kling-official

Official Kling direct API guidance for OpenMontage providers. Use before calling `kling_official_video`, `kling_official_image`, `kling_tts`, `kling_avatar`, or `kling_lip_sync`.

Quality

70%

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 ./.agents/skills/kling-official/SKILL.md

Quality

Content

58%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 highly actionable and well-sequenced with strong validation checkpoints and concrete field-level guidance, but it is dense and inlines a large amount of API reference material into SKILL.md rather than using progressive disclosure, and it references internal helper modules that are not present in the bundle.

Suggestions

Move the detailed per-tool parameter and endpoint reference (e.g. Avatar, Lip Sync, Audio/Video Effects, Elements/Account helpers) into separate reference files under references/ and keep SKILL.md as a concise overview with clear one-level-deep pointers.

Either include the referenced helper modules (tools/_kling/media.py, elements.py, account.py) in a scripts/ bundle or rephrase the guidance so it does not depend on files the reader cannot open.

Add at least one complete copy-paste-ready request example (headers + body + poll) for the most common path (e.g. Classic text-to-video) to lift actionability from strong to fully executable.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's intelligence about the Kling protocol, but it is noticeably long with many inline sections (Auth, Task Protocols, Omni References, multiple parameter blocks) that pack a large amount of reference material into SKILL.md rather than splitting it out; mostly efficient but could be tightened by offloading detail.	3 / 5
Actionability	Provides concrete, executable guidance throughout — specific endpoint paths ('/v1/videos/avatar/image2video'), exact request/response field names ('data.task_id', 'data[0].outputs[]'), and concrete parameter lists ('voice_id', 'voice_language', 'voice_speed'); minor gaps in that no full copy-paste request example is given, but field-level specifics are highly actionable.	4 / 5
Workflow Clarity	Multi-step processes are clearly sequenced (e.g. lip sync: identify-face then advanced-lip-sync) with validation/confirmation checkpoints ('stop and return the face list for confirmation unless auto_select_face=True') and explicit error-handling decision rules by code; minor gap is that no explicit re-validate feedback loop is spelled out for the few batch/destructive paths.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) yet the body references internal helper paths ('tools/_kling/media.py', 'tools/_kling/elements.py', 'tools/_kling/account.py') that are not provided as part of the skill, and ~200 lines of API reference are inlined into SKILL.md with section headers rather than split into separate reference files — structure exists but content that should be separate is inlined and references are not backed by real files.	2 / 5
	Total	13 / 20 Passed

Description

81%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 specific, well-triggered, and explicitly distinguishes itself from the related fal.ai Kling path, with clear 'what' and 'when' guidance tied to concrete tool names. Minor room for improvement in enumerating per-tool actions and adding natural synonym coverage.

Suggestions

Consider briefly enumerating the per-tool action (e.g. video/image generation, TTS, avatar, lip sync) so the 'what' is comprehensive rather than relying on tool names alone.

Add a couple of natural-language trigger phrases a user might say beyond the tool identifiers (e.g. 'Kling video generation', 'official Kling TTS').

Dimension	Reasoning	Score
Specificity	Lists several specific concrete actions across five distinct tools ('kling_official_video', 'kling_official_image', 'kling_tts', 'kling_avatar', 'kling_lip_sync') with a clear purpose ('Official Kling direct API guidance for OpenMontage providers'); minor gap in that the actions per tool are not individually enumerated.	4 / 5
Completeness	Clearly states both what it does ('Official Kling direct API guidance for OpenMontage providers') and when to use it ('Use before calling' the listed tools); the 'when' is explicit and tied to concrete tool calls rather than vague contexts.	4 / 5
Trigger Term Quality	Includes natural trigger terms users would say ('Kling', 'OpenMontage') plus the explicit tool identifiers a user would reference ('kling_official_video', 'kling_official_image', 'kling_tts', 'kling_avatar', 'kling_lip_sync'); a few natural synonyms are missing but coverage is good.	4 / 5
Distinctiveness Conflict Risk	Names a very specific niche (official Kling direct API for OpenMontage providers) with distinct tool-name triggers and an explicit anti-conflict signal ('This is not the fal.ai Kling gateway'), making it unlikely to trigger for the wrong skill.	5 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/kling-official/SKILL.md
Commit: 08e2151

Reviewed: 6 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.