Klingai Video Extension

What it does

When your agent uses it

• Creating longer videos from shorter clips
• Building sequences
• With phrases like klingai extend video
• Kling ai video continuation

Example prompts

• “klingai extend video”
• “kling ai video continuation”
• “klingai longer video”
• “/klingai-video-extension”

Requirements

• Python 3
• A credential in KLING_ACCESS_KEY
• A credential in KLING_SECRET_KEY
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(npm:*), Grep

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Confirm source ownership, completion state, and approved continuity brief before creating an extension; do not use private, unlicensed, or…
2. 2Submit one watermarked draft canary within the approved duration and credit cap, then verify policy, rights, quality, and destination…
3. 3Halt on continuity, policy, rights, or budget drift and delete the extension task instead of publishing it.
4. 4Promote only after owner approval; retain a redacted receipt and remove temporary assets at the agreed retention boundary.

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash(npm:*)
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.klingai.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • KLING_ACCESS_KEY
  • KLING_SECRET_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Klingai Video Extension loads about 1.8k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 69 tokens; SKILL.md has 319 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~69

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 319 words, ~1,791 tokens.

name

klingai-video-extension

description

Extend video duration using Kling AI continuation. Use when creating longer videos from shorter clips or building sequences. Trigger with phrases like 'klingai extend video', 'kling ai video continuation', 'klingai longer video', 'extend klingai clip'.

allowed-tools

Read, Write, Edit, Bash(npm:*), Grep

compatibility

Designed for Claude Code

version

1.18.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, kling-ai, video-extension, continuation

import jwt, time, os, requests

BASE = "https://api.klingai.com/v1"

def get_headers():
    ak, sk = os.environ["KLING_ACCESS_KEY"], os.environ["KLING_SECRET_KEY"]
    token = jwt.encode(
        {"iss": ak, "exp": int(time.time()) + 1800, "nbf": int(time.time()) - 5},
        sk, algorithm="HS256", headers={"alg": "HS256", "typ": "JWT"}
    )
    return {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}

# Step 1: Generate the initial 5s video
initial = requests.post(f"{BASE}/videos/text2video", headers=get_headers(), json={
    "model_name": "kling-v2-master",
    "prompt": "A rocket launching from a desert landscape, cinematic",
    "duration": "5",
    "mode": "standard",
}).json()
initial_task_id = initial["data"]["task_id"]

# Wait for completion...
# (poll until task_status == "succeed")

# Step 2: Extend by 5 more seconds
extension = requests.post(f"{BASE}/videos/video-extend", headers=get_headers(), json={
    "task_id": initial_task_id,
    "prompt": "The rocket ascends through clouds into the stratosphere",
    "duration": "5",
    "mode": "standard",
}).json()
ext_task_id = extension["data"]["task_id"]

# Step 3: Poll extension task
while True:
    time.sleep(15)
    result = requests.get(
        f"{BASE}/videos/video-extend/{ext_task_id}", headers=get_headers()
    ).json()
    if result["data"]["task_status"] == "succeed":
        extended_url = result["data"]["task_result"]["videos"][0]["url"]
        print(f"Extended video: {extended_url}")
        break
    elif result["data"]["task_status"] == "failed":
        print(f"Failed: {result['data']['task_status_msg']}")
        break

def chain_extensions(initial_task_id: str, prompts: list[str],
                     duration: str = "5", mode: str = "standard") -> list[str]:
    """Chain multiple extensions to build a longer video."""
    current_task_id = initial_task_id
    video_urls = []

    for i, prompt in enumerate(prompts):
        print(f"Extension {i + 1}/{len(prompts)}: submitting...")

        # Submit extension
        r = requests.post(f"{BASE}/videos/video-extend", headers=get_headers(), json={
            "task_id": current_task_id,
            "prompt": prompt,
            "duration": duration,
            "mode": mode,
        }).json()
        ext_task_id = r["data"]["task_id"]

        # Poll for completion
        while True:
            time.sleep(15)
            result = requests.get(
                f"{BASE}/videos/video-extend/{ext_task_id}", headers=get_headers()
            ).json()
            status = result["data"]["task_status"]

            if status == "succeed":
                url = result["data"]["task_result"]["videos"][0]["url"]
                video_urls.append(url)
                current_task_id = ext_task_id  # next extension chains from this
                print(f"Extension {i + 1} complete: {url}")
                break
            elif status == "failed":
                raise RuntimeError(f"Extension {i + 1} failed: {result['data']['task_status_msg']}")

    return video_urls

# Generate initial 5s
initial_r = requests.post(f"{BASE}/videos/text2video", headers=get_headers(), json={
    "model_name": "kling-v2-master",
    "prompt": "Morning sunrise over a mountain lake, mist rising",
    "duration": "5",
    "mode": "standard",
}).json()
initial_id = initial_r["data"]["task_id"]
# ... poll until complete ...

# Chain 3 more extensions = 5 + 5 + 5 + 5 = 20 seconds total
extensions = chain_extensions(initial_id, [
    "Sun rises higher, birds begin flying across the lake",
    "A deer approaches the water's edge to drink",
    "Wide shot pulling back to reveal the full mountain range",
])

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/.curated/klingai-video-extension of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/errors.md
• references/examples.md
• references/seamless-loop-creation.md
• references/video-concatenation.md
• references/video-extension-implementation.md

Open the folder on GitHubat commit cfae287