What makes Alibabacloud Starops Chat notable?

983 downloads. Trust evidence available

How should Alibabacloud Starops Chat be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Alibabacloud Starops Chat

Alibaba Cloud STAROps Agent AIOps diagnostic skill. Use this skill to help users diagnose service errors, analyze root causes, query workspace/service topolo...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

983

Updated

Oct 11, 2026

Version

0.0.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 983 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 983 downloadsadoption · observed Oct 11, 2026
Latest release: 0.0.2release · observed Jun 22, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 0.0.2release
alibabacloud-starops-chat 0.0.2 - Added support for reading configuration from `.starops/config.json`, `~/.starops/config.json`, or a custom path via `--config`/`STAROPS_AGENT_CONFIG` - Environment variables and config file values can now both be used for required identifiers (`employeeId`, `workspace`, `uid`) - Additional optional config keys and command-line overrides: endpoint, project, timeout, idleTimeout - Pre-flight check and documentation updated for config file usage; config key names must be exact (no aliases) - Improved flexibility in how STAROps Agent connection details are supplied—makes setup easier for users and teams - Removed outdated `skill-card.md` documentation file
Observed Jun 22, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s173swjet2yrebzqrp6hjkvmy583mxef:alibabacloud-starops-chat

Install using `clawhub skill install s173swjet2yrebzqrp6hjkvmy583mxef:alibabacloud-starops-chat` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/sdk-team/alibabacloud-starops-chat before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-sdk-team-alibabacloud-starops-chat/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

68,954 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: alibabacloud-starops-chat
description: |
  Alibaba Cloud STAROps Agent AIOps diagnostic skill. Use this skill to help users diagnose service errors, analyze root causes, query workspace/service topology, inspect APM metrics, and troubleshoot incidents through the STAROps Agent.
  Triggers: "排查根因", "根因分析", "服务报错", "服务异常", "APM 服务", "workspace 服务", "STAROps", "AIOps 诊断", "链路追踪", "告警分析".
---

# Alibaba Cloud STAROps Agent

Call the Alibaba Cloud STAROps Agent through STAROps OpenAPI and receive a streaming diagnostic answer.

## Scenario Description

Use this skill when the user wants to:

- Diagnose service errors or exceptions (root cause analysis)
- Query workspace topology, service lists, or service metrics
- Analyze APM traces, error rates, latency, or request volume
- Triage alerts or investigate incidents
- Ask questions about their STAROps workspace or services

## Configuration

The script reads STAROps connection values from environment variables and optional JSON config files. Environment variables and command-line flags override config file values.

Config files are loaded in this order:

1. User config: `~/.starops/config.json`
2. Project config: `./.starops/config.json` (overrides user config)
3. Explicit config: `--config <path>` or `STAROPS_AGENT_CONFIG` (overrides user/project config)

The three required values (`employeeId`, `workspace`, `uid`) may come from either environment variables or config files.

| Variable | Required | Description |
|----------|----------|-------------|
| `STAROPS_AGENT_EMPLOYEE` | Yes, unless config provides `employeeId` | Digital Employee ID in STAROps (from console → Digital Employee list → ID column) |
| `STAROPS_AGENT_WORKSPACE` | Yes, unless config provides `workspace` | Workspace identifier |
| `STAROPS_AGENT_UID` | Yes, unless config provides `uid` | Alibaba Cloud account UID that owns the workspace |
| `STAROPS_AGENT_ENDPOINT` | No | API endpoint (default: `starops.cn-beijing.aliyuncs.com`) |
| `STAROPS_AGENT_PROJECT` | No | Optional STAROps project variable forwarded with each request. Overridden by `--project` |
| `STAROPS_AGENT_TIMEOUT` | No | Default value for `--timeout` (CreateChat stream total timeout in seconds; default `1800`) |
| `STAROPS_AGENT_IDLE_TIMEOUT` | No | Default value for `--idle-timeout` (max seconds to wait for the next SSE event; default `60`) |
| `STAROPS_AGENT_CONFIG` | No | Path to an explicit JSON config file loaded after user/project config |

Minimal config file example:

```json
{
  "employeeId": "<your-digital-employee-id>",
  "workspace": "<your-workspace-name>",
  "uid": "<your-alibaba-cloud-account-uid>"
}
```

Optional fields:

```json
{
  "endpoint": "starops.cn-beijing.aliyuncs.com",
  "project": "optional-project",
  "timeout": 1800,
  "idleTimeout": 60
}
```

Config files use the exact key names shown above. Do not use alternate aliases such as `employee`, `digitalEmployeeId`, `workspaceName`, or `accountUid`.

