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

83%

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

Quality

Content

92%

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

The content is a lean, highly actionable API reference with concrete endpoints, field paths, and error-handling decisions, plus a well-sequenced lip-sync workflow with a face-selection validation checkpoint. Its only weakness is progressive disclosure: everything lives in one monolithic file with no separate reference materials.

Suggestions

Extract the detailed protocol and parameter tables (Task Protocols, Omni references, the full error-code retry table) into a separate reference file and summarize them in SKILL.md, so the body acts as an overview with one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	The body is dense, bullet-driven, and assumes Claude's competence throughout, conveying only non-obvious API specifics (endpoints, field paths, status enums, error codes) with no padding or explanations of known concepts, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	It gives exact, copy-ready specifics — endpoints like '/v1/videos/avatar/image2video', field paths like 'data.task_id', status enums, and precise retry/no-retry error-code decisions — so for an instruction/protocol skill the guidance is fully actionable, matching the top anchor.	3 / 3
Workflow Clarity	The lip-sync flow is a clearly sequenced two-step process ('identify-face' then 'advanced-lip-sync') with an explicit validation checkpoint (stop and return the face list for confirmation when multiple faces are returned without an explicit face_id), and error handling supplies retry/abort decision logic, matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	No bundle/reference files exist and the ~190-line body is a single monolithic document; it is well-organized by section headers but all detailed protocol and parameter material is inline with no one-level-deep reference files to split it, matching 'some structure but content that should be separate is inline.'	2 / 3
	Total	11 / 12 Passed

Description

75%

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 third-person, explicit, and well-scoped with a clear 'Use before calling' trigger and strong distinctiveness from the fal.ai gateway path. It is weakest on action specificity and natural-language trigger variation, leaning on the abstract word 'guidance' and technical tool names.

Suggestions

Replace the abstract action 'guidance' with concrete verbs, e.g. 'Configure official Kling auth, build and poll task requests, and parse video/image/TTS/avatar results for OpenMontage providers.'

Add natural-language trigger variations users would say alongside the tool names, such as 'Kling official API', 'KLING_API_KEY', or 'official Kling video/image generation'.

Dimension	Reasoning	Score
Specificity	It names the domain ('Official Kling direct API guidance for OpenMontage providers') and lists five concrete tool identifiers, but the action itself is the abstract noun 'guidance' rather than a set of concrete performed actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states both what ('Official Kling direct API guidance for OpenMontage providers') and when ('Use before calling ...') with an explicit trigger clause, matching the 'clearly answers both what AND when' anchor; not below because the 'Use before calling' trigger is explicit.	3 / 3
Trigger Term Quality	The explicit trigger 'Use before calling' plus the five tool names gives relevant, on-niche triggers, but they are technical identifiers rather than natural-language variations a user would say, fitting 'some relevant keywords but missing common variations.'	2 / 3
Distinctiveness Conflict Risk	The 'Official Kling direct API' framing carves a clear niche distinct from the fal.ai Kling gateway, with tool-specific triggers unlikely to fire for the wrong skill, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 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
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: 0af32ce

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.