
huawei-cloud-flexus-l-server-ops
Based on Huawei Cloud Flexus L API for instance management and operations. Supports querying instance list and details, querying traffic packages, batch start/stop/reboot instances, resetting passwords, and modifying instance information. Suitable for daily operations, lifecycle management, configuration changes, traffic monitoring, and other scenarios for Flexus L instances. Triggers: Flexus L, Huawei Cloud ops, query instance, start, stop, reboot, reset password, modify info, check traffic, traffic package (中文触发词: L实例运维,查询L实例,L实例开机,L实例关机,L实例重启,L实例重置密码,查询L实例流量包).
- Installs
- 198
- 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-flexus-l-server-ops- 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-flexus-l-server-ops 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.
⚠️ Security Execution Rules (Highest Priority):
- All scripts MUST be executed via skill action=exec, NEVER run directly in shell
- NEVER print script contents or commands containing AK/SK/Token in conversation
- NEVER create temporary script files, prefer inline execution (python -c)
- On execution failure, only return error info, do NOT rewrite scripts or print full commands
- AK/SK/Token MUST be passed via environment variables, NEVER appear in conversation
- ⚠️ ABSOLUTELY NEVER expose, log, or print AK/SK/Token values in any form - this is a critical security requirement
Huawei Cloud Flexus L Instance Operations
Overview
This skill provides complete operational capabilities for Huawei Cloud Flexus L instances, covering instance lifecycle management, configuration modification, monitoring queries, and other core scenarios.
Architecture
OpenClaw Agent → Flexus L Ops Skill → Huawei Cloud SDK → Huawei Cloud Services
│ │ │
│ │ ├─ Flexus L (instance/lifecycle/password)
│ │ └─ BSS (traffic query)
│ │
└─ scripts/ └─ huaweicloudsdk{core,ecs,bss,config}
Core Components:
- Flexus L Service: Elastic Cloud Server, provides instance management, lifecycle control, password reset, etc.
- BSS Service: Business Support System, provides traffic package usage query
- Python SDK: Official Huawei Cloud SDK, encapsulates API call logic
- Operation Scripts: 6 independent scripts, each corresponding to one operation
Applicable Scenarios
Typical Problem Scenarios:
- Instance Status View: Need to quickly view the running status of all Flexus L instances under the account
- Batch Operations: Need to perform start, stop, reboot operations on multiple servers
- Configuration Modification: Need to modify instance name, description, hostname, and other basic information
- Password Management: Need to reset instance login password
- Traffic Monitoring: Need to view traffic package remaining amount and usage
Trigger Keywords:
| English Keyword | Chinese Keyword |
|---|---|
| Flexus L | Flexus L |
| Huawei Cloud Ops | 华为云运维 |
| Query Instance | 查询实例 |
| Start/Stop/Reboot | 开机/关机/重启 |
| Reset Password | 重置密码 |
| Update Info | 修改信息 |
| Query Traffic | 查流量 |
| Traffic Package | 流量包 |
| List All Servers | 查所有服务器 |
| My Servers | 我的服务器有哪些 |
| List All Instances | 列出所有实例 |
Prerequisites
1. Python Environment and dependencies
- Python >= 3.8
- huaweicloudsdkcore >= 3.0.0
- huaweicloudsdkecs >= 3.0.0
- huaweicloudsdkbss >= 3.0.0
- huaweicloudsdkconfig >= 3.0.0
- requests >= 2.31.0
2. Install Huawei Cloud SDK
pip3 install huaweicloudsdkcore huaweicloudsdkecs huaweicloudsdkconfig huaweicloudsdkbss \
-i https://repo.huaweicloud.com/repository/pypi/simple
⚠️ Important: Script Usage Rules
Different operations MUST use the corresponding script. Do NOT use other scripts' commands.
| Operation | Must Use Script | Correct Command | ❌ Wrong Command |
|---|---|---|---|
| Query Flexus L instances | query_instances.py | query_instances.py list | password_unified.py list |
| Query instance details | query_instances.py | query_instances.py detail -i <ID> | lifecycle.py list |
| Start/Stop/Reboot | lifecycle.py | lifecycle.py stop --instance-id <ID> | query_instances.py stop |
| Reset password | password_unified.py | password_unified.py reset --instance-id <ID> --password <pwd> | lifecycle.py reset |
| Modify server info | update_server.py | update_server.py --instance-id <ID> --name <name> | query_instances.py update |
Operation Feedback Requirement
After any lifecycle operation (start/stop/reboot), MUST query and report the final status to user.
