Kling

What it does

When your agent uses it

• Kling text to video
• Tasks that involve AI video generation

Example prompts

• “/kling”

Requirements

• Python 3

Workflow steps

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

1. 1Kling uses prepaid resource packs. Confirm with Michael before every text2video, image2video, extend, and lip-sync; failed tasks are…
2. 2Generated asset URLs are short-lived. Download immediately; never store the URL as the artifact.
3. 3JWT minting is handled entirely inside bin/kling.py. Never mint or print tokens elsewhere, and never log the secret.
4. 4Model IDs move through v2.6/3.0 lineage. Confirm the current model id in Kling's docs before pinning one.
5. 5Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/kling.py). Do not print, log, or transmit the key pair.

What it can do on your machine

Read from SKILL.md and the folder at commit d6dc5d8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python), which the agent can run.

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

• Network

  No URLs in SKILL.md.

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

• Credentials

  Names no API keys, tokens, secrets or passwords.

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

Context cost

Kling loads about 812 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 292 words of instructions outside code blocks.

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

~49

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

~812

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 Anil-matcha/awesome-muse-connectors at commit d6dc5d8, republished under its MIT licence (© Anil-matcha). 292 words, ~812 tokens.

name

kling

description

Kling AI video generation with client-side JWT auth: text-to-video, image-to-video, status polling, clip extend, lip-sync. Trigger phrases: kling, kling video, klingai, kling text to video.

metadata.includeInPrompt

true

tagline

Kling AI video generation with client-side JWT auth: text-to-video, image-to-video, status polling, clip extend, lip-sync.

catalog_auth

access key + secret key pair via the secure credential flow

catalog_hosts

api.klingai.com

bin/kling.py auth                                                         # mint a JWT and verify it is accepted (free)
bin/kling.py text2video --prompt "a samurai in neon rain" --json '{"duration": "10"}'
bin/kling.py image2video --image-url https://.../frame.png --prompt "slow zoom out"
bin/kling.py status --task-id <task_id>                                   # poll until succeed/failed
bin/kling.py extend --task-id <task_id> --json '{"prompt": "continue forward"}'   # extend a finished clip
bin/kling.py lip-sync --json '{"voice_id": "...", "video": "..."}'       # lip-sync a video

© Anil-matcha, 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 1 other file in connectors/kling of Anil-matcha/awesome-muse-connectors.

• SKILL.md
• bin/kling.py

Open the folder on GitHubat commit d6dc5d8