What makes Kling AI notable?

4.9K downloads. Trust evidence available

How should Kling AI be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Claim this agent

agentCLAWHUBUnverified

Kling AI

Official Kling AI Skill. Call Kling AI for video generation, image generation, subject management, and account quota inquiry. Use subcommand video / image / element / account by user intent. Use when the user mentions "Kling", "可灵", "文生视频", "图生视频", "参考视频", "视频编辑", "文生图", "图生图", "AI 画图", "视频生成", "图片生

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

4.9k

Updated

Oct 9, 2026

Version

2.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 4.9K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 4.9K downloadsadoption · observed Oct 9, 2026
Latest release: 2.0.0release · observed Sep 23, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s171hj9jje7gzmg9v3nvpjweph83hj68:klingai

Install using `clawhub skill install s171hj9jje7gzmg9v3nvpjweph83hj68:klingai` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/klingai-dev/klingai before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-klingai-dev-klingai/snapshot"

Documentation

CLAWHUB

149,597 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: klingai
version: "2.0.0"
description: Official Kling AI Skill. Call Kling AI for video generation, image generation, subject management, and account quota inquiry. Use subcommand video / image / element / account by user intent. Use when the user mentions "Kling", "可灵", "文生视频", "图生视频", "参考视频", "视频编辑", "文生图", "图生图", "AI 画图", "视频生成", "图片生成", "主体", "角色", "多镜头", "分镜", "多图", "两张图", "首尾帧", "组图", "余额", "资源包", "余量", "配额", "text-to-video", "image-to-video", "reference video", "video editing", "text-to-image", "multi-shot", "omni", "4K", "subject", "character", "element", "storyboard", "series", "quota", "balance".
metadata: {"openclaw":{"emoji":"🎬","requires":{"bins":["node"]},"primaryEnv":"KLING_API_KEY","homepage":"https://klingai.com/document-api/"}}
---

> **Language**: Respond in the user's language (detect from their message). Use it for explanations, confirmations, errors, and follow-ups. CLI output is bilingual (English / Chinese); present results in the user's language.

# Kling AI

Video generation, image generation, subject management, and (read-only) account resource/quota inquiry.
Invoke with subcommand `video` | `image` | `element` | `account` by user intent.
Generation tasks are billable; confirm with the user when intent is ambiguous before submitting.

## Invocation

From repository root:

```bash
node skills/klingai/scripts/kling.mjs <video|image|element|account> [options]
```

In examples below, `{baseDir}` means the skill directory (for example `skills/klingai`).

## Routing priority (OpenClaw)

- For Kling/可灵 requests with complex generation requirements, default to this skill (`node {baseDir}/scripts/kling.mjs ...`).
- Extension (video-generation tool) is allowed only for simple, unambiguous, low-parameter basics: text-to-video or single-image image-to-video.
- Do not use trial-and-error routing ("try extension first, then fallback to skill") unless the user explicitly asks for that flow.

## Intent routing (required)

Choose subcommand from user intent first. HTTP API path and default `model_name` are determined by **Route & model**.

| User intent | Subcommand |
| --- | --- |
| Video (t2v, i2v, multi-shot, Omni ref/edit clip via `feature`/`base`, subject-in-video, animation) | `video` |
| Image (text-to-image, image-to-image, 4K, series, AI drawing) | `image` |
| Subject / element (create, manage, list, presets, delete) | `element` |
| Account resources, packs, remaining quota / balance (read-only) | `account` (`--costs`, default) |
| Credential setup (bind/import) | `account` with `--bind-url` / `--import-env` / `--import-credentials` |

Selection rules:
- Video-related -> `video`
- For simple, unambiguous basic t2v or single-image i2v, extension may be used; for other video cases, prefer this skill.
- Image-only -> `image`
- Subject CRUD -> `element`
- Quota/balance/resource packs -> `account` (default `--costs`)
- Use existing subject in generation -> `video`/`image` + `--element_ids`
- Create subject first -> `elemen

README.md

# Kling AI

Video generation, image generation, and subject management.