Example feedback format:
✅ Operation completed
Instance: your-instance-name
Status: Running
Public IP: <IP>
This ensures the user knows the operation has completed successfully.
Scripts Description
Functional Scripts (4 scripts)
| Script | Function | Commands |
|---|---|---|
| query_instances.py | Instance query tool ⭐ | list, detail, free-resources, traffic, traffic-region |
| lifecycle.py | Lifecycle management | stop, start, reboot |
| password_unified.py | Password reset | test, list, reset |
| update_server.py | Modify server info | --name, --description, --hostname |
Helper Scripts (2 scripts)
| Script | Function |
|---|---|
| auth.py | Authentication management |
| params.py | Parameter processing |
Core Commands
See Execution Flow for operation steps.
Parameters
Required Parameters:
| Operation | Required Parameters | Description |
|---|---|---|
| Query Instance Details | instance-id | Instance ID |
| Start/Stop/Reboot | instance-id | Instance ID (supports multiple) |
| Reset Password | instance-id, password | Instance ID + new password |
| Modify Info | instance-id + (name/description/hostname) | Instance ID + at least one modification |
| Query Traffic by Region | target-region | Target region code |
| Query Traffic by ID | traffic_ids | Traffic package ID list |
Optional Parameters:
| Parameter | Description | Required | Default | Example |
|---|---|---|---|---|
| --region | Target region code (supports Chinese names) | No | cn-north-4 | --region cn-north-4 |
| --ak | Huawei Cloud Access Key AK (can be temporary AK) | No | HW_ACCESS_KEY env var | --ak AXXX... |
| --sk | Huawei Cloud Access Key SK (can be temporary SK) | No | HW_SECRET_KEY env var | --sk SXXX... |
| --security-token | Security token for temporary credentials (required when using temporary AK/SK) | No | HW_SECURITY_TOKEN env var | --security-token XXXX... |
Region Parameter Support:
- Region code:
cn-north-4 - Full name:
North-China-Beijing4 - Short name:
Beijing4,Guangzhou,Shanghai
Execution Flow
Step 1: Check Existing Credentials (Automatic)
Get credentials from environment variables first, automatic check, no need to ask user.
Decision Logic:
| Credential Status | Next Step |
|---|---|
| ✅ HW_ACCESS_KEY + HW_SECRET_KEY + HW_SECURITY_TOKEN exist | Execute script directly (Recommended: Temporary AK/SK authentication, higher security level, pass --ak --sk --security-token parameters) |
| ✅ HW_ACCESS_KEY + HW_SECRET_KEY exist (no Token) | Execute script directly (Permanent AK/SK authentication, pass --ak --sk parameters) |
| ❌ Environment variables not found | Prompt user to configure credentials (prefer environment variables, do NOT ask directly) |
| ❌ Authentication failed | Prompt user to check or reconfigure credentials (prefer environment variables, do NOT ask directly) |
⚠️ Security Recommendations:
- Prefer temporary credentials: Strongly recommend using temporary AK/SK + Security Token method for higher security, credentials expire automatically
- Environment variable configuration: Credentials should be configured via environment variables (HW_ACCESS_KEY, HW_SECRET_KEY, HW_SECURITY_TOKEN)
- Sensitive information protection: AK/SK are sensitive information, do NOT input or disclose in conversation
Credential Missing or Authentication Failed Message:
❌ Credentials not configured or authentication failed
Please configure Huawei Cloud credentials. For security, we recommend using temporary AK/SK + Security Token method via environment variables:
- HW_ACCESS_KEY: Access Key AK
- HW_SECRET_KEY: Secret Key SK
- HW_SECURITY_TOKEN: Security Token (Recommended)
⚠️ Security Note: Temporary credentials are more secure, please prefer using them!
Note: We prioritize obtaining credentials from environment variables and NEVER ask users to input AK/SK directly. However, we still support parsing credentials if user voluntarily provides them via other methods (e.g., conversation input, config file).
Step 2: Select Operation
After credentials are verified, ask user what operation to perform:
Step 3: Execute Operation
⚠️ Instance Validation (When user provides instance ID/name):
python3 {baseDir}/scripts/query_instances.py free-resources --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
- ✅ Found in list → Proceed with operation
- ❌ Not found → Tell user: "This is NOT a Flexus L instance. This skill only supports Flexus L instances." Then refer to Finding Server ID section for guidance.