**Pre-flight check — run this before

_meta.json

{
  "ownerId": "kn74p5w8ywv6prh40g0s82gmqh83nw54",
  "slug": "alibabacloud-starops-chat",
  "version": "0.0.2",
  "publishedAt": 1782119622449
}

references/acceptance-criteria.md

# Acceptance Criteria: alibabacloud-starops-chat

**Scenario**: STAROps Agent AIOps Diagnostic Skill
**Purpose**: Skill testing acceptance criteria

---

## Correct Script Invocation Patterns

### 1. Command Format — mandatory flags

#### CORRECT

```bash
python3 scripts/call_starops_agent.py \
  --question "Help me investigate the root cause of inventory service errors" \
  --pipe
```

#### INCORRECT — Missing `--pipe`

```bash
python3 scripts/call_starops_agent.py \
  --question "Help me investigate the root cause of inventory service errors"
```

**Why**: `--pipe` is mandatory. Without it, the script outputs in CLI mode, which lacks `=== STAROPS ANSWER BEGIN ===` delimiters and produces unstructured output that cannot be reliably parsed.

#### INCORRECT — Missing `--question`

```bash
python3 scripts/call_starops_agent.py --pipe
```

**Why**: `--question` is a required parameter. The script will exit with an argument error.

### 2. Thread Reuse — follow-up questions

#### CORRECT — Reusing thread ID for follow-up

```bash
# First call
python3 scripts/call_starops_agent.py \
  --question "How many APM services are in the current workspace?" --pipe
# Output: THREAD: thread-abc123-xyz

# Follow-up call with --thread
python3 scripts/call_starops_agent.py \
  --thread "thread-abc123-xyz" \
  --question "Which service has the highest error rate?" --pipe
```

#### INCORRECT — New thread for follow-up

```bash
# First call
python3 scripts/call_starops_agent.py \
  --question "How many APM services are in the current workspace?" --pipe

# Follow-up WITHOUT --thread — loses all prior context
python3 scripts/call_starops_agent.py \
  --question "Which service has the highest error rate?" --pipe
```

**Why**: Omitting `--thread` creates a new conversation. The STAROps Agent loses all prior investigation context and findings.

### 3. Dependency Installation

#### CORRECT — Install from scripts/requirements.txt

```bash
pip3 install -r scripts/requirements.txt
```

#### INCORRECT — Using `uv` or wrong path

```bash
uv run scripts/call_starops_agent.py --question "..." --pipe
pip3 install -r requirements.txt
```

**Why**: `uv` is not available in all environments. `requirements.txt` is located under `scripts/`, not the project root.

### 4. Environment Variables or Config File — required before invocation

#### CORRECT — All required variables set

```bash
export STAROPS_AGENT_EMPLOYEE="<your-digital-employee-id>"
export STAROPS_AGENT_WORKSPACE="rca-benchmark"
export STAROPS_AGENT_UID="<your-uid>"
```

#### CORRECT — Project config file supplies required values

```bash
mkdir -p .starops
cat > .starops/config.json <<'JSON'
{
  "employeeId": "<your-digital-employee-id>",
  "workspace": "rca-benchmark",
  "uid": "<your-uid>"
}
JSON

python3 scripts/call_starops_agent.py \
  --question "How many APM services are in the current workspace?" \
  --pipe
```

**Why**: The script loads `~/.starops/config.json` first, then `./.starops/config.json`, so project-level va

references/api-reference.md

# STAROps Agent API Reference

This skill uses STAROps OpenAPI version `2026-04-28` with ACS3-HMAC-SHA256 signing.

## Authentication

Requests are signed with Alibaba Cloud Credentials default-chain credentials. The Python script builds the ACS3 canonical request, signs it with `ACS3-HMAC-SHA256`, and sends HTTPS requests directly.

The default endpoint is:

```text
starops.cn-beijing.aliyuncs.com
```

Override with `STAROPS_AGENT_ENDPOINT` when a different endpoint is required.

