Aliyun Arms Query

What it does

When your agent uses it

• Querying distributed traces
• Application metrics in Alibaba Cloud ARMS (Application Real-Time Monitoring Service)
• Trace search by service/duration/tags
• Trace detail and method stack retrieval

Example prompts

• “/aliyun-arms-query”

Requirements

• Python 3
• A credential in ALIBABACLOUD_ACCESS_KEY_SECRET

Workflow steps

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

1. 1List traced apps with list_trace_apps.py to obtain PID.
2. 2Search traces with time range, service name, and optional filters via search_traces.py.
3. 3Get detail for a specific trace using its TraceID via get_trace_detail.py.
4. 4Inspect method stack for a slow or errored span via get_stack.py (requires TraceID, RpcID, PID).
5. 5Query aggregated metrics using PID, metric name, and desired measures/dimensions via query_metrics.py.

What it can do on your machine

Read from SKILL.md and the folder at commit 1818263. 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 6 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • python3

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

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.aliyun.com

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ALIBABACLOUD_ACCESS_KEY_ID
  • ALIBABACLOUD_ACCESS_KEY_SECRET

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

Context cost

Aliyun Arms Query loads about 1.6k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 375 words of instructions outside code blocks.

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

~71

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

~1.6k

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

~3.5k

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

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); the scripts in this folder are not scanned.

SKILL.md

The full file from cinience/alicloud-skills at commit 1818263, republished under its MIT licence (© cinience). 375 words, ~1,589 tokens.

name

aliyun-arms-query

description

Use when querying distributed traces or application metrics in Alibaba Cloud ARMS (Application Real-Time Monitoring Service). Use for trace search by service/duration/tags, trace detail and method stack retrieval, application listing, and performance metrics queries.

version

1.0.0

python3 -m venv .venv
. .venv/bin/activate
python -m pip install -U alibabacloud_arms20190808 alibabacloud_tea_openapi

import os, time
from alibabacloud_arms20190808.client import Client
from alibabacloud_arms20190808 import models
from alibabacloud_tea_openapi.models import Config

config = Config(
    access_key_id=os.environ["ALIBABACLOUD_ACCESS_KEY_ID"],
    access_key_secret=os.environ["ALIBABACLOUD_ACCESS_KEY_SECRET"],
    region_id=os.environ.get("ARMS_REGION_ID", "cn-hangzhou"),
)
config.endpoint = f'arms.{config.region_id}.aliyuncs.com'
client = Client(config)

end_ms = int(time.time() * 1000)
start_ms = end_ms - 15 * 60 * 1000

request = models.SearchTracesByPageRequest(
    region_id=config.region_id,
    start_time=start_ms,
    end_time=end_ms,
    service_name="my-app",
    min_duration=500,
    page_number=1,
    page_size=20,
)
response = client.search_traces_by_page(request)
for trace in response.body.page_bean.trace_infos:
    print(f"{trace.trace_id}  {trace.duration}ms  {trace.service_name}")

request = models.QueryMetricByPageRequest(
    region_id=config.region_id,
    metric="appstat.incall",
    start_time=start_ms,
    end_time=end_ms,
    interval_in_sec=60000,
    measures=["rt", "count", "error"],
    dimensions=["rpc"],
    filters=[models.QueryMetricByPageRequestFilters(key="pid", value="xxx@cn-hangzhou")],
    current_page=1,
    page_size=10,
)
response = client.query_metric_by_page(request)
for item in response.body.data.items:
    print(item)

python skills/observability/arms/aliyun-arms-query/scripts/search_traces.py \
  --service-name my-app \
  --last-minutes 15

python skills/observability/arms/aliyun-arms-query/scripts/get_trace_detail.py \
  --trace-id 1c34ffee16xxxxxxxx

python skills/observability/arms/aliyun-arms-query/scripts/query_metrics.py \
  --metric appstat.incall \
  --pid "xxx@cn-hangzhou" \
  --last-minutes 30

python skills/observability/arms/aliyun-arms-query/scripts/list_trace_apps.py

python skills/observability/arms/aliyun-arms-query/scripts/get_stack.py \
  --trace-id 1c34ffee16xxxxxxxx \
  --rpc-id 0.1 \
  --pid "xxx@cn-hangzhou"

mkdir -p output/aliyun-arms-query
for f in skills/observability/arms/aliyun-arms-query/scripts/*.py; do
  python3 -m py_compile "$f"
done
echo "py_compile_ok" > output/aliyun-arms-query/validate.txt

© cinience, 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 9 other files (scripts, references) in skills/observability/arms/aliyun-arms-query of cinience/alicloud-skills.

• SKILL.md
• agents/openai.yaml
• references/api-reference.md
• references/sources.md
• scripts/_common.py
• scripts/get_stack.py
• scripts/get_trace_detail.py
• scripts/list_trace_apps.py
• scripts/query_metrics.py
• scripts/search_traces.py

Open the folder on GitHubat commit 1818263