volcengine-sdk-generator
Generate complete, runnable Volcengine SDK code and provide SDK configuration guidance. Supports Go, Python, PHP, Java, and Node.js. Trigger this skill whenever the user wants to call a Volcengine API, generate Volcengine SDK code, or describes a cloud operation on Volcengine (e.g., "list ECS instances", "create a VPC on Volcengine", "query Volcengine billing with Python"). Also trigger when the user asks about Volcengine SDK configuration and best practices — including retry, timeout, authentication (AK/SK, STS, AssumeRole), proxy, connection pooling, SSL, debug mode, and error handling (e.g., "how to configure retry for Volcengine Go SDK", "volcengine python sdk proxy setup"). Trigger when the user mentions Volcengine service names such as ECS, VPC, CDN, CLB, RDS, Redis, Kafka, billing, IAM, DNS with code generation or SDK usage intent. When the user only needs API specification queries (parameters, error codes, response structures), hand off to the volcengine-api skill. When the user needs CLI-based operations, hand off to the volcengine-cli skill. Supports both Chinese and English prompts.
What this skill does
# Volcengine SDK Code Generator
Generate complete, runnable Volcengine SDK code from natural-language descriptions, and answer SDK configuration questions.
## Workflow
When a user describes a Volcengine API operation, follow these steps:
### Step 1: Identify Target Service, Operation, and Advanced Configuration Needs
Parse the user's description to determine:
- **Target service**: which Volcengine service (e.g., ECS, VPC, TOS, billing)
- **Target operation**: what operation to perform (e.g., list instances, create a VPC, query billing)
- **Target language**: which programming language (Go, Python, PHP, Java, Node.js). If not specified, ask the user.
- **Advanced configuration needs**: whether the user mentions or the scenario implies any of the following:
- **Retry**: user mentions "retry", "fault tolerance", or the operation is a write/create type (prone to throttling)
- **Timeout**: user mentions "timeout", or the operation involves large data volumes (batch queries, file uploads)
- **Credentials**: user mentions "STS", "AssumeRole", "temporary credentials", "OIDC", or explicitly wants to avoid hardcoding AK/SK
- **Proxy/network**: user mentions "proxy" or "internal network"
- **Debug mode**: user mentions "debug" or "logging"
- **Connection pooling**: user mentions "connection pool", "high concurrency", or "pool"
If the user explicitly requests these, include the corresponding configuration in the generated code. If not explicitly requested but implied by the scenario (e.g., resource creation naturally warrants retry), include suggested configuration as comments.
### Step 2: Query Service Metadata via Volcengine API Explorer
Use the following APIs to find the correct service code, version, and action name. This step is critical because guessing often produces incorrect code — the API Explorer is the authoritative source.
**2a. Find the ServiceCode**
Fetch the service catalog:
```
GET https://api.volcengine.com/api/common/explorer/services
```
Response structure:
```json
{
"Result": {
"Categories": [
{
"CategoryName": "...",
"Services": [
{
"ServiceCn": "Cloud Server",
"ServiceCode": "ecs",
"Product": "ECS",
"IsSdkAvailable": true,
"RegionType": "regional"
}
]
}
]
}
}
```
Match the user's intent to the correct `ServiceCode` based on `ServiceCn`, `Product`, and category name.
**2b. Find the API version**
```
GET https://api.volcengine.com/api/common/explorer/versions?ServiceCode={ServiceCode}
```
Response:
```json
{
"Result": {
"Versions": [
{
"ServiceCode": "billing",
"Version": "2022-01-01",
"IsDefault": 0
}
]
}
}
```
Use the version with `IsDefault == 1`. If no default version exists, use the latest available.
**2c. Find the Action name**
```
GET https://api.volcengine.com/api/common/explorer/apis?ServiceCode={ServiceCode}&Version={Version}&APIVersion={Version}
```
Response:
```json
{
"Result": {
"Groups": [
{
"Name": "Instance",
"Apis": [
{
"Action": "DescribeInstances",
"NameCn": "Query instance list",
"Description": "..."
}
]
}
]
}
}
```
Match user intent using the `Action` name and `NameCn` (Chinese name).
