Alicloud Ai Pai Aiworkspace
- 264 installs
- 396 repo stars
- Updated July 18, 2026
- cinience/alicloud-skills
alicloud-ai-pai-aiworkspace is an Alibaba Cloud agent skill that integrates PAI AI Workspace notebooks, model endpoints, and experiment tracking for developers building managed ML and agent inference backends.
About
alicloud-ai-pai-aiworkspace is a cinience/alicloud-skills pack entry for managing Alibaba Cloud Platform for AI (PAI) AI Workspace through OpenAPI and SDKs. It supports listing and configuring workspace resources, creating or updating notebook environments, querying model endpoint status, and running troubleshooting workflows for managed inference inside ML and agent backends. Developers reach for it when wiring experiment tracking, notebook provisioning, or deployment endpoints into automated agent pipelines on Alibaba rather than using the PAI console manually. Like sibling alicloud skills, it follows metadata-first API discovery, resolves credentials from ALICLOUD environment variables or shared credential files, and writes reproducible output artifacts. Install with npx skills add cinience/alicloud-skills --skill alicloud-ai-pai-aiworkspace when building data science platforms or agent services on Alibaba PAI infrastructure.
- PAI AI Workspace provisioning flows
- Model registry and endpoint deployment
- Notebook and experiment workspace access
- IAM and regional configuration guidance
- Managed inference integration patterns
Alicloud Ai Pai Aiworkspace by the numbers
- 264 all-time installs (skills.sh)
- Ranked #2,456 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-ai-pai-aiworkspaceAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 264 |
|---|---|
| repo stars | ★ 396 |
| Last updated | July 18, 2026 |
| Repository | cinience/alicloud-skills ↗ |
How do you integrate Alibaba PAI AI Workspace APIs?
Integrate Alibaba PAI AI Workspace for notebooks, model endpoints, experiment tracking, and managed inference inside ML and agent backends.
Who is it for?
ML engineers and backend developers automating Alibaba PAI AI Workspace notebooks, experiments, and inference endpoints inside agent or data platforms.
Skip if: Teams training models entirely on local GPUs without Alibaba PAI or any cloud ML workspace dependency.
When should I use this skill?
The developer asks to provision PAI notebooks, deploy model endpoints, track experiments, or troubleshoot AI Workspace API workflows on Alibaba Cloud.
What you get
Configured PAI workspace resources, model endpoint status reports, and OpenAPI execution evidence for ML pipelines.
- PAI workspace configurations
- Model endpoint status reports
- OpenAPI execution evidence files
Files
Category: service
PAI AIWorkspace
Use Alibaba Cloud OpenAPI (RPC) with official SDKs or OpenAPI Explorer to manage resources for Platform for Artificial Intelligence PAI - AIWorkspace.
Workflow
1) Confirm region, resource identifiers, and desired action. 2) Discover API list and required parameters (see references). 3) Call API with SDK or OpenAPI Explorer. 4) Verify results with describe/list APIs.
AccessKey priority (must follow)
1) Environment variables: ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET / ALICLOUD_REGION_ID Region policy: ALICLOUD_REGION_ID is an optional default. If unset, decide the most reasonable region for the task; if unclear, ask the user. 2) Shared config file: ~/.alibabacloud/credentials
API discovery
- Product code:
AIWorkSpace - Default API version:
2021-02-04 - Use OpenAPI metadata endpoints to list APIs and get schemas (see references).
High-frequency operation patterns
1) Inventory/list: prefer List* / Describe* APIs to get current resources. 2) Change/configure: prefer Create* / Update* / Modify* / Set* APIs for mutations. 3) Status/troubleshoot: prefer Get* / Query* / Describe*Status APIs for diagnosis.
Minimal executable quickstart
Use metadata-first discovery before calling business APIs:
python scripts/list_openapi_meta_apis.pyOptional overrides:
python scripts/list_openapi_meta_apis.py --product-code <ProductCode> --version <Version>The script writes API inventory artifacts under the skill output directory.
Output policy
If you need to save responses or generated artifacts, write them under: output/alicloud-ai-pai-aiworkspace/
Validation
mkdir -p output/alicloud-ai-pai-aiworkspace
for f in skills/ai/platform/alicloud-ai-pai-aiworkspace/scripts/*.py; do
python3 -m py_compile "$f"
done
echo "py_compile_ok" > output/alicloud-ai-pai-aiworkspace/validate.txtPass criteria: command exits 0 and output/alicloud-ai-pai-aiworkspace/validate.txt is generated.
