skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
huaweicloud/huaweicloud-skills73 installs

huawei-cloud-cloudrobo-infer

Manage CloudRobo inference services — deploy a model into a managed inference service, list/query deployed services and their logs, start/stop a running service, update or delete a service, and orchestrate the 'wait-deploy' convenience flow that polls a service until it finishes deploying. Inference services consume models produced by cloudrobo-train and are consumed by robo-dispatcher when dispatching embodied tasks. Triggers include: infer, inference, model deployment, deploy model, inference service, service deployment, start inference, stop inference, service logs, wait-deploy, model serving, 推理, 推理服务, 模型部署, 部署模型, 推理服务管理, 服务日志, 模型服务.

How do I install this agent skill?

npx skills add https://github.com/huaweicloud/huaweicloud-skills --skill huawei-cloud-cloudrobo-infer
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill manages Huawei Cloud CloudRobo inference services using an official CLI. It follows standard security practices such as credential masking and path-traversal protection for service identifiers. However, it is vulnerable to indirect prompt injection because it automatically discovers and processes model configuration files (including prompts and commands) from external cloud assets without sanitizing them before interpolation into deployment commands.

  • Socketpass

    No alerts

  • Snykfail

    Risk: CRITICAL · 2 issues

What does this agent skill do?

Windows / PowerShell: Examples use bash syntax. To run on Windows PowerShell:

  • Flatten \ line continuations to a single line, or end lines with a backtick.
  • Set env vars with $env:NAME="value" instead of export NAME="value".
  • Single-quoted JSON '{"a":"b"}' works as-is.

Overview

The cloudrobo-infer skill manages the full lifecycle of CloudRobo inference services (also called model-serving / inference-service): deploy a model (identified by model_id + model_version_id passed as a --model-json JSON object) into a long-running service, then operate it (start / stop / update / delete / logs), and use wait-deploy to poll until the service status is no longer DEPLOYING (status != "DEPLOYING"), returning any other state (e.g. RUNNING, FAILED, STOPPED).

wait-deploy only waits on the DEPLOYING phase — it does NOT wait through CREATING. Exact semantics: Wait-Deploy.

Applicable scenarios:

  • Model deployment — Deploy a model as an inference service (create → wait-deploy)
  • Wait-Deploy — Poll every 5s until status is no longer DEPLOYING (600s default)
  • Service O&M — List deployed services, show detail, update config, start/stop
  • Log diagnosis — list-logs with millisecond time range and keyword filter
  • Cross-skill orchestration — Consume models exported by cloudrobo-train; expose the service to robo-dispatcher for embodied tasks (via the service id).

Out of Scope:

  • Model training / dataset, robots, dispatch, and asset / compute pool / workspace lifecycle are separate CloudRobo capabilities (train / dataset / robot / dispatch / asset / resource / workspace). Route those requests through the matching Agent skill; this skill only produces an inference service that dispatch consumes via its id.

Architecture:

Agent / LLM
    │
    ├── CLI  →  cloudrobo infer <command>
    └── SDK  →  InferClient (Python)
                    │
                    ▼
              cloudrobo-service (REST API)
              /v1/infer-services/*

All operations target the cloudrobo-service backend with a valid workspace_id (the default workspace is used unless explicitly provided). Deploying a service consumes compute (pool) resources — always confirm before starting a long-running service.

Prerequisites

  • CLI installed, AK/SK configured, workspace resolved — references/cli-installation-guide.md.
  • A valid workspace_id (cloudrobo workspace current, or list + use).
  • A deployable model: model_id (=asset_id) + model_version_id (=latest_version_id): --model-json '{"model_id": "<asset_id>", "model_version_id": "<latest_version_id>"}'. The model must have ONLINE_DEPLOYMENT with status: "ENABLE" in show-asset; DRAFT/CREATING models are rejected with 403.
  • A compute pool: pool_type + flavor (cloudrobo resource list-pools --resource-type MODELARTS, only status: "AVAILABLE" pools). --pool-id pool-<resource_id> is optional — pass it only for a dedicated pool.
  • --stop-schedule-json is required by the backend: {"duration": <N>, "time_unit": "MINUTES"}.
  • Region: cloudrobo (0.3.0) has no --cli-region command-line option (the root command only accepts --verbose/-v; region is not a CLI flag). Set it with cloudrobo config set region <region> (persisted to ~/.cloudrobo/config.yaml) — default cn-southwest-2. Never append --cli-region to cloudrobo commands: an unknown option exits non-zero. --cli-region belongs to hcloud/KooCLI only, not here.

执行前置自检(Preflight — 每条命令前先做)

任一项失败立即输出中文提示并以非零码退出;禁止静默等待、禁止把空结果当成成功:

command -v cloudrobo >/dev/null 2>&1 || {
  echo "未检测到 cloudrobo 命令:请先安装聚合客户端 CLI(pip install hw-cloudrobo-client),详见 references/cli-installation-guide.md。" >&2; exit 2; }
cloudrobo infer --help >/dev/null 2>&1 || {
  echo "cloudrobo infer 子命令不可用:请安装或升级 hw-cloudrobo-client(聚合包,已含推理模块)后重试(cloudrobo --help 可确认已注册的命令)。" >&2; exit 2; }
cloudrobo asset --help >/dev/null 2>&1 || {
  echo "cloudrobo asset 命令组不可用(报错形如 Error: No such command asset):说明只装了推理模块,模型资料解析无法进行。请改装聚合客户端 pip install hw-cloudrobo-client 后重试。" >&2; exit 2; }
  • 凭证缺失不阻断上面的自检,但所有联网命令都会以 401 失败:先 export HUAWEI_CLOUD_AK=<ak> HUAWEI_CLOUD_SK=<sk> 或 cloudrobo config set ak <ak> sk <sk>,再重试。
  • scripts/test-cli-commands.sh 自检更严:CLI、infer 子命令、AK/SK 任一缺失即输出中文 提示并 exit 2(没有凭证时它不会给出虚假通过)。
  • 查询类命令返回空列表属正常结果(0 条服务),不等同于失败;命令报错则必须如实上报。

Workflow

Natural-Language-First Principle

Every workflow below starts from a user intent (1-2 sentences), not from manual CLI/SDK orchestration. The skill then drives the matching command chain and reports state feedback (status changes, polling progress).

Model Deployment Workflow (interactive parameter resolution)

Scenario: "我想创建一个推理服务" / "Deploy model X as an inference service."

Core principle: query each required parameter → present options → let user choose → assemble full command → execute.

  1. Resolve workspace — cloudrobo workspace current.

    • Default workspace set → use its workspace_id and asset_catalog_id.
    • Not set → cloudrobo workspace list → present names + IDs → cloudrobo workspace use --workspace-id <id> → re-run current to confirm.
  2. Ask model source & type — ask in this order:

    • Source (where to search): embodiment plaza (具身广场), workspace assets (空间资产), or custom (自定义). The source decides the entire parameter policy below.
    • Type (by ext_metadata.model_type): perception (感知), vln (导航), vla (操作), planning (规划).
    • Vague request (e.g. "so101 相关的模型") → skip both and use cloudrobo asset search-assets by keyword.
    • Branch immediately to the Model Source → Parameter Policy table before assembling create.
  3. Query models:

    • Embodiment plaza: cloudrobo asset list-publication-assets --type model --actions ONLINE_DEPLOYMENT --action-status ENABLE.
    • Workspace assets: cloudrobo asset list-assets --catalog-id <asset_catalog_id> --type model (use --catalog-id, NOT --repository-id).
    • Keyword search: cloudrobo asset search-assets --keyword "<keyword>" --type model.
    • Present matching models (name, asset_id, status, model_type) for selection.
  4. Resolve model version — cloudrobo asset show-asset --asset-id <asset_id>.

    • latest_version_id → model_version_id in --model-json.
    • version_count > 1 → cloudrobo asset list-versions --asset-id <id> → let user choose.
    • ONLINE_DEPLOYMENT must be ENABLE; model status must be RELEASE (or published), otherwise the platform returns 403.
  5. Auto-discover deployment parameters — space asset / custom models ONLY. Embodiment plaza models: skip this step entirely and carry none of --cmd/--image-swr-url/--envs-json/--skill-config-json/--service-invoke-json/ --readiness-health-json/--model-ext-metadata/--model-json.mount_path — plaza models are pre-configured on the platform, and extra parameters risk a mismatched deployment.

    For space asset / custom models, discover from the model's algorithm asset and its config files (algorithm asset → ext_metadata.command / engine.image_url / environment_variables / deployment_config; skill_config.json and r2c config via the download-url API). Full discovery table, download-url code, strict field and r2c fallback rules: references/service-config-catalog.md → "Parameter Auto-Discovery Sources".

    Priority: config files > ext_metadata fields > ask user. Undiscoverable parameters are skipped silently (never block deployment). For "bare" models with no algorithm association, ask the user whether to supply optional parameters manually.

  6. Resolve pool & flavor — cloudrobo resource list-pools --resource-type MODELARTS.

    • Only status: "AVAILABLE" pools are usable; present names, pool_type and flavors.
    • resource_id → --pool-id pool-<resource_id>; pool_type → --pool-type (DEDICATED / SHARED). Omit --pool-id for SHARED pools.
    • Flavors live under config.flavor grouped by hardware (CPU/GPU/ASCEND); let the user pick (e.g. "1 * SNT9B2 | 24 vCPUs | 192 GiB").
  7. Confirm parameters & deploy — present the create command using the variant that matches the source from Step 2 (never mix variants):

    Variant A — embodiment plaza (required core parameters ONLY):

    cloudrobo infer create --name <service-name> --flavor "<flavor>" --model-json '{"model_id": "<asset_id>", "model_version_id": "<latest_version_id>"}' --workspace-id <workspace_id> --pool-type <pool_type> --stop-schedule-json '{"duration": 60, "time_unit": "MINUTES"}' [--pool-id pool-<resource_id>] [--dry-run]
    

    Variant B — space asset / custom (core + auto-discovered params):

    cloudrobo infer create --name <service-name> --flavor "<flavor>" --model-json '{"model_id": "<asset_id>", "model_version_id": "<latest_version_id>", "mount_path": "<mount_path>"}' --workspace-id <workspace_id> --pool-type <pool_type> --stop-schedule-json '{"duration": 60, "time_unit": "MINUTES"}' [--pool-id pool-<resource_id>] [--cmd "<command>"] [--image-swr-url "<image_url>"] [--envs-json '{"KEY":"VALUE"}'] [--skill-config-json '{"skills":[{"name":"...","prompt":"..."}],"strict":true}'] [--service-invoke-json '{"auth_type":"...","port":8080,"protocol":"HTTP"}'] [--readiness-health-json '{"path":"/ready","port":8080}'] [--model-ext-metadata '<r2c_config_file_content>'] [--dry-run]
    
    • Include only parameters actually discovered in Step 5; --pool-id only for DEDICATED.
    • --envs-json takes a map ({"K":"V"}) — convert the asset's array form first.
    • --skill-config-json skill items keep only name + prompt.
    • Run with --dry-run first, confirm with the user, then re-run without --dry-run.
  8. Wait for deployment — cloudrobo infer wait-deploy --service-id <sid> (polls every 5s until status != "DEPLOYING", 600s default).

    • After create the service auto-enters CREATING → DEPLOYING. Do NOT call start — it returns 400 "Status DEPLOYING does not support start". start only restarts a STOPPED service.
    • If wait-deploy returns while still CREATING, immediately re-invoke it.
  9. Report — output the service id (the returned identifier; some docs call it service_id), model name, flavor and final status. On FAILED → list-logs for diagnosis. Never auto-delete a failed service — present the delete command and ask for explicit confirmation.

Asset note: model_id / version_id / flavor / pool_id must be resolved dynamically via the query commands above; never hardcode them. Always let the user choose from queried options.

Model Source → Parameter Policy (authoritative decision table)

This table is the single source of truth for which create parameters to carry, based on the model source resolved in Step 2. cloudrobo-model-workflow Stage 3 references it to keep both skills consistent. Resolve the source first, then apply exactly the matching column — do not mix variants.

Model source (from Step 2)Search command (Step 3)Auto-discovery (Step 5)create parameters to carry
Embodiment plaza (具身广场)cloudrobo asset list-publication-assets --type model --actions ONLINE_DEPLOYMENT --action-status ENABLESKIP entirely — model is pre-configured on platformRequired core only: --name, --flavor, --model-json (model_id+model_version_id), --workspace-id, --pool-type, --stop-schedule-json; --pool-id only for DEDICATED pool. Do NOT carry --cmd/--image-swr-url/--envs-json/--skill-config-json/--service-invoke-json/--readiness-health-json/--model-ext-metadata/--model-json.mount_path
Space asset / custom (空间资产/自定义)cloudrobo asset list-assets --catalog-id <asset_catalog_id> --type model / cloudrobo asset search-assets --keyword ...Run Step 5 fully — query algorithm asset (cmd/image/envs/mount_path/service-invoke/readiness-health) + download skill_config.json + r2c configRequired core plus every parameter actually discovered in Step 5; omit undiscovered ones silently
Unknown model id (user passed explicit id)cloudrobo asset show-asset --asset-id <id>Determine from show-asset: ONLINE_DEPLOYMENT action pointing to a platform algorithm → treat as space-asset path (run Step 5); self-contained/pre-configured config → core onlyAs per the resolved path

Rationale: embodiment plaza models bundle their orchestration, image, envs, health probes, skills and r2c mapping on the platform. Re-supplying these in create is redundant and risks an invalid/mismatched deployment (the "不该带的参数不要带" rule). Space asset / custom models have no bundled config, so their parameters must be discovered and passed explicitly.

Wait-Deploy Workflow (CLI convenience)

Scenario: "Wait for this inference service to finish deploying."

  1. cloudrobo infer wait-deploy --service-id <sid> [--timeout 600] — client-side polling of show every 5s until status != "DEPLOYING"; returns any other state (RUNNING, FAILED, STOPPED). Timeout range 1–3600; on timeout it raises RuntimeError → JSON error + ClickException, non-zero exit.
  2. Feedback — report the final status; on FAILED suggest list-logs.

wait-deploy does NOT create the service — call create first, then wait-deploy. Do NOT call start after create (auto-deploys CREATING → DEPLOYING → RUNNING); start is only for restarting a STOPPED service.

Service O&M / Lookup Workflow

Scenario: "What inference services are running in my workspace?"

  1. cloudrobo infer list --workspace-id <ws> [--status <status>] [--model-id <mid>] [--name <name>] [--model-name <mn>] [--model-version-id <mvid>] [--model-version-name <mvn>] [--user-name <un>] [--user-id <uid>] + pagination (--limit/--offset) and sorting (--sort-key/--sort-dir).
  2. cloudrobo infer show --service-id <sid> for a full config snapshot.
  3. Report status and key fields (model, flavor, status, pool).

Service Start/Stop Workflow

Scenario: "Stop the inference service behind this API." / "Bring it back up."

  1. Confirm the service via show --service-id <sid>.
  2. cloudrobo infer stop --service-id <sid> or start --service-id <sid> (mutating; confirm before executing).
  3. Poll show until the desired terminal state (STOPPED / RUNNING).

Log Diagnosis Workflow

Scenario: "Why is my deployed service failing? Show me its logs."

  1. cloudrobo infer list-logs --service-id <sid> --start-time <ms> --end-time <ms> — both timestamps are milliseconds (13-digit). Optional: --keywords, --limit, --line-num, --is-count, --highlight, --is-desc.
  2. Correlate log lines with show status (e.g. CREATE_FAILED/START_FAILED).
  3. Suggest remediation (pool capacity, model artifact, health-check config).

Service Update / Deletion Workflow

Scenario: "Reconfigure this service" / "Shut down and remove this service."

  • Update — cloudrobo infer update --service-id <sid> [--description <desc>] [--model-ext-metadata <json>] [--dry-run] (mutating; confirm). update only supports --description and --model-ext-metadata; changing image/flavor/model/pool/stop-schedule is not supported — use delete + create to rebuild.
  • Delete — cloudrobo infer delete --service-id <sid> [--dry-run] (mutating; irreversible; confirm). It removes only the service, not the model asset — delete assets through the CloudRobo asset skill (cloudrobo asset delete-asset).

Combined Workflow A — Deploy a trained model (infer + train + asset)

Scenario: "I trained a VLA model; deploy it as an inference service."

  1. Resolve workspace (cloudrobo workspace current).
  2. Query the model (cloudrobo asset list-assets --catalog-id <asset_catalog_id> --type model) → asset_id.
  3. cloudrobo asset show-asset --asset-id <asset_id> → latest_version_id; verify ONLINE_DEPLOYMENT = ENABLE.
  4. cloudrobo resource list-pools --resource-type MODELARTS → user selects resource_id and flavor.
  5. A trained model is a space asset → Variant B of Step 7: run Step 5 auto-discovery and carry whatever was discovered.
  6. cloudrobo infer create ... (Variant B) → cloudrobo infer wait-deploy --service-id <sid> (do NOT call start — the service auto-deploys).
  7. Report the service id and status; the service is now consumable.

Core Commands

cloudrobo infer <command> [OPTIONS]
SubcommandDescriptionKey options
createDeploy a new inference service--name, --flavor, --model-json, --workspace-id, --pool-type, --stop-schedule-json (required); --pool-id optional (dedicated pools only)
wait-deployPoll until deployment completes--service-id, --timeout
listList inference services--workspace-id, --status, --limit, --offset
showShow service detail--service-id
start / stopStart or stop a service--service-id
updateUpdate service config--service-id, --description, --model-ext-metadata
deleteDelete a service--service-id
list-logsQuery service logs--service-id, --start-time (ms), --end-time (ms), --keywords

SDK path: when CLI is inconvenient (dynamic JSON, cross-package queries), use InferClient — one consolidated snippet for the five main calls (create / show / list / list-logs / wait-deploy) lives in references/service-config-catalog.md → "InferClient Main-Chain Snippet". Parameter-resolution table and edge cases: same file → "Parameter Resolution & Confirmation", "Edge Cases". SDK exposes 9 methods, CLI exposes 9 commands (0 gaps); wait-deploy is a client-side polling helper in both.

Return identifier: create/show/list/wait-deploy identify the service with the id field (some API/SDK docs call it service_id). Use that value as --service-id for all downstream commands — there is no top-level service_id key in create/show responses.

Parameter Confirmation

Resolve every value from query commands, present it to the user, then execute. Never hardcode IDs or flavors; mutating commands (create / start / stop / update / delete) need an explicit confirmation first.

ParameterRequiredResolution
--workspace-idcreate / listcloudrobo workspace current (or list + use)
--model-jsoncreatemodel_id from asset search, model_version_id = latest_version_id from show-asset
--flavorcreatecloudrobo resource list-pools --resource-type MODELARTS → config.flavor
--pool-typecreateSHARED / DEDICATED from the selected pool
--pool-iddedicated pool onlypool-<resource_id> from the selected pool
--stop-schedule-jsoncreate{"duration": <N>, "time_unit": "MINUTES"} (backend-required)
--service-idshow / start / stop / update / delete / logs / wait-deployid returned by create, show or list
--dry-runcreate / update / deleteadd to preview parameter assembly; no resource is created or changed

Reference Documents

Edge Cases

See references/service-config-catalog.md → "Edge Cases" for the full table (missing model_id, invalid JSON, wrong timestamp unit, 403 permission deny, 500 internal error, missing stop-schedule, r2c config fallback, envs format mismatch, cross-skill invocation).

Verification Method

Specification compliance and functional smoke both run the same scripted suite:

bash scripts/test-cli-commands.sh

The script runs a one-time preflight (CLI present, infer registered, AK/SK present; region is reported when configured, otherwise the client default applies), executes the read-only and dry-run cases in one batch, scores negative cases as EXPECT-FAIL (pass means a non-zero exit code), and exits non-zero when any case fails.

Test Cases

See templates/test-vars.json for the full case list (deployment, wait-deploy, lifecycle, logs, safety). Cases marked "result": "SKIP" are mutating and never auto-run; cases marked "negative": true must exit non-zero.

Verification Checklist

  • After create, service appears in list with correct status
  • After wait-deploy, status is no longer DEPLOYING (or timeout/failure is reported with log guidance)
  • After start/stop, show reflects the new status
  • After delete, show returns not-found
  • list-logs with ms timestamps returns log lines; keyword filter works
  • Negative cases (../ service_id, malformed JSON, missing --name / --model-json) exit non-zero with the client-side error text (Click Missing option ...)
  • Mutating operations (especially start) prompt for user confirmation

Best Practices

  • Resolve each create parameter via query commands, then let the user choose — never hardcode
  • Model source drives parameter policy: resolve the source (Step 2) first, then apply the Model Source → Parameter Policy table. Plaza models carry required core params only; space asset / custom models run Step 5 auto-discovery
  • Model search: cloudrobo asset list-publication-assets --actions ONLINE_DEPLOYMENT --action-status ENABLE for deployable plaza models; cloudrobo asset list-assets --catalog-id <id> for workspace models; cloudrobo asset search-assets --keyword "<kw>" for fuzzy search
  • --model-json's model_version_id must be latest_version_id from show-asset, NOT actions[].algorithm.version_id
  • Always include --stop-schedule-json '{"duration": N, "time_unit": "MINUTES"}' in create; omit --pool-id unless deploying to a dedicated pool
  • Use wait-deploy after create (5s interval, 600s default). Do NOT call start after create — the service auto-deploys; re-invoke wait-deploy if it returns while CREATING
  • Use --dry-run on create to validate parameter assembly before submission
  • Report health-check pickup as part of deployment verification
  • Use list-logs with --keywords to isolate errors fast; remember ms timestamps
  • Keep internet_access_enable OFF unless the user explicitly needs outbound access
  • Mask sensitive envs/values; never echo credentials
  • Combine with workspace (cloudrobo workspace current) and asset skills to resolve context; combine with dispatch to execute embodied tasks

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-cloudrobo-infer">View huawei-cloud-cloudrobo-infer on skillZs</a>