google-agents-cli-scaffold
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
reapi
Call public reAPI APIs to submit image/video generation tasks, poll task status, and return generated media URLs. Requires REAPI_API_KEY or REAPI_KEY from https://reapi.ai.
Full skill instructions
Use reAPI's public API to submit asynchronous image/video generation tasks and poll for generated media URLs.
Default API base URL: https://reapi.ai.
This skill is safe to publish. Keep it that way:
Required:
REAPI_API_KEY or REAPI_KEY: reAPI bearer token.Get an API key:
https://reapi.ai.export REAPI_API_KEY="rk_live_xxx"
Optional:
REAPI_BASE_URL: override the API base URL. Defaults to https://reapi.ai.If the API key is missing, ask the user to configure it. Do not ask them to paste
the key into chat unless there is no safer option. Direct them to
https://reapi.ai to create the key.
Use the bundled script from this skill directory.
Check configuration:
python3 scripts/reapi.py config
List bundled model examples:
python3 scripts/reapi.py models
Print an example payload:
python3 scripts/reapi.py example gpt-image-2
Print a ready-to-run command for a model:
python3 scripts/reapi.py example gpt-image-2 --with-command
Submit an image task and wait for completion:
python3 scripts/reapi.py submit images \
--wait \
--json '{"model":"gpt-image-2","prompt":"a cute red panda eating bamboo","size":"1:1"}'
Submit a video task and wait for completion:
python3 scripts/reapi.py submit videos \
--wait \
--json '{"model":"doubao-seedance-2.0","prompt":"a cinematic red panda walking through bamboo","duration":5,"resolution":"720p"}'
Poll an existing task:
python3 scripts/reapi.py wait task_xxx
Get a task once:
python3 scripts/reapi.py get task_xxx
Submit by model id and let the CLI pick the endpoint from the bundled catalog:
python3 scripts/reapi.py submit-model gpt-image-2 \
--wait \
--json '{"prompt":"a cute red panda","size":"1:1"}'
Use only canonical model values documented by reAPI. Do not invent or rely on
community aliases when submitting requests or reporting results. If the user
gives an undocumented nickname, ask for the exact reAPI model ID or list the
documented candidates from references/models.json.
/api/v1/images/generations or /api/v1/videos/generations.id from the response.GET /api/v1/tasks/{id} every 2-3 seconds.status: "completed", return URLs from output.image_urls,
or output.video_urls.status: "failed", report error.code and error.message.Polling does not consume credits. Submission requests consume credits based on the selected model and parameters.
curl https://reapi.ai/api/v1/images/generations \
-H "Authorization: Bearer $REAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-image-2","prompt":"a cute red panda","size":"1:1"}'
curl https://reapi.ai/api/v1/tasks/task_xxx \
-H "Authorization: Bearer $REAPI_API_KEY"
reAPI errors use:
{
"error": {
"code": 20002,
"message": "Missing required parameter",
"request_id": "req_xxx"
}
}
Handling rules:
400, 401, 402, 404: fix the request or credentials.429: retry after the Retry-After header.500, 502, 503, 504: for polling, retry with backoff when appropriate.
For submission, avoid blind retries unless the user accepts the possibility of
creating a second task.status: "failed" is a task failure; report the
task's error.code and error.message.references/API.md: public endpoint, task, auth, and response notes.references/MODELS.md: bundled model examples and common parameters.references/models.json: machine-readable examples used by the CLI.https://reapi.ai/docsProject scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.
Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.
Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.
Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.
Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.
Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Opus.ai: Revolutionize Your Web Experience
Build a no-code AI app in minutes.
An IDE for code migration from legacy to modern frameworks through coding agents.
Automate CGI animation in live-action scenes
Branded artistic QR-code concepts
Launch a website in seconds with AI.
Streamline Your Coding Experience with AI Code Helper
Convert any screenshot or design to clean code.