⚠️ Important Notes:
1. Instance Type Confirmation: Before executing any operation, remind user that this skill only supports Flexus L instances
2. Server ID Guidance: If user hasn't specified a server ID to operate on, guide user to query all instances or specific server
4.1 List Instances
Query all instances across regions:
python3 {baseDir}/scripts/query_instances.py list --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
Query instances in specific region:
python3 {baseDir}/scripts/query_instances.py list --region cn-north-4 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
4.2 Query Instance Details
Required Parameters:
- Instance ID (required)
- Region code (optional, default cn-north-4)
python3 {baseDir}/scripts/query_instances.py detail --instance-id <ID> --region cn-north-4 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
⚠️ Error Handling: If query fails with "server not found" and user didn't specify region, tell user to check region, instance type, and ID.
4.3 Batch Start
Required Parameters:
- Instance ID (required, supports multiple)
- Region code (optional, default cn-north-4)
python3 {baseDir}/scripts/lifecycle.py start --instance-id <ID1> --instance-id <ID2> --region cn-north-4 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
4.4 Batch Stop
⚠️ Dangerous Operation: Must Confirm Twice
🔒 Instance Type Restriction: This operation ONLY supports Flexus L instances, NOT all ECS instances. Must verify instance type before execution.
Required Parameters:
- Instance ID (required, supports multiple)
- Region code (optional, default cn-north-4)
Must confirm twice before execution:
- Tell user the consequences of stopping (service interruption, data loss risk)
- If stopping the server currently running OpenClaw, must warn additionally (conversation interruption, need manual restart)
- Only execute after user replies "confirm stop"
python3 {baseDir}/scripts/lifecycle.py stop --instance-id <ID1> --instance-id <ID2> --region cn-north-4 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
4.5 Batch Reboot
⚠️ Dangerous Operation: Must Confirm Twice
🔒 Instance Type Restriction: This operation ONLY supports Flexus L instances, NOT all ECS instances. Must verify instance type before execution.
Required Parameters:
- Instance ID (required, supports multiple)
- Region code (optional, default cn-north-4)
- Reboot type (optional): SOFT (normal reboot, default) or HARD (forced reboot)
Must confirm twice before execution:
- Tell user the consequences of rebooting (brief service interruption, memory data loss)
- If rebooting the server currently running OpenClaw, must warn additionally (brief conversation interruption, auto recovery)
- Only execute after user replies "confirm reboot"
python3 {baseDir}/scripts/lifecycle.py reboot --instance-id <ID1> --instance-id <ID2> --region cn-north-4 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
4.6 Reset Password
Required Parameters:
- Instance ID (required)
- New password (required)
- Length 8-26 characters
- Must contain at least 3 of: uppercase, lowercase, numbers, special characters
- Cannot contain username or reversed username
- Cannot contain 3 or more consecutive identical characters
- Region code (optional, default cn-north-4)
⚠️ Important: After resetting password, the instance MUST be rebooted for the new password to take effect.
Must confirm with user before reboot:
- Inform user that password reset is successful
- Warn user about consequences: brief service interruption, memory data loss
- If rebooting the server currently running OpenClaw, must warn additionally (brief conversation interruption, auto recovery)
- Only execute reboot after user replies "confirm reboot"
python3 {baseDir}/scripts/password_unified.py reset --instance-id <ID> --password <new_password> --region cn-north-4 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
Reboot Command:
python3 {baseDir}/scripts/lifecycle.py reboot --instance-id <ID> --region cn-north-4 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
4.7 Modify Instance Information
Required Parameters:
- Instance ID (required)
- Region code (optional, default cn-north-4)
- Modification parameters (at least one):
- name: Instance name (1-64 characters, supports Chinese, letters, numbers, _-, .)