## CreateThread

```http
POST /digitalEmployee/{employeeId}/thread
```

Body:

```json
{
  "title": "short question title",
  "idempotencyKey": "uuid",
  "variables": {
    "workspace": "workspace-name",
    "project": "optional-project"
  },
  "attributes": {
    "source": "alibabacloud-starops-chat"
  }
}
```

Expected response field:

```json
{
  "threadId": "thread-id"
}
```

## CreateChat

```http
POST /chat
```

Body:

```json
{
  "action": "create",
  "digitalEmployeeName": "employee-id",
  "threadId": "thread-id",
  "messages": [
    {
      "messageId": "uuid",
      "role": "user",
      "contents": [
        {
          "type": "text",
          "value": "user question"
        }
      ]
    }
  ],
  "variables": {
    "workspace": "workspace-name"
  }
}
```

The response is an SSE stream whose `data:` payloads contain STAROps `messages`. The script stops when the stream emits a `done` message or a `task_finished` event, and it always closes the streaming HTTP response before exiting.

## Output Modes

JSONL mode emits structured records:

```jsonl
{"type":"thread","thread_id":"thread-id","starops_url":"https://starops.console.aliyun.com/chat?threadId=thread-id&assistantId=apsara-ops"}
{"type":"message","role":"assistant","content":"answer"}
{"type":"done","thread_id":"thread-id","status":"completed"}
```

Pipe mode emits:

```text
THREAD: thread-id
STAROPS_URL: https://starops.console.aliyun.com/chat?threadId=thread-id&assistantId=apsara-ops
=== STAROPS ANSWER BEGIN ===
answer
=== STAROPS ANSWER END ===
```

The console URL uses the same digital employee ID as `assistantId`.

Pipe mode writes progress to stderr, including tool status lines such as:

```text
[tool:started] query_metrics
[tool:running] generate_diagnosis_report
[tool:done] query_metrics
```

`generate_diagnosis_report` text chunks are also mirrored to stderr for live visibility and included in the final stdout answer block.

references/ram-policies.md

# STAROps RAM Policy Notes

This skill does not use STAROps-specific AccessKey environment variables. It relies on Alibaba Cloud Credentials default-chain behavior, so credentials should be configured through standard Alibaba Cloud mechanisms.

## Required Access

Grant the caller the following STAROps actions:

| Action | Description |
|--------|-------------|
| `starops:CreateThread` | Create an investigation thread |
| `starops:CreateChat` | Send a message and stream the agent response |

Resource ARN format:

```
acs:starops::{uid}:digitalemployee/{employeeId}
```

### Example Custom Policy

```json
{
"Version": "1",
"Statement": [
{
"Effect": "Allow",
"Action": [
"starops:CreateThread",
"starops:CreateChat"
],
"Resource": "acs:starops::*:digitalemployee/*"
}
]
}
```

To restrict access to a specific account and digital employee, replace `*` with concrete values, e.g. `acs:starops::<your-uid>:digitalemployee/<employee-id>`.

## Recommended Credential Sources

Use one of the Alibaba Cloud Credentials default-chain sources:

- Standard Alibaba Cloud AccessKey environment credentials.
- Alibaba Cloud CLI profile or shared credentials profile.
- STS credentials.
- RAM role credentials.
- ECS instance metadata credentials, when available.

For local development environments where metadata lookup causes delays, set:

```bash
export ALIBABA_CLOUD_ECS_METADATA_DISABLED=true
```

## Security Boundaries

This skill creates STAROps investigation threads and streams STAROps Agent answers. It does not directly mutate ECS, OSS, RDS, SLS, or other cloud resources. Any operational action proposed by STAROps should still be reviewed according to the user's normal change-management process.

## Permission Failure Handling

When the script returns an HTTP 401 or 403 error indicating an authorization failure:

1. Stop immediately. Do **not** retry with different credentials or fabricate diagnostic results.
2. Report the exact error message to the user, including the `Action` and `Resource` from the error response.
3. Direct the user to check that their identity has the required STAROps permissions listed in the **Required Access** section above.
4. If using STS credentials, verify that the STS token has not expired and that the assumed role's policy includes `starops:CreateThread` and `starops:CreateChat`.
5. Wait for the user to confirm that permissions have been granted before retrying.

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular