
huawei-cloud-maas-tokens-usage
Query Huawei Cloud MaaS (Model as a Service) tokens usage statistics, including total tokens, prompt tokens, completion tokens, total requests, and total errors. Supports preset service, my service, and custom endpoint with time range queries (last 7/14/30 days or custom). Data source is MaaS ShowStatistics API, consistent with console. Use this skill when the user wants to: (1) query MaaS token consumption statistics, (2) check MaaS service request counts and error rates, (3) analyze token usage for preset service or my service, (4) monitor MaaS usage over a specific time period. Trigger: user mentions "MaaS", "Model as a Service", "tokens usage", "token consumption", "request count", "error count", "MaaS usage", "preset service usage", "completion tokens", "prompt tokens", "MaaS statistics", "模型服务", "令牌用量", "token统计", "token用量", "词元用量", "请求次数", "MaaS监控", "华为云MaaS"
- Installs
- 195
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/huaweicloud/huaweicloud-skills --skill huawei-cloud-maas-tokens-usage- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads huawei-cloud-maas-tokens-usage automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Huawei Cloud MaaS Tokens Usage Monitoring Skill
Overview
Query Huawei Cloud MaaS (Model as a Service) usage statistics via the ShowStatistics API, including total tokens, prompt tokens, completion tokens, total requests, and total errors. Supports querying last 7 days, 14 days, 30 days, or custom time ranges. Default query type is MaaS preset service. AK/SK never leaves Python process memory.
Tool separation principle:
- Python SDK signing — AK/SK signing via
huaweicloudsdkcore.signer.Signer(credentials never leave Python process memory, never appear inps -ef) - Python requests — HTTP POST to MaaS ShowStatistics endpoint (signed request sent from Python process only)
- No hcloud CLI — MaaS ShowStatistics is not covered by KooCLI; pure Python REST + SDK signing
Security architecture:
- AK/SK is read from environment variables (
HW_ACCESS_KEY/HW_SECRET_KEY) or a credentials file by the Python script (never typed by user in conversation, never passed via CLI args, never exported to shell) - Temporary credentials add
HW_SECURITY_TOKEN(passed asX-Security-Tokenheader by the SDK signer) - Signing is performed by
huaweicloudsdkcore.Signerinside the Python process; the signed Authorization header is sent to the MaaS endpoint only - AK/SK is never printed, never logged, never appears in
ps -ef, never appears in conversation - No KMS dependency, no hcloud CLI dependency, no third-party skill dependency
⛔ Prohibited Operations (Security Constraints)
This skill strictly forbids the following operations, regardless of user requests:
| Prohibited Operation | Reason |
|---|---|
| ❌ Ask the user to provide AK/SK directly in the conversation | Credentials must never appear in conversation |
| ❌ Accept AK/SK directly provided by the user in the conversation | Credentials must never appear in conversation |
| ❌ Hardcode AK/SK in scripts or command-line arguments | Credential exposure risk |
❌ Use hcloud configure set to pass plaintext AK/SK values | Credentials recorded in command history |
| ❌ Print or log the AK/SK values in any output | Credentials must only exist in Python process memory |
| ❌ Export AK/SK to shell variables or stdout via the script | Credentials must stay in Python process; only statistics result is printed |
| ❌ Implement SDK-HMAC-SHA256 signing manually | Error-prone; must use huaweicloudsdkcore.Signer |
❌ Use service_type=3 for Custom Endpoint | API only supports [1, 2, 4]; returns 400 error |
❌ Hardcode timezone as CST or Asia/Shanghai | Must auto-detect OS local timezone |
| ❌ Query a time range exceeding 30 days without segmentation | API retains only 30 days; script must auto-segment |
❌ Use a region other than cn-southwest-2 | MaaS ShowStatistics only supports Southwest-Guiyang-1 |
❌ Write a new query script instead of using maas_rest_usage_stats.py | Must use the script in scripts/ directory |
If a user requests a prohibited operation, you must refuse and explain the security constraint.
