Dashboard Preview
m4r1k/Eneru
Visually verify Eneru browser-dashboard changes against a live daemon or audit an exact deployment.
Bootstrap, create, connect to, operate, secure, scale, upgrade, troubleshoot, inspect, and tear down Alibaba Cloud Container Compute Service (ACS) Agent Sandbox environments.
$ npx skills add cinience/alicloud-skills --skill alicloud-acs-agent-sandbox -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cinience/alicloud-skills alicloud-acs-agent-sandbox --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cinience/alicloud-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/compute/acs/alicloud-acs-agent-sandbox .claude/skills/alicloud-acs-agent-sandbox && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "alicloud-acs-agent-sandbox" agent skill from https://github.com/cinience/alicloud-skills/tree/main/skills/compute/acs/alicloud-acs-agent-sandbox into .claude/skills/alicloud-acs-agent-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alicloud-acs-agent-sandbox", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cinience/alicloud-skills/tree/main/skills/compute/acs/alicloud-acs-agent-sandboxType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cinience/alicloud-skills --skill alicloud-acs-agent-sandbox -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cinience/alicloud-skills alicloud-acs-agent-sandbox --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cinience/alicloud-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/compute/acs/alicloud-acs-agent-sandbox .agents/skills/alicloud-acs-agent-sandbox && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "alicloud-acs-agent-sandbox" agent skill from https://github.com/cinience/alicloud-skills/tree/main/skills/compute/acs/alicloud-acs-agent-sandbox into .agents/skills/alicloud-acs-agent-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alicloud-acs-agent-sandbox", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cinience/alicloud-skills --skill alicloud-acs-agent-sandbox -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cinience/alicloud-skills alicloud-acs-agent-sandbox --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cinience/alicloud-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/compute/acs/alicloud-acs-agent-sandbox .cursor/skills/alicloud-acs-agent-sandbox && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "alicloud-acs-agent-sandbox" agent skill from https://github.com/cinience/alicloud-skills/tree/main/skills/compute/acs/alicloud-acs-agent-sandbox into .cursor/skills/alicloud-acs-agent-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alicloud-acs-agent-sandbox", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cinience/alicloud-skills.git --path skills/compute/acs/alicloud-acs-agent-sandbox--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cinience/alicloud-skills --skill alicloud-acs-agent-sandbox -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cinience/alicloud-skills alicloud-acs-agent-sandbox --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cinience/alicloud-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/compute/acs/alicloud-acs-agent-sandbox .gemini/skills/alicloud-acs-agent-sandbox && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "alicloud-acs-agent-sandbox" agent skill from https://github.com/cinience/alicloud-skills/tree/main/skills/compute/acs/alicloud-acs-agent-sandbox into .gemini/skills/alicloud-acs-agent-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alicloud-acs-agent-sandbox", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cinience/alicloud-skills alicloud-acs-agent-sandboxInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cinience/alicloud-skills --skill alicloud-acs-agent-sandbox -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cinience/alicloud-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/compute/acs/alicloud-acs-agent-sandbox .github/skills/alicloud-acs-agent-sandbox && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "alicloud-acs-agent-sandbox" agent skill from https://github.com/cinience/alicloud-skills/tree/main/skills/compute/acs/alicloud-acs-agent-sandbox into .github/skills/alicloud-acs-agent-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alicloud-acs-agent-sandbox", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cinience/alicloud-skills --skill alicloud-acs-agent-sandbox -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cinience/alicloud-skills alicloud-acs-agent-sandbox --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cinience/alicloud-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/compute/acs/alicloud-acs-agent-sandbox .opencode/skills/alicloud-acs-agent-sandbox && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "alicloud-acs-agent-sandbox" agent skill from https://github.com/cinience/alicloud-skills/tree/main/skills/compute/acs/alicloud-acs-agent-sandbox into .opencode/skills/alicloud-acs-agent-sandbox/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "alicloud-acs-agent-sandbox", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
alicloud-acs-agent-sandboxBootstrap, create, connect to, operate, secure, scale, upgrade, troubleshoot, inspect, and tear down Alibaba Cloud Container Compute Service (ACS) Agent Sandbox environments.