- **Command**: `node scripts/kling.mjs <video|image|element|account> [options]`
- **Subcommands**:
  - `video`: video generation (text-to-video, image-to-video, omni-video, multi-shot)
  - `image`: image generation (text-to-image, image-to-image, omni-image, 4K/series)
  - `element`: subject CRUD
  - `account`: quota query and credential bind/import
- Choose by user intent; if ambiguous, ask the user first.

See [SKILL.md](SKILL.md) for full routing/parameters and [reference.md](reference.md) for endpoint mapping.
Official docs: [CN](https://app.klingai.com/cn/dev/document-api) / [Global](https://kling.ai/document-api/quickStart/productIntroduction/overview).

_meta.json

{
  "ownerId": "kn7bczybw3dwrwf452ghdtzty582nxj0",
  "slug": "klingai",
  "version": "2.0.0",
  "publishedAt": 1790165453034
}

reference.md

# Kling AI — API reference

Official source: [klingai.com/document-api/llms.txt](https://klingai.com/document-api/llms.txt)

| Subcommand | Endpoints |
| ---------- | --------- |
| `video`    | `POST /text-to-video/kling-3.0` (`kling-3.0-turbo` / `kling-2.6` / `kling-2.5-turbo`); `POST /image-to-video/kling-3.0` (same model suffixes); `POST /omni-video/kling-3.0-omni`; `POST /omni-video/kling-o1`; query `GET /tasks?task_ids=` |
| `image`    | `POST/GET /v1/images/generations`, `POST/GET /v1/images/omni-image` |
| `element`  | `POST/GET /v1/general/advanced-custom-elements`, `GET /v1/general/advanced-presets-elements`, `POST /v1/general/delete-advanced-elements` |
| `account`  | `GET /account/costs` (quota/resource packs); bind flow (no Bearer, bind base): `POST /console/api/auth/skill/init-sessions`, `POST /console/api/auth/skill/exchange` |

Auth and polling notes:

- Official: path-encoded models (all `video` submit paths above) are **new API** and require `Authorization: Bearer <API Key>`. See [authentication](https://klingai.com/document-api/api/get-started/authentication.md).
- Official: `/v1/...` image and element paths are **old API** (`model_name` in body); API Key Bearer works.
- Current script: process env `KLING_API_KEY` is sent as Bearer as-is. Else `api_key` in `~/.config/kling/.credentials` is sent as Bearer (**no JWT**). `account --bind` writes that API Key from exchange `ISSUED`. `KLING_TOKEN` is not recognized.
- Bind APIs (`/console/api/auth/skill/...`) are device-bind endpoints and do not use Bearer.
- New video submit returns `data.id` + `data.status` (`submitted` / `processing` / `succeeded` / `failed`). Poll `GET /tasks?task_ids=` and read `outputs[].url`.
- Image/element `/v1` submit still returns `task_id`; poll `GET {submit_path}/{task_id}` until `succeed`/`failed`, then read `task_result`.

Account mode mapping:

- `account --costs`: remote call to `GET /account/costs`
- `account --bind` / `account --bind-url`: remote bind calls (`init-sessions` + `exchange`)
- `account --import-env` / `--import-credentials` / `--configure`: local credential operations only (no business API submit)

## Model docs

Official pages (primary source):

- [Docs index](https://klingai.com/document-api/llms.txt)
- [Video capability map](https://klingai.com/document-api/guides/capability-map/video.md)
- [Image capability map](https://klingai.com/document-api/guides/capability-map/image.md)
- [Kling 3.0 T2V](https://klingai.com/document-api/api/video/3-0-omni/text-to-video.md)
- [Kling 3.0 I2V](https://klingai.com/document-api/api/video/3-0-omni/image-to-video.md)
- [Kling 3.0 Omni video](https://klingai.com/document-api/api/video/3-0-omni/video-omni.md)
- [Kling 3.0 Turbo T2V](https://klingai.com/document-api/api/video/3-0-turbo/text-to-video.md)
- [Kling 3.0 Turbo I2V](https://klingai.com/document-api/api/video/3-0-turbo/image-to-video.md)
- [Kling O1 video](https://klingai.com/document-api/api/video/o1/video-omni.md)
- [Kling 2.6 T2V](https://k

skill-card.md

## Description:

Calls Kling AI for video generation, image generation, subject management, and account quota inquiry.