🚫 Unsupported Operations (Capability Boundary)
This skill only supports the ShowStatistics aggregate statistics query. The MaaS monitoring API family contains 10 APIs; the other 9 are outside this skill's capability boundary and are not implemented.
| Unsupported API | Purpose | Why Not Covered |
|---|---|---|
ListServiceStatistics | List per-service statistics | Skill focuses on aggregate tokens usage, not per-service breakdown |
ShowDetailChart | Show detail chart data | Skill returns a summary table, not chart series |
ListErrors | List error details | Skill reports error count/rate only, not error detail records |
ListServices | List services | Skill queries statistics, not service inventory |
ListSourceIps | List source IPs | Skill does not track caller IP distribution |
GetServiceDetailMetricData | Get service detail metrics | Skill provides aggregate metrics, not per-service detail |
ListVersionStatistics | List version statistics | Skill does not segment by model version |
GetGenerationSupportedMetrics | Get supported metrics | Skill uses the fixed metric set from ShowStatistics response |
ShowErrorCodeChart | Show error code chart | Skill reports error rate, not error code distribution |
If a user requests any of the above APIs or their underlying capabilities (per-service breakdown, error detail, chart data, source IP list, version statistics, error code distribution, etc.), you must refuse and clarify: this skill only supports the ShowStatistics aggregate statistics query (total/prompt/completion tokens, request count, error count, error rate).
Architecture
Huawei Cloud MaaS Tokens Usage Monitoring
├── Task 1: Query MaaS Tokens Usage Statistics (via MaaS ShowStatistics API)
│ ├── 1a. Load credentials (env vars or --credentials-file, in Python memory only)
│ ├── 1b. Resolve time range (last 7/14/30 days, this month, or custom YYYY-MM-DD)
│ ├── 1c. Auto-segment (split ranges > 30 days, aggregate results)
│ ├── 1d. SDK sign request (huaweicloudsdkcore.Signer, AK/SK in process memory)
│ ├── 1e. POST ShowStatistics (modelarts.{region}.myhuaweicloud.com)
│ ├── 1f. Aggregate & convert (token unit: thousand → M tokens)
│ └── 1g. Print table (Total/Prompt/Completion Tokens, Requests, Errors, Error Rate)
└── Task 2: Verify & Report (compare with console, check error rate)
Prerequisites
Prerequisite check 1/3: Python 3.8+ and huaweicloudsdkcore required
The MaaS ShowStatistics query script uses Python to keep AK/SK in process memory only. Install the required packages:
# Auto-use China mirror when system timezone is UTC+8 (faster in CN region; auto-detected via Python) PIP_INDEX=$(python3 -c "import time;print('-i https://mirrors.huaweicloud.com/repository/pypi/simple' if -(time.timezone)//3600==8 else '')") pip install $PIP_INDEX huaweicloudsdkcore requestsVerify SDK installation:
python3 --version # Expected: >= 3.8 python3 -c "import huaweicloudsdkcore; print('SDK OK')" python3 -c "import requests; print('requests OK')"
Prerequisite check 2/3: Environment variables for Python SDK credentials (highest priority)
The query script (
maas_rest_usage_stats.py) reads credentials from environment variables or a credentials file. The following environment variables MUST be set before running the script (unless--credentials-fileis used):
Variable Required Description HW_ACCESS_KEYYes Huawei Cloud Access Key ID (AK) HW_SECRET_KEYYes Huawei Cloud Secret Access Key (SK) HW_SECURITY_TOKENNo Temporary security token (only for temporary AK/SK) # Linux — verify HW_ACCESS_KEY / HW_SECRET_KEY are set (values never printed) python3 -c 'import os,sys;ak=os.environ.get("HW_ACCESS_KEY","");sk=os.environ.get("HW_SECRET_KEY","");ok=bool(ak) and bool(sk);print("AK/SK configured OK" if ok else "ERROR: HW_ACCESS_KEY/HW_SECRET_KEY not set");sys.exit(0 if ok else 1)' # Windows (cmd / PowerShell) python -c "import os,sys;ak=os.environ.get('HW_ACCESS_KEY','');sk=os.environ.get('HW_SECRET_KEY','');ok=bool(ak) and bool(sk);print('AK/SK configured OK' if ok else 'ERROR: HW_ACCESS_KEY/HW_SECRET_KEY not set');sys.exit(0 if ok else 1)"If verification reports ERROR (variables not set), configure them:
- Linux: add
export HW_ACCESS_KEY=.../export HW_SECRET_KEY=...to your shell profile (~/.bashrc,~/.zshrc) or a secrets manager, thensourcethe profile.- Windows: set system environment variables via the GUI (System Properties → Advanced → Environment Variables → System variables → New). See references/cli-installation-guide.md "Windows GUI Setup" for step-by-step instructions. Avoid
setx(it records credentials in command history).⚠️ Never set these variables in conversation or hardcode them in scripts. After setting, restart the terminal/Python process and re-run the verification above.
Prerequisite check 3/3: MaaS service region limitation
- Region: cn-southwest-2 (Southwest-Guiyang-1) — the only region supported by MaaS ShowStatistics API
- API retention: 30 days of statistics data
- Rate limit: total requests ≤ 1000/min, per-user ≤ 200/min
Authentication
Security rules (must be followed):
- Prohibited from reading, echoing, or printing AK/SK values
- Prohibited from asking the user to input AK/SK directly in the conversation
- Prohibited from using
hcloud configure setto pass plaintext credential values- Prohibited from accepting AK/SK directly provided by the user in the conversation
- Only allowed to read credentials from environment variables or a credentials file
⚠️ Important: Handling user-provided credentials
If a user attempts to provide AK/SK directly (e.g., "my AK is xxx, SK is yyy"):
- Stop immediately — Do not execute any commands
- Politely refuse and return the following message:
For account security, please do not provide Huawei Cloud Access Key ID and Access Key Secret directly in the conversation. Please use one of the following secure methods to configure credentials: Method 1: Environment variables (permanent AK/SK) export HW_ACCESS_KEY=<your-access-key-id> export HW_SECRET_KEY=<your-access-key-secret> Method 2: Environment variables (temporary AK/SK + Security Token) export HW_ACCESS_KEY=<your-temp-access-key-id> export HW_SECRET_KEY=<your-temp-access-key-secret> export HW_SECURITY_TOKEN=<your-security-token> Method 3: Credentials file Create a file (e.g., ~/aksk.txt) with AK on line 1, SK on line 2, Security Token on line 3 (if using temporary credentials). Then use: --credentials-file ~/aksk.txt After configuration is complete, please retry your request.- Do not continue executing any Huawei Cloud operations until credentials are configured
IAM Permission Policies
Ensure the IAM user has the required permissions (ModelArts monitoring + IAM read, scoped to the MaaS query workflow only). See references/iam-policies.md for the full permission table and recommended IAM policy JSON.
Permission boundaries:
- Scope constraint: Only query MaaS statistics data (read-only). Never modify or delete any MaaS service, endpoint, or configuration.
- Must stop if: credentials missing or invalid, user declines any confirmation, API returns 403/401, or time range exceeds 30 days and segmentation fails.
- Prohibited actions: modifying MaaS services, deleting API keys, changing IAM policies, accessing resources outside the MaaS query workflow, running commands not documented in this skill.
Core Workflows
Task 1: Query MaaS Tokens Usage Statistics
Query MaaS usage statistics via the ShowStatistics API. Data is consistent with the Huawei Cloud console.
⚠️ Tool separation: Python SDK signing + Python requests
- Python SDK (
huaweicloudsdkcore.Signer): Signs the request with AK/SK. Credentials never leave Python process memory.- Python requests: Sends the signed HTTP POST to the MaaS endpoint. No CLI, no shell variable, no
ps -efleakage.
📄 Detailed steps → references/task-query-tokens-usage.md
Sub-tasks:
- 1a. Load credentials — Read
HW_ACCESS_KEY/HW_SECRET_KEY/HW_SECURITY_TOKENfrom env vars, or read from--credentials-file(supports one-per-line, comma-separated, KEY=VALUE formats) - 1b. Resolve time range — Parse
--from/--to(YYYY-MM-DD), or map user expression ("last 7 days" / "last 14 days" / "last 30 days" / "this month") to a rolling/calendar window - 1c. Auto-segment — If time range exceeds 30 days, split into multiple ≤ 30-day segments and aggregate results
- 1d. SDK sign request —
Signer(_Creds(ak, sk)).sign(sdk_request)— AK/SK in Python process memory only - 1e. POST ShowStatistics —
requests.post("https://modelarts.{region}.myhuaweicloud.com/v1/{project_id}/maas/monitoring/show-statistics", headers=signed_headers, data=body_bytes) - 1f. Aggregate & convert — Sum segment results; convert token unit (thousand → M tokens, actual = value × 1000)
- 1g. Print table — Output Total Tokens / Prompt Tokens / Completion Tokens / Total Requests / Total Errors / Error Rate + Period
Task 2: Verify & Report
Compare the API result with the Huawei Cloud console and report the error rate.
📄 Acceptance criteria → references/acceptance-criteria.md
⚠️ Small discrepancy is normal. API vs. console may differ by < 0.1% due to minor time boundary differences. Data is reliable.
Core Commands
Python Script (SDK signing + requests — AK/SK never in ps -ef)
| Command | Description |
|---|---|
pip install huaweicloudsdkcore requests | Install Python SDK signing library + HTTP client (for UTC+8, add -i https://mirrors.huaweicloud.com/repository/pypi/simple) |
python3 scripts/maas_rest_usage_stats.py --from 2026-05-08 --to 2026-05-21 | Query preset service usage (default --service-type 2) for the given date range |
python3 scripts/maas_rest_usage_stats.py --from 2026-05-08 --to 2026-05-21 --service-type 1 | Query My Service usage |
python3 scripts/maas_rest_usage_stats.py --from 2026-05-08 --to 2026-05-21 --service-type 4 | Query Custom Endpoint usage |
python3 scripts/maas_rest_usage_stats.py --from 2026-05-08 --to 2026-05-21 --infer-type batch | Query batch inference usage (default real_time) |
python3 scripts/maas_rest_usage_stats.py --from 2026-05-08 --to 2026-05-21 --api-keys key1 key2 | Filter by API Key list |
python3 scripts/maas_rest_usage_stats.py --from 2026-05-08 --to 2026-05-21 --credentials-file /path/to/aksk.txt | Use credentials file instead of env vars |
python3 scripts/maas_rest_usage_stats.py --from 2026-05-08 --to 2026-05-21 --raw | Show raw API response (for debugging) |
⚠️ Key constraints on Core Commands:
- MaaS query: MUST use
scripts/maas_rest_usage_stats.py— AK/SK never inps -ef- Credentials: MUST use env vars or
--credentials-file— never hardcode, never pass via CLI args--service-type: MUST be 1, 2, or 4 — never 3 (API returns 400)--region: MUST becn-southwest-2(default) — the only supported region- Time range: MUST match user expression exactly — "last 7 days" ≠ "this month"
Parameter Confirmation
Before executing any task, the following parameters must be confirmed with the user. Guessing is prohibited.
| Parameter | Required/Optional | Description | Default |
|---|---|---|---|
| Time range | Required | --from / --to (YYYY-MM-DD), or user expression ("last 7 days", "last 14 days", "last 30 days", "this month") | Last 7 days |
| Service type | Optional | --service-type: 1=My Service, 2=Preset Service, 4=Custom Endpoint | 2 (Preset Service) |
| Inference type | Optional | --infer-type: real_time (online) or batch | real_time |
| Region | Optional | Huawei Cloud region (only cn-southwest-2 is supported) | cn-southwest-2 |
| API Keys filter | Optional | --api-keys list to filter specific keys | All keys |
| Credentials file | Optional | --credentials-file path (alternative to env vars) | - |
| Raw response | Optional | --raw flag to show raw API response | off |
Note: No AK/SK parameter is required. Credentials are read from environment variables or a credentials file by the Python script. AK/SK is never exported from the Python process.
Script Tools
| Script | Description |
|---|---|
| maas_rest_usage_stats.py | MaaS ShowStatistics API query script (SDK signing + requests, AK/SK never in ps -ef). Auto-segments ranges > 30 days, auto-detects OS local timezone, supports permanent/temporary AK/SK + credentials file. See Core Commands above for usage. |
⚠️ Script usage rules:
- Must use the existing script; do not write a new query script as a replacement
- Do not split the script internal logic into individual curl/HTTP commands
- Do not implement SDK-HMAC-SHA256 signing manually — must use
huaweicloudsdkcore.Signer
Verification Method
See references/verification-method.md for details. For common issues and solutions, see references/troubleshooting.md.