Alicloud Acs Agent Sandbox is an agent skill from cinience/alicloud-skills. Bootstrap, create, connect to, operate, secure, scale, upgrade, troubleshoot, inspect, and tear down Alibaba Cloud Container Compute Service (ACS) Agent Sandbox environments. Use for zero-to-Sandbox deployments from VPC and ACS cluster creation, Sandbox, SandboxSet, SandboxClaim, Checkpoint, SandboxUpdateOps, E2B SDK integration, tenant API keys and quotas, OSS or NAS CSI mounts, TrafficPolicy and SecurityProfile controls, SandboxGateway routing, Prometheus monitoring, ACK-based deployments, or ACK One…
Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/bootstrap-and-teardown.md` and `references/crd-reference.md`).
It sits in DevOps & Cloud, covering Deployment, Monitoring and alerting and Third-party API integration. It works with Alibaba Cloud and Prometheus. The repository describes itself as: alibaba cloud skills,qwen ,wan and all skills. The licence is MIT.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 1818263. It shows what the files ask for, not the result of running them.
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.
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3kubectlpythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use kubectl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
E2B_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Alicloud Acs Agent Sandbox loads about 2.7k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 142 tokens; SKILL.md has 996 words of instructions outside code blocks.
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.
The automated check found no risky patterns in SKILL.md.
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.
The full file from cinience/alicloud-skills at commit 1818263, republished under its MIT licence (© cinience). 996 words, ~2,733 tokens.
.claude/skills/alicloud-acs-agent-sandbox/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.Operate ACS Agent Sandbox through Kubernetes custom resources and the E2B-compatible API. Treat the sandbox workload as untrusted and preserve a reproducible evidence trail under output/alicloud-acs-agent-sandbox/.
python3 skills/compute/acs/alicloud-acs-agent-sandbox/scripts/inspect_agent_sandbox.py \
--output output/alicloud-acs-agent-sandbox/inspection.jsonhashPepper, kubeconfigs, or generated migration SQL in evidence.kubectl describe pod or dump Deployment/Pod arguments for Sandbox Manager: some addon versions place the admin API key in container arguments. Use the redacting inspector and bounded JSONPath queries; rotate the key immediately if it is exposed.automountServiceAccountToken: false unless the workload explicitly needs Kubernetes API access.100.100.100.200/32 and private networks except for explicitly required endpoints.NET_ADMIN, SYS_ADMIN, CAP_SETUID, or CAP_SETGID; these privileges can bypass in-namespace ACLs.code-interpreter:v1.6 and OpenClaw examples as validation images, not production-hardened images.SandboxUpdateOps rebuilds the Pod and does not retain rootfs, memory, or IP.volumeAttributes are immutable; recreating a PV can interrupt OSS access.csi runtime only on storage-enabled SandboxSets. It injects a privileged container and a /var/run/csi hostPath, which changes the isolation boundary.For an empty-account deployment, use $aliyun-vpc-manage and $alicloud-acs-cluster as described in bootstrap-and-teardown.md. Then use this sequence for the Agent Sandbox layer:
creation-lifecycle.md. Confirm managed-coredns is active before creating any component or Sandbox that needs cluster service discovery.ack-agent-identity when required, ack-agent-sandbox-controller, and ack-sandbox-manager. Grant AliyunCSManagedAgentSandboxRole only through the documented authorization flow.SandboxSet warm pool with explicit requests and limits, ACS labels, automountServiceAccountToken: false, and only required runtimes.status.availableReplicas == spec.replicas.Sandbox.create() or a SandboxClaim. Prefer claims for declarative Kubernetes workflows.status.phase=Running, Ready=True, the claimed label, runtime API operations, and network policy behavior.Minimal warm-pool shape:
apiVersion: agents.kruise.io/v1alpha1
kind: SandboxSet
metadata:
name: code-interpreter
namespace: default
spec:
replicas: 4
runtimes:
- name: agent-runtime
template:
metadata:
labels:
alibabacloud.com/acs: "true"
alibabacloud.com/compute-class: agent-sandbox
alibabacloud.com/compute-qos: default
spec:
automountServiceAccountToken: false
containers:
- name: sandbox
image: <REGION-LOCAL-HARDENED-IMAGE>
resources:
requests: {cpu: "1", memory: 1Gi, ephemeral-storage: 30Gi}
limits: {cpu: "1", memory: 1Gi}
terminationGracePeriodSeconds: 30The official ACS documentation currently requires E2B Python SDK versions below 2.25.0; its validated example pins e2b-code-interpreter==2.7.0 and e2b==2.24.0. Recheck the official page before changing these versions.