This skill is ready for commercial/non-commercial use.

## Publisher:

[klingai-dev](https://clawhub.ai/user/klingai-dev)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to turn Kling AI generation, subject-management, and quota requests into validated CLI actions. It helps agents choose the correct video, image, element, or account workflow before submitting billable Kling API tasks.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Prompts and selected media are sent to Kling AI for generation and subject workflows.

Mitigation: Submit only prompts and media that are appropriate to share with Kling AI, and confirm ambiguous generation intent before starting billable tasks.

Risk: Kling API keys may be persisted under the Kling storage root when bind, import, or configure flows are used.

Mitigation: Prefer session-only KLING_API_KEY for non-persistent use, or protect and periodically review the local Kling credentials storage.

Risk: Subject deletion is explicit but not separately confirmed by the skill.

Mitigation: Review delete commands and subject identifiers carefully before execution.

Risk: Generated assets may be removed by the platform after a retention period.

Mitigation: Download and retain needed outputs locally after successful generation.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/klingai-dev/skills/klingai)
- [Kling AI API Documentation](https://klingai.com/document-api/)
- [Kling AI Docs Index](https://klingai.com/document-api/llms.txt)
- [Kling API Authentication](https://klingai.com/document-api/api/get-started/authentication.md)
- [Video Capability Map](https://klingai.com/document-api/guides/capability-map/video.md)
- [Image Capability Map](https://klingai.com/document-api/guides/capability-map/image.md)
- [Kling Elements API](https://klingai.com/document-api/api/video/3-0-omni/elements.md)
- [Account Usage API](https://klingai.com/document-api/api/assets/account-usage.md)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, files, guidance]

**Output Format:** [Markdown guidance with shell commands; CLI runs print task status and local output paths.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Generated media can be downloaded to the selected output directory; account and subject commands may print status, quota, or task identifiers.]

## Skill Version(s):

2.0.0 (source: frontmatter and server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/klingai-dev/skills/klingai",
      "sourceUrl": "https://clawhub.ai/klingai-dev/skills/klingai",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T04:37:23.518Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-klingai-dev-klingai/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-klingai-dev-klingai/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T04:37:23.518Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "4.9K downloads",
      "href": "https://clawhub.ai/klingai-dev/klingai",
      "sourceUrl": "https://clawhub.ai/klingai-dev/klingai",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T04:37:23.518Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "2.0.0",
      "href": "https://clawhub.ai/klingai-dev/klingai",
      "sourceUrl": "https://clawhub.ai/klingai-dev/klingai",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-09-23T12:10:53.034Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-klingai-dev-klingai/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-klingai-dev-klingai/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 2.0.0",
      "description": "Kling AI Skill 2.0.0 introduces support for the new official API and updates authentication. - Updated API authentication: now uses KLING_API_KEY (Bearer token) only; legacy KLING_TOKEN and AK/SK are no longer supported. - Revised canonical model names and routing: model lists and alias handling are changed to match the new API requirements. - Changed credential flows: device bind and import now write/read API Key, and never JWT/AK/SK. - Documentation updated throughout for new flags, stricter preflight checks, and clearer error/retry/reporting flows. - Removed legacy credential handling and references to outdated parameters. - Removed the skill-card.md file.",
      "href": "https://clawhub.ai/klingai-dev/klingai",
      "sourceUrl": "https://clawhub.ai/klingai-dev/klingai",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-09-23T12:10:53.034Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

About

Avoid when

Public facts

Install and run

Documentation

Extracted files

SKILL.md

README.md

_meta.json

reference.md

skill-card.md

Related agents

activepieces

cherry-studio

AionUi

CopilotKit

Machine-readable data