Quick validation (permanent AK/SK):
python3 -c 'import os,sys;ak=os.environ.get("HW_ACCESS_KEY","");sk=os.environ.get("HW_SECRET_KEY","");ok=bool(ak) and bool(sk);print("AK/SK configured OK" if ok else "ERROR: HW_ACCESS_KEY/HW_SECRET_KEY not set");sys.exit(0 if ok else 1)'
python3 scripts/maas_rest_usage_stats.py --from 2026-05-08 --to 2026-05-21
Quick validation (temporary AK/SK + Security Token):
python3 -c 'import os,sys;ak=os.environ.get("HW_ACCESS_KEY","");sk=os.environ.get("HW_SECRET_KEY","");st=os.environ.get("HW_SECURITY_TOKEN","");ok=bool(ak) and bool(sk) and bool(st);print("Temp AK/SK + Token configured OK" if ok else "ERROR: HW_ACCESS_KEY/HW_SECRET_KEY/HW_SECURITY_TOKEN not set");sys.exit(0 if ok else 1)'
python3 scripts/maas_rest_usage_stats.py --from 2026-05-08 --to 2026-05-21
⚠️ Credential reminder: AK/SK is read from environment variables or a credentials file by the Python script. If you need to configure credentials, see references/cli-installation-guide.md.
Security Design
The security architecture keeps AK/SK exclusively in Python process memory — never in ps -ef, shell variables, environment variables (read-only access), or conversation. Tool separation: Python SDK signing for AK/SK authentication, Python requests for HTTP POST to the MaaS endpoint. Credentials are never printed, never logged, never exported. Temporary credentials add HW_SECURITY_TOKEN as the X-Security-Token header via the SDK signer.
📄 Full details (tool separation table, credential leakage risk elimination, credential lifecycle) → references/security-design.md
References
| Document | Description |
|---|---|
| cli-installation-guide.md | Prerequisites + Python SDK + credentials configuration + Windows GUI env var setup |
| task-query-tokens-usage.md | Task 1: Query tokens usage statistics detailed steps |
| related-apis.md | MaaS ShowStatistics API and parameter details |
| maas-metrics.md | MaaS monitoring metrics reference |
| iam-policies.md | Required IAM permissions |
| verification-method.md | Query result verification method |
| acceptance-criteria.md | Correct/error pattern comparison |
| troubleshooting.md | Common query issues and solutions |
| security-design.md | Security design: tool separation, credential lifecycle |
| maas_rest_usage_stats.py | ShowStatistics API usage statistics script (AK/SK never in ps -ef) |
FAQ
What does the huawei-cloud-maas-tokens-usage skill do?
Query Huawei Cloud MaaS (Model as a Service) tokens usage statistics, including total tokens, prompt tokens, completion tokens, total requests, and total errors. Supports preset service, my service, and custom endpoint with time range queries (last 7/14/30 days or custom). Data source is MaaS ShowStatistics API, consistent with console. Use this skill when the user wants to: (1) query MaaS token consumption statistics, (2) check MaaS service request counts and error rates, (3) analyze token usage for preset service or my service, (4) monitor MaaS usage over a specific time period. Trigger: user mentions "MaaS", "Model as a Service", "tokens usage", "token consumption", "request count", "error count", "MaaS usage", "preset service usage", "completion tokens", "prompt tokens", "MaaS statistics", "模型服务", "令牌用量", "token统计", "token用量", "词元用量", "请求次数", "MaaS监控", "华为云MaaS"
How do I install huawei-cloud-maas-tokens-usage?
Run npx skills add https://github.com/huaweicloud/huaweicloud-skills --skill huawei-cloud-maas-tokens-usage in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/huawei-cloud-maas-tokens-usage/ (personal) or .claude/skills/huawei-cloud-maas-tokens-usage/ (project).
Which AI agents can use huawei-cloud-maas-tokens-usage?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is huawei-cloud-maas-tokens-usage safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains huawei-cloud-maas-tokens-usage?
