Klingai Team Setup

What it does

When your agent uses it

• With phrases like klingai team
• Kling ai organization
• Klingai multi-user
• Shared klingai access

Example prompts

• “klingai team”
• “kling ai organization”
• “klingai multi-user”
• “/klingai-team-setup”

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. 1Configure least-privilege roles in a sandbox team and reject shared credentials or unapproved publishing destinations.
2. 2Test quota, approval, audit, policy, and revocation paths with synthetic briefs only; keep all generated assets draft-only.
3. 3Run one role canary at a time and halt on unexpected permission, budget, policy, or retention drift.
4. 4Promote roles only after owner approval, revoke temporary access, and delete test assets after the agreed window.

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

  Shell commands in SKILL.md call:

  • aws
  • gcloud
  • vault

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

• Network

  No URLs in SKILL.md. Its commands use aws and gcloud, which can reach the network depending on how they are called.

  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 Team Setup loads about 1.7k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 291 words of instructions outside code blocks.

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

~56

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

~1.7k

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

~4.5k

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

• NoteMentions a .env fileSKILL.md:40

  # .env.development

• NoteMentions a .env fileSKILL.md:44

  # .env.production

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). 291 words, ~1,718 tokens.

name

klingai-team-setup

description

Configure Kling AI for teams with per-project API keys, usage quotas, and role-based access. Trigger with phrases like 'klingai team', 'kling ai organization', 'klingai multi-user', 'shared klingai access'.

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, teams, access-control

# .env.development
KLING_ACCESS_KEY="ak_dev_..."
KLING_SECRET_KEY="sk_dev_..."

# .env.production
KLING_ACCESS_KEY="ak_prod_..."
KLING_SECRET_KEY="sk_prod_..."

from dataclasses import dataclass
from typing import Optional

@dataclass
class TeamMember:
    name: str
    email: str
    role: str  # admin, editor, viewer
    daily_credit_limit: int
    allowed_models: list[str]

@dataclass
class TeamConfig:
    name: str
    members: list[TeamMember]
    total_daily_limit: int = 1000
    default_model: str = "kling-v2-master"
    default_mode: str = "standard"

    def get_member(self, email: str) -> Optional[TeamMember]:
        return next((m for m in self.members if m.email == email), None)

# Example team configuration
team = TeamConfig(
    name="marketing",
    total_daily_limit=5000,
    members=[
        TeamMember("Alice", "alice@co.com", "admin", 2000,
                   ["kling-v2-6", "kling-v2-master", "kling-v2-5-turbo"]),
        TeamMember("Bob", "bob@co.com", "editor", 500,
                   ["kling-v2-master", "kling-v2-5-turbo"]),
        TeamMember("Carol", "carol@co.com", "viewer", 100,
                   ["kling-v2-5-turbo"]),
    ],
)

import time
from collections import defaultdict

class TeamQuotaManager:
    """Enforce per-member and team-wide credit limits."""

    def __init__(self, config: TeamConfig):
        self.config = config
        self._usage = defaultdict(int)  # email -> credits used today
        self._reset_time = time.time()

    def _check_reset(self):
        if time.time() - self._reset_time > 86400:
            self._usage.clear()
            self._reset_time = time.time()

    def authorize(self, email: str, credits_needed: int, model: str) -> bool:
        self._check_reset()
        member = self.config.get_member(email)
        if not member:
            raise PermissionError(f"Unknown user: {email}")

        if model not in member.allowed_models:
            raise PermissionError(f"{email} not authorized for {model}")

        if self._usage[email] + credits_needed > member.daily_credit_limit:
            raise RuntimeError(f"{email} exceeds daily limit "
                             f"({self._usage[email]} + {credits_needed} > {member.daily_credit_limit})")

        team_total = sum(self._usage.values()) + credits_needed
        if team_total > self.config.total_daily_limit:
            raise RuntimeError(f"Team daily limit exceeded ({team_total} > {self.config.total_daily_limit})")

        return True

    def record_usage(self, email: str, credits: int):
        self._usage[email] += credits

    def usage_report(self) -> dict:
        return {
            "team_total": sum(self._usage.values()),
            "team_limit": self.config.total_daily_limit,
            "by_member": dict(self._usage),
        }

# Load from AWS Secrets Manager
import boto3
import json

def get_kling_credentials(secret_name="kling/prod"):
    client = boto3.client("secretsmanager")
    secret = client.get_secret_value(SecretId=secret_name)
    creds = json.loads(secret["SecretString"])
    return creds["access_key"], creds["secret_key"]

class TeamKlingClient:
    """Kling client with team-level access control."""

    def __init__(self, base_client, quota_manager: TeamQuotaManager):
        self.client = base_client
        self.quotas = quota_manager

    def text_to_video(self, email: str, prompt: str, **kwargs):
        model = kwargs.get("model", "kling-v2-master")
        credits = 10 if kwargs.get("mode") != "professional" else 35
        self.quotas.authorize(email, credits, model)

        result = self.client.text_to_video(prompt, **kwargs)
        self.quotas.record_usage(email, credits)
        return result

© 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-team-setup of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/api-key-wrapper-with-team-context.md
• references/errors.md
• references/example-team-config.md
• references/examples.md
• references/team-configuration.md

Open the folder on GitHubat commit cfae287