- description: Description (0-85 characters, cannot contain <>)
- hostname: Hostname (1-64 characters)
python3 {baseDir}/scripts/update_server.py --instance-id <ID> --name "new_name" --region cn-north-4 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
4.8 Query Traffic Package
Option 1: Query by Traffic Package ID
Required Parameters:
- Traffic package ID (required)
⚠️ Special Note: Traffic package query uses Beijing-1 region (cn-north-1) by default, traffic package ID can be from any region
python3 {baseDir}/scripts/query_instances.py traffic <traffic_id_1> <traffic_id_2> --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
Option 2: Query by Region ⭐ Recommended
Required Parameters:
- Target region (required)
python3 {baseDir}/scripts/query_instances.py traffic-region --target-region cn-east-3 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
Finding Server ID
If user asks "how to find server ID" or "don't know server ID", first provide console lookup steps:
You can find server ID through the following ways:
Option 1: Via Huawei Cloud Console
1. Login to Huawei Cloud Console
2. Go to Flexus Application Server L instance list
3. Click instance name to enter details page
4. In basic information, click "Cloud Host VM"
5. View cloud host ID in cloud host information
6. Click copy button after ID to quickly copy
Help Document: https://support.huaweicloud.com/intl/zh-cn/flexusl_faq/faq_01_0003.html
Then append the following, offer automatic query option:
Option 2: I can also help query all servers under your account
Would you like me to list all instances under your account? I can query directly for you.
If user agrees, execute list all instances:
python3 {baseDir}/scripts/query_instances.py list --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
Region Support
Common Region Codes
| Region Code | Region Name |
|---|---|
| cn-north-4 | North China-Beijing 4 |
| cn-north-1 | North China-Beijing 1 |
| cn-south-1 | South China-Guangzhou |
| cn-east-3 | East China-Shanghai 1 |
| ap-southeast-1 | China-Hong Kong |
| ap-southeast-2 | Asia Pacific-Singapore |
Region Name Conversion
This skill supports automatic region name conversion, can use Chinese names or English codes:
# Use region code
python3 {baseDir}/scripts/query_instances.py list --region cn-north-4 --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
# Use region name (auto-convert)
python3 {baseDir}/scripts/query_instances.py list --region "North-China-Beijing4" --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
python3 {baseDir}/scripts/query_instances.py list --region "Beijing4" --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
python3 {baseDir}/scripts/query_instances.py list --region "Guangzhou" --ak "$HW_ACCESS_KEY" --sk "$HW_SECRET_KEY" [--security-token "$HW_SECURITY_TOKEN"]
Traffic Package Query Special Note
⚠️ Traffic package query uses Beijing-1 region (cn-north-1) by default
- Traffic package query does not support --region parameter
- Traffic package ID can be from any region
- Automatically uses Beijing-1 region for query
Notes
- Instance ID is the cloud host ID corresponding to Flexus L instance
- Region defaults to cn-north-4 (Beijing 4)
- AK/SK Security Requirements:
- ✅ Must be stored via environment variables (HW_ACCESS_KEY, HW_SECRET_KEY, HW_SECURITY_TOKEN)
- ❌ Do not store in any configuration files
- Stop/Reboot Security Requirements:
- ✅ Must confirm twice - No direct execution without user confirmation
- ✅ Must be Flexus L instances only - Cannot operate on all ECS instances, must verify instance type
- ✅ Must inform operation consequences
- ✅ If current server, must give additional warning
- ❌ Never execute batch operations on all ECS instances - Only Flexus L instances are supported
References
Skill Reference Documents
This skill includes the following reference documents:
- IAM Policies - Detailed IAM permission configuration
- Verification Method - Skill verification method
Huawei Cloud Official Documentation
FAQ
What does the huawei-cloud-flexus-l-server-ops skill do?
Based on Huawei Cloud Flexus L API for instance management and operations. Supports querying instance list and details, querying traffic packages, batch start/stop/reboot instances, resetting passwords, and modifying instance information. Suitable for daily operations, lifecycle management, configuration changes, traffic monitoring, and other scenarios for Flexus L instances. Triggers: Flexus L, Huawei Cloud ops, query instance, start, stop, reboot, reset password, modify info, check traffic, traffic package (中文触发词: L实例运维,查询L实例,L实例开机,L实例关机,L实例重启,L实例重置密码,查询L实例流量包).
How do I install huawei-cloud-flexus-l-server-ops?
Run npx skills add https://github.com/huaweicloud/huaweicloud-skills --skill huawei-cloud-flexus-l-server-ops 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-flexus-l-server-ops/ (personal) or .claude/skills/huawei-cloud-flexus-l-server-ops/ (project).
Which AI agents can use huawei-cloud-flexus-l-server-ops?
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-flexus-l-server-ops 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-flexus-l-server-ops?
It is published by huaweicloud in huaweicloud/huaweicloud-skills. It has 198 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 backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.