python3 -m venv .venv
. .venv/bin/activate
python -m pip install "e2b-code-interpreter==2.7.0" "e2b==2.24.0"Set E2B_DOMAIN and E2B_API_KEY outside source code. Exercise run_code, files.write/read, and commands.run, then explicitly pause or kill the test sandbox.
For private acceptance, port-forward service/sandbox-manager on port 7788, install the OpenKruise customized E2B patch package, set E2B_DOMAIN=localhost:7788, and pass --private-protocol. This uses HTTP only on the local tunnel and is not a production ingress design.
Run the bundled smoke test for a repeatable acceptance and guaranteed cleanup attempt:
python3 skills/compute/acs/alicloud-acs-agent-sandbox/scripts/e2b_smoke_test.py \
--template code-interpreter \
--output output/alicloud-acs-agent-sandbox/e2b-smoke.jsonFor an existing OSS or NAS PV, enable the csi runtime on the target SandboxSet and pass the mount as E2B metadata:
python3 skills/compute/acs/alicloud-acs-agent-sandbox/scripts/e2b_smoke_test.py \
--template code-interpreter \
--storage-type nas \
--storage-pv pv-nas-sandbox \
--storage-mount-path /mnt/shared \
--output output/alicloud-acs-agent-sandbox/e2b-nas-smoke.jsonFor OSS Agent Identity, also pass --credential-provider and --agent-name. See storage-mounts.md; the script never accepts or records AccessKeys.
Run inspection before and after a change. For manual follow-up, use bounded queries:
kubectl get sandbox,sandboxset,sandboxclaim,checkpoint,sandboxupdateops -A
kubectl get pods -n sandbox-system -o wide
kubectl get events -A --field-selector type=Warning --sort-by=.lastTimestamp
kubectl get trafficpolicy -A
kubectl get globaltrafficpolicy
kubectl get securityprofile -A
kubectl get globalsecurityprofileClassify findings as:
Save the inspection JSON, redacted manifests, command transcript, and final verification beneath output/alicloud-acs-agent-sandbox/<operation>/. A task is complete only when:
python3 -m py_compile skills/compute/acs/alicloud-acs-agent-sandbox/scripts/inspect_agent_sandbox.py
python3 -m py_compile skills/compute/acs/alicloud-acs-agent-sandbox/scripts/e2b_smoke_test.py
python3 skills/compute/acs/alicloud-acs-agent-sandbox/scripts/inspect_agent_sandbox.py --help
python3 skills/compute/acs/alicloud-acs-agent-sandbox/scripts/e2b_smoke_test.py --help
python3 scripts/quick_validate.py skills/compute/acs/alicloud-acs-agent-sandbox© cinience, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 12 other files (scripts, references) in skills/compute/acs/alicloud-acs-agent-sandbox of cinience/alicloud-skills.
Open the folder on GitHubat commit 1818263
Alicloud Acs Agent Sandbox next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Alicloud Acs Agent Sandbox this skillcinience/alicloud-skills | 397 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Dashboard Previewm4r1k/Eneru | 149 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Aqua Metricsoracle/accelerated-data-science | 125 | — | ~1.5k | Automated safety check: Pass | UPL-1.0 | |
| Analyzing Experiment Precompute CanaryPostHog/posthog | 40k | — | ~3.5k | Automated safety check: Pass | Custom licence | |
| Doca Collectx DeploymentNVIDIA/skills | 3.6k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Deepgram Prod Checklistjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~2.3k | Automated safety check: Pass | MIT |
m4r1k/Eneru
Visually verify Eneru browser-dashboard changes against a live daemon or audit an exact deployment.
oracle/accelerated-data-science
Set up Prometheus and Grafana monitoring for AQUA vLLM model deployments on OCI.
PostHog/posthog
Analyze the experiment precompute result-consistency canary across prod-US and prod-EU, deep-dive any issues, and produce an actionable report.