**2c-alt: Search API (when direct lookup fails)**
If the service catalog or API list cannot clearly match the user's description — for example, the user uses vague terms, Chinese names that don't map directly to a ServiceCode, or the API list doesn't seem to contain what the user wants — use the search API as a fallback:
```
GET https://api.volcengine.com/api/common/search/all?Query={URL-encoded search term}&Channel=api&Limit=10
```
Search terms can be Chinese or English — use whichever best matches the user's description.
Response structure:
```json
{
"Result": {
"List": [
{
"BizInfo": {
"Action": "ListProjects",
"ServiceCn": "Access Control",
"ServiceCode": "iam",
"Version": "2021-08-01"
},
"Highlight": [
{"Field": "title", "Summary": "Get <em>project</em> <em>list</em>"}
]
}
],
"Total": 200
}
}
```
Select the best match based on `ServiceCn`, `Action`, and highlight text, then continue to step 2d.
The search API is particularly useful when:
- The user describes the operation in natural language but doesn't know which service owns it
- A service has too many APIs to browse manually
- The description spans multiple services (search returns results across all services)
**2d. Get full API parameter details**
```
GET https://api.volcengine.com/api/common/explorer/api-swagger?ServiceCode={ServiceCode}&Version={Version}&APIVersion={Version}&ActionName={Action}
```
Returns the full Swagger/OpenAPI specification, including:
- HTTP method (GET/POST)
- All request parameters with types, required flags, and descriptions
- Response structure
- Constraints and validation rules
- **`x-demo` field**: contains `requestDemo` and `responseDemo` with official examples
Read this specification carefully — it is essential for generating accurate code.
**2e. Extract parameter example values (from x-demo requestDemo)**
The `info.x-demo` array in the Swagger response contains `requestDemo` — official request examples. Extract realistic parameter values from these to populate generated code.
Extraction process:
1. Locate `info.x-demo[0].requestDemo` and parse the request body JSON
2. Use requestDemo values as example values in generated code — they are more accurate and realistic than invented values
3. For masked values (e.g., `cc5silum********`), keep the masked format and add a comment prompting the user to replace with real values
4. If a parameter value is a JSON string (e.g., a `Config` field), format it clearly and comment each sub-field
Example: for VKE CreateAddon, requestDemo contains:
```json
{
"ClusterId": "cc5silum********",
"Name": "ingress-nginx",
"DeployMode": "Unmanaged",
"DeployNodeType": ["VirtualNode"],
"Config": "{\"Replica\":1,\"Resource\":{\"Request\":{\"Cpu\":\"0.25\",\"Memory\":\"512Mi\"},\"Limit\":{\"Cpu\":\"0.5\",\"Memory\":\"1024Mi\"}},\"PrivateNetwork\":{\"SubnetId\":\"subnet-2d61qn69iji****\",\"IpVersion\":\"IPV4\"}}"
}
```
Use these example values directly instead of empty placeholders.
**2f. Retrieve detailed configuration for complex parameters**
Some parameter `description` fields contain documentation links (e.g., `https://www.volcengine.com/docs/...`) pointing to detailed configuration guides. For complex parameters, fetch these links for more information:
When to consult documentation:
- The parameter value is a JSON string with a "see detailed configuration" reference in the description (e.g., VKE `Config`)
- The parameter is a nested structure whose sub-field format is documented externally
- The `enum` values have unclear meanings that are explained in the documentation
Processing flow:
1. Check whether the parameter `description` contains a `volcengine.com/docs` link
2. If so, use WebFetch to retrieve the linked page and extract configuration details relevant to the parameter
3. Incorporate documentation examples into the generated code as comments or structured parameters
4. If the documentation is inaccessible, fall back to requestDemo example values
**2g. Determine required and recommended parameters**
Required-field detection relies on multiple sources, not just the `required` array:
1. **Explicitly required**: listed in the Swagger `required` array
2. **Implied by description**: the description contains phrases like "must specify", "required", or equivalent
3. **Logically required**: semantically essential even if not formally marked (e.g., instance type and network config when creating resources)
4. **Conditionally required**: the description states "required when XRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.