operation cap of 3.

Replace the inlined full state-machine and Redis-queue implementations with concise overviews that link to references/workflow-state-machine.md and references/redis-queue-integration.md, and surface the errors.md reference from the error-handling discussion.

Either define poll_task inline or link clearly to the job-monitoring skill so the multi-step pipeline example is executable end-to-end without an unresolved external symbol.

DimensionReasoningScore

Conciseness

The body is mostly lean executable code with brief one-line section intros and assumes Claude's competence (no explanations of Redis or state machines), but the inlined state-machine and Redis-queue implementations partially duplicate expanded versions in references/, which could be trimmed.

4 / 5

Actionability

Provides concrete, mostly copy-paste-ready Python for submit/callback, Redis worker, state machine, and pipeline, but poll_task is referenced as 'from job-monitoring skill' without an inline definition and the webhook section is illustrative rather than complete.

4 / 5

Workflow Clarity

Sequences are present (pipeline generate→extend→download, queue worker loop, state transitions) but the batch/queue operations lack validation checkpoints and any validate→fix→retry feedback loop, capping this dimension at 3 per the rubric.

3 / 5

Progressive Disclosure

The body has clear section structure but inlines full implementations that also exist expanded in five references/ files (e.g. workflow-state-machine.md, redis-queue-integration.md), and none of those bundle files are linked or signaled from the body, leaving navigation to detailed materials missing.

3 / 5

Total

14

/

20

Passed

Description

82%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.

A well-crafted description that clearly states what the skill does and when to invoke it, with concrete trigger phrases and a distinct Kling-AI niche. Specificity is solid but slightly pattern-level rather than enumerating discrete operations.

DimensionReasoningScore

Specificity

Names the domain ('async video generation workflows with Kling AI') and three concrete mechanisms ('queues, state machines, and event-driven patterns'), but the single generic verb 'Build' keeps it from listing several distinct concrete actions like the anchor-4 example.

3 / 5

Completeness

Explicitly answers both 'what' ('Build async video generation workflows ... using queues, state machines, and event-driven patterns') and 'when' ('Trigger with phrases like ...') with concrete trigger phrases, matching the anchor-5 example.

5 / 5

Trigger Term Quality

Provides four natural trigger phrases ('klingai async', 'kling ai workflow', 'klingai pipeline', 'async video generation') including klingai/kling ai variation, giving good keyword coverage though a few natural synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

A clear Kling-AI-specific niche with branded distinct triggers ('klingai async', 'kling ai workflow') yields minimal conflict risk with other skills.

5 / 5

Total

17

/

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.