CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

An unusually disciplined policy/reference body: every section carries provider-specific facts Claude could not guess (field names, status enums, error-code retry rules, cost governance), with explicit stop-and-ask guardrails for risky substitutions. The main gaps are the missing video creation endpoint paths, the implicit (never enumerated) polling workflow, and no progressive-disclosure split despite the file's length.

Suggestions

Add the actual video creation endpoint paths (classic, turbo, and omni text/image-to-video), which are conspicuously absent while every other capability lists its paths.

Lay out the create → poll → fetch-result loop once as an ordered sequence per api_family, instead of leaving the reader to assemble it from the Create ID path, Poll path, and Result path fields.

Move the error-code retry table and the per-capability parameter detail into a single one-level-deep reference file to cut SKILL.md length and improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense and imperative throughout — JSON paths, statuses, parameter constraints, and error codes with no filler and no explanation of concepts Claude already knows. Minor repetition keeps it below anchor 5: the 'must not be silently uploaded through fal.ai' guardrail appears in three sections (Omni References, Video Parameters, Lip Sync Parameters) and the provider split is restated in several places.

4 / 5

Actionability

Highly concrete: exact endpoints (`/v1/videos/avatar/image2video`, `/v1/videos/identify-face`, `/v1/audio/text-to-audio`), JSON paths (`data.task_result.videos[]`, `data[0].outputs[]`), status enums, parameter names, and a numeric error-code retry policy. Not anchor 5 because the video-generation endpoint paths themselves are never stated (unlike image/avatar/lip-sync/audio) and there are no example request payloads or code snippets.

4 / 5

Workflow Clarity

Lip sync has an explicit numbered two-step sequence; the Task Protocols section supplies the create-ID → poll-path → result-path pieces; error handling provides a retry/no-retry feedback loop; callback URLs get explicit validation rules. Below anchor 5 because the core create→poll→fetch-result loop is never laid out as an ordered sequence with checkpoints — the reader assembles it from scattered fields.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so everything lives in one well-sectioned SKILL.md covering auth, task protocols, per-capability parameters, error handling, and cost governance — clear navigation, appropriate placement for a single-provider policy skill. Not anchor 5 because at ~200 lines the error-code table and per-capability parameter detail are natural candidates for a one-level-deep reference file, and the body's `tools/_kling/*.py` mentions point into the target repo rather than into a documented bundle.

4 / 5

Total

16

/

20

Passed

Description

83%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 strong description: it pairs a clearly scoped what with an explicit use-before-when trigger listing all five covered tools, and it distinguishes the official Kling path from the fal.ai gateway. Its main limitation is that "guidance" is generic as a capability statement and it lacks plain-language keyword variations beyond the exact tool identifiers.

Suggestions

Replace or augment the generic word 'guidance' with one or two concrete capability statements (e.g., 'Auth, task polling, and parameter rules for the official Kling API').

Add a few natural-language trigger phrases (Kling video generation, Kling TTS, Kling avatar) alongside the backticked tool names so users who don't type exact identifiers still match.

State the key distinction inline (e.g., 'official Kling API, not the fal.ai Kling gateway') so the description alone prevents wrong-skill triggering.

DimensionReasoningScore

Specificity

"Official Kling direct API guidance for OpenMontage providers" names the domain and scopes it with five concrete tool names (`kling_official_video`, `kling_official_image`, `kling_tts`, `kling_avatar`, `kling_lip_sync`), but the capability verb itself is generic ("guidance") — it never states what the skill covers (auth, task polling, parameter rules). Fits between anchor 2 ("actions are minimal or generic") and anchor 3 ("1-2 concrete actions"), noticeably above 2 because of the named tools, but not 5 since no concrete actions are enumerated.

4 / 5

Completeness

It explicitly answers both: what ("Official Kling direct API guidance for OpenMontage providers") and when ("Use before calling kling_official_video, kling_official_image, kling_tts, kling_avatar, or kling_lip_sync") with concrete trigger phrases. Matches anchor 5; the when-clause is fully explicit with named triggers, so the anchor-4 caveat ("'when' could be more explicit") does not apply.

5 / 5

Trigger Term Quality

Trigger terms are the exact tool names plus "Official Kling", "direct API", and "OpenMontage providers" — precise and natural for anyone working in this codebase. Missing common plain-language variations users might say ("Kling video generation", "Kling TTS", "Kling avatar" without the backticked identifier), so it is good-but-not-comprehensive coverage per anchor 4, not 5.

4 / 5

Distinctiveness Conflict Risk

"Official Kling direct API" draws a clear line against the fal.ai Kling gateway path, and the backticked tool names are unambiguous triggers with minimal conflict risk. Minor overlap remains with a hypothetical fal.ai-based `kling_video` skill since the bare word "Kling" alone would match both, keeping it at anchor 4 ("mostly distinct; minor overlap risk") rather than 5.

4 / 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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

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.