Output And Evidence
- Save artifacts, command outputs, and API response summaries under
output/alicloud-ai-pai-aiworkspace/. - Include key parameters (region/resource id/time range) in evidence files for reproducibility.
Prerequisites
- Configure least-privilege Alibaba Cloud credentials before execution.
- Prefer environment variables:
ALICLOUD_ACCESS_KEY_ID,ALICLOUD_ACCESS_KEY_SECRET, optionalALICLOUD_REGION_ID. - If region is unclear, ask the user before running mutating operations.
References
- Sources:
references/sources.md
interface:
display_name: "Alibaba Cloud AI PAI Aiworkspace"
short_description: "PAI AIWorkspace management workflows"
default_prompt: "Use $alicloud-ai-pai-aiworkspace to complete this ai/platform task on Alibaba Cloud."
Sources
- OpenAPI product page:
https://api.aliyun.com/product/AIWorkSpace - API list (metadata):
https://api.aliyun.com/meta/v1/products/AIWorkSpace/versions/2021-02-04/api-docs.json - API definition (single API):
https://api.aliyun.com/meta/v1/products/AIWorkSpace/versions/2021-02-04/apis/{ApiName}/api.json
#!/usr/bin/env python3
"""Fetch OpenAPI metadata API list for one product/version and save to output/.
Env:
- OPENAPI_META_TIMEOUT (seconds, default: 20)
"""
from __future__ import annotations
import argparse
import json
import os
import pathlib
import urllib.request
DEFAULT_PRODUCT_CODE = "AIWorkSpace"
DEFAULT_VERSION = "2021-02-04"
OUTPUT_DIR = pathlib.Path("output/alicloud-ai-pai-aiworkspace")
def fetch_json(url: str, timeout: int) -> dict:
req = urllib.request.Request(url, headers={"User-Agent": "codex-skill"})
with urllib.request.urlopen(req, timeout=timeout) as resp:
return json.loads(resp.read().decode("utf-8"))
def main() -> None:
parser = argparse.ArgumentParser()
parser.add_argument("--product-code", default=DEFAULT_PRODUCT_CODE)
parser.add_argument("--version", default=DEFAULT_VERSION)
parser.add_argument("--output-dir", default=str(OUTPUT_DIR))
args = parser.parse_args()
timeout = int(os.getenv("OPENAPI_META_TIMEOUT", "20"))
output_dir = pathlib.Path(args.output_dir)
output_dir.mkdir(parents=True, exist_ok=True)
url = (
f"https://api.aliyun.com/meta/v1/products/{args.product_code}"
f"/versions/{args.version}/api-docs.json"
)
payload = fetch_json(url, timeout)
raw_apis = payload.get("apis", {})
if isinstance(raw_apis, dict):
api_names = sorted(raw_apis.keys())
elif isinstance(raw_apis, list):
names = []
for item in raw_apis:
if isinstance(item, dict):
name = item.get("name") or item.get("apiName")
if name:
names.append(name)
elif isinstance(item, str):
names.append(item)
api_names = sorted(set(names))
else:
api_names = []
json_file = output_dir / f"{args.product_code}_{args.version}_api_docs.json"
md_file = output_dir / f"{args.product_code}_{args.version}_api_list.md"
json_file.write_text(json.dumps(payload, ensure_ascii=False, indent=2), encoding="utf-8")
md_lines = [
f"# {args.product_code} {args.version} API List",
"",
f"- Source: {url}",
f"- API count: {len(api_names)}",
"",
]
md_lines.extend([f"- `{name}`" for name in api_names])
md_file.write_text("\n".join(md_lines) + "\n", encoding="utf-8")
print(f"Saved: {json_file}")
print(f"Saved: {md_file}")
if __name__ == "__main__":
main()
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Use this for PAI AI Workspace lifecycle automation; use generic ML training skills when models never touch Alibaba managed workspaces.
FAQ
What PAI resources does alicloud-ai-pai-aiworkspace manage?
alicloud-ai-pai-aiworkspace manages Alibaba PAI AI Workspace resources including notebooks, model endpoints, experiment tracking, and managed inference workflows through OpenAPI list, create, update, and status query operations.
How do you install alicloud-ai-pai-aiworkspace?
Run npx skills add cinience/alicloud-skills --skill alicloud-ai-pai-aiworkspace, configure ALICLOUD_ACCESS_KEY_ID and ALICLOUD_ACCESS_KEY_SECRET, then invoke the skill when automating PAI workspace or endpoint tasks from your agent client.