It is published by huaweicloud in huaweicloud/huaweicloud-skills. It has 195 recorded installs.
More from huaweicloud/huaweicloud-skills
huawei-cloud-terraform-installer
huaweicloud/huaweicloud-skills
Installs Terraform CLI cross-platform with Huawei Cloud mirror support. Use this skill whenever the user mentions installing Terraform, setting up Terraform environment, or when IaC tasks detect missing Terraform. Trigger: install terraform, setup terraform, terraform environment, huaweicloud provider.
huawei-cloud-find-skills
huaweicloud/huaweicloud-skills
Invoke this skill to search, list, query, discover, browse, find and install any Huawei Cloud (华为云) agent skill. Triggers include: "华为云", "华为云有什么skill", "华为云相关skill", "华为云agent skill 市场", "华为云skill类目", "explore Huawei Cloud skills", "show Huawei Cloud skill categories", "does a Huawei Cloud skill exist for...", "which Huawei Cloud skills exist", "搜索华为云技能", "查询华为云skill列表", "有没有管理ECS/OBS/RDS的skill", "帮我找 XX 华为云skill", "介绍 XX Skill 内容", "华为云 XX Skill 具体做什么", "安装华为云Skill".
huawei-cloud-billing-scout
huaweicloud/huaweicloud-skills
Huawei Cloud BSS billing (not AWS/Azure/other clouds; refuses pricing quotes, real-name review, and any non-billing scope): balance, spend, attribution, reconciliation, coupons, stored-value cards, enterprise/partner billing. One-page briefing via hcloud. Use only when the user explicitly mentions 华为云 / Huawei Cloud / BSS and 余额/账单/对账/资源包/代金券/储值卡/企业或伙伴账务; refuses pay, renew, refund, delete.
huawei-cloud-computing-query
huaweicloud/huaweicloud-skills
Queries Huawei Cloud computing resources (ECS/BMS/IMS/AS), Covers ECS instances, flavors, keypairs, quotas, server groups, block devices, NICs, VNC console, BMS bare metal servers/flavors/quotas, IMS images/OS versions/members/quotas, and AS scaling groups/configs/policies/activity logs/lifecycle hooks/warm pools/quotas. No write operations. Use this skill when the user needs to query ECS instance details, list flavors, check BMS availability, browse images, or view auto-scaling group/policy status. Triggers: 弹性云服务器, ECS, 裸金属, BMS, 镜像, IMS, 弹性伸缩, AS, 伸缩组, 伸缩策略, 规格查询, flavor, instance, image, scaling.
huawei-cloud-obs-upload
huaweicloud/huaweicloud-skills
Upload local files or directories to Huawei Cloud OBS (Object Storage Service) buckets, list OBS buckets with capacity and object count, and schedule periodic uploads via crontab. Use this skill when the user wants to: (1) upload a local file or directory to an OBS bucket, (2) list OBS buckets and check their storage capacity and object count, (3) set up a scheduled/periodic upload task to automatically sync a local directory to an OBS bucket. Triggers include: user mentions "OBS", "object storage", "bucket list", "bucket capacity", "upload to OBS", "upload file", "upload directory", "scheduled upload", "periodic upload", "sync to bucket", "对象存储", "桶列表", "桶容量", "上传文件", "上传目录", "定时上传", "OBS管理"
huawei-cloud-terraform-generator
huaweicloud/huaweicloud-skills
Generate Huawei Cloud Terraform configurations and execute deployment with user-guided approval. Use this skill when users want to create Huawei Cloud infrastructure as Terraform, whether they ask explicitly for Terraform or describe goals such as deploying a website, launching an application, or creating network, compute, database, load balancing, or storage resources. Trigger when users mention 创建/create、生成/generate、部署/deploy、配置/configure、使用/use、管理/manage、华为云/Huawei Cloud、Terraform、ECS、VPC、资源/resource、云服务器/ECS、虚拟机/VM、实例/instance、网络/network、负载均衡/ELB、数据库/database、RDS、存储/storage、OBS、桶/bucket、域名/domain、DNS、证书/certificate、SSL、监控/monitoring、日志/log、备份/backup、容器/container、CCE、函数工作流/FunctionGraph
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available