NVIDIA/skills
A skill your agent uses to deploy and operate a CollectX (clx) based DOCA telemetry collector on a host or BlueField — wiring providers / counters into the collector, running the collection daemon…
jeremylongshore/tons-of-skills-marketplace
Execute Deepgram production deployment checklist. An agent skill from jeremylongshore/tons-of-skills-marketplace.
Orchestra-Research/AI-Research-SKILLs
Deploys LLMs with vLLM for high-throughput serving, covering the OpenAI-compatible server, offline batch inference, monitoring and a Docker rollout.
cinience/alicloud-skills
A skill your agent uses when creating, migrating, or optimizing skills for this alicloud-skills repository.
cinience/alicloud-skills
Create, inspect, connect to, inventory, and delete Alibaba Cloud Container Compute Service (ACS) clusters through the official CS OpenAPI.
cinience/alicloud-skills
A skill your agent uses when managing Alibaba Cloud AnalyticDB for MySQL (ADB) via OpenAPI/SDK, including the user needs AnalyticDB resource lifecycle and configuration operations, status checks, or…
cinience/alicloud-skills
A skill your agent uses when managing Alibaba Cloud AIContent (AiContent) via OpenAPI/SDK, including the user needs AI content generation or content workflow operations in Alibaba Cloud, including…
cinience/alicloud-skills
A skill your agent uses when managing Alibaba Cloud Quan Miao (AiMiaoBi) via OpenAPI/SDK, including the user asks for Alibaba Cloud MiaoBi content operations, including listing resources…
cinience/alicloud-skills
A skill your agent uses when managing Alibaba Cloud AIRec (Airec) via OpenAPI/SDK, including the user needs recommendation-engine resource operations in Alibaba Cloud, including list/create/update…
Works with
Categories
Bootstrap, create, connect to, operate, secure, scale, upgrade, troubleshoot, inspect, and tear down Alibaba Cloud Container Compute Service (ACS) Agent Sandbox environments. Alicloud Acs Agent Sandbox is an agent skill from cinience/alicloud-skills. Bootstrap, create, connect to, operate, secure, scale, upgrade, troubleshoot, inspect, and tear down Alibaba Cloud Container Compute Service (ACS) Agent Sandbox environments.
Alicloud Acs Agent Sandbox fits situations like: zero-to-Sandbox deployments from VPC and ACS cluster creation; sandboxUpdateOps; E2B SDK integration; tenant API keys and quotas.
Run `npx skills add cinience/alicloud-skills --skill alicloud-acs-agent-sandbox -a claude-code`. Or copy the skill folder (skills/compute/acs/alicloud-acs-agent-sandbox in cinience/alicloud-skills) into .claude/skills/alicloud-acs-agent-sandbox in your project. Claude Code loads it when a task matches its description.
Run `npx skills add cinience/alicloud-skills --skill alicloud-acs-agent-sandbox -a codex`. Or copy the skill folder (skills/compute/acs/alicloud-acs-agent-sandbox in cinience/alicloud-skills) into .agents/skills/alicloud-acs-agent-sandbox in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cinience/alicloud-skills --skill alicloud-acs-agent-sandbox -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/alicloud-acs-agent-sandbox, .gemini/skills/alicloud-acs-agent-sandbox, .github/skills/alicloud-acs-agent-sandbox and .opencode/skills/alicloud-acs-agent-sandbox in your project.
Going by SKILL.md and its folder, Alicloud Acs Agent Sandbox needs Python for the scripts in its folder, the command-line tools its instructions call (python3, kubectl and python) and credentials named E2B_API_KEY. Our summary lists: Python 3; A credential in E2B_API_KEY.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Alicloud Acs Agent Sandbox is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Alicloud Acs Agent Sandbox: Dashboard Preview (m4r1k/Eneru, 149 stars), Aqua Metrics (oracle/accelerated-data-science, 125 stars), Analyzing Experiment Precompute Canary (PostHog/posthog, 40k stars) and Doca Collectx Deployment (NVIDIA/skills, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
cinience (a GitHub user) maintains it in cinience/alicloud-skills, which has 397 GitHub stars. The repository holds 96 skills in this directory. The repository was last updated on August 11, 2026.
Source: cinience/alicloud-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.