volcengine-api
Query and answer questions about Volcengine API specifications. Trigger this skill whenever a user asks about Volcengine API parameters, error codes, request methods, enum values, required fields, response structures, pagination, parameter dependencies, or API comparisons — even if they don't explicitly say "API". Typical triggers include questions like "What parameters does DescribeInstances have?", "What values does Status support?", "What does InvalidInstanceId.NotFound mean?", "Does Volcengine have a batch tag deletion API?", "Which APIs does ECS support?", "How do I pass parameters to CreateDatabase?", "Is ChargeType required?", "What fields does DescribeInstances return?", "How do I paginate instance lists?", "What's the difference between these two APIs?", "RunInstances returns InvalidParameterValue". When the user needs runnable SDK code, hand off to the volcengine-sdk-generator 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 API Query Assistant
Answer user questions about Volcengine APIs by querying the API Explorer for authoritative, up-to-date information.
## Applicable Scenarios
| Scenario | Example Questions |
|----------|-------------------|
| Find an API | "How do I list ECS instances?", "Is there a batch tag creation API?" |
| Query parameters | "What are the required params for RunInstances?", "What values does ChargeType accept?" |
| Response structure | "What fields does DescribeInstances return?", "What statuses can Status have?" |
| Parameter dependencies | "If I set Ipv6Isp, how should I fill Ipv6MaskLen?", "When is SpotPriceLimit required?" |
| Pagination | "How do I paginate instance queries?", "How does NextToken work?" |
| Error codes | "What does InvalidInstanceId.NotFound mean?", "CreateVpc returns QuotaExceeded" |
| Browse services | "Which APIs does ECS have?", "What operations does VPC support?" |
| API comparison | "What's the difference between DescribeInstances and DescribeInstancesByIds?" |
## Workflow
### Step 1: Understand User Intent
Determine what the user is looking for:
| Intent | Signal | Query Path |
|--------|--------|------------|
| **Find an API** | Describes an operation but doesn't know the API name | Search (2e) or Services (2a) -> API list (2c) -> Details (2d) |
| **Query parameters** | Knows the API name, asks about params/enums/required fields | Go directly to Details (2d) |
| **Query response** | Asks about return fields or status values | Go directly to Details (2d), focus on response schema |
| **Query parameter dependencies** | Asks "when is X required?" or "how does X relate to Y?" | Go directly to Details (2d), focus on conditional rules in descriptions |
| **Query error codes** | Provides an error code or error message | Error code handling (Step 3) |
| **Browse a service** | Asks what capabilities a service offers | Services (2a) -> API list (2c) |
| **Compare APIs** | Asks about differences between two APIs | Query Details (2d) for each, compare params and functionality |
### Step 2: Query API Information Progressively
Start from the appropriate sub-step based on what is already known. When the user describes a requirement in natural language, Search (2e) is often faster than browsing level by level.
#### 2a. Query service list (when the service is unknown)
```
GET https://api.volcengine.com/api/common/explorer/services
```
Each service in the response contains:
- `ServiceCode`: service identifier (e.g., `ecs`, `vpc`)
- `ServiceCn`: Chinese name (e.g., "cloud server", "virtual private cloud")
- `Product`: product identifier (e.g., `ECS`, `VPC`)
- `RegionType`: `regional` or `global`
Match the most appropriate `ServiceCode` based on the user's description.
#### 2b. Query version list (when the version is unknown)
```
GET https://api.volcengine.com/api/common/explorer/versions?ServiceCode={ServiceCode}
```
Each version contains:
- `Version`: version string (e.g., `2020-04-01`)
- `IsDefault`: `1` indicates the default version
Prefer the version with `IsDefault=1`. If none is marked default, use the latest version.
#### 2c. Query API list (when the specific API is unknown)
```
GET https://api.volcengine.com/api/common/explorer/apis?ServiceCode={ServiceCode}&Version={Version}&APIVersion={Version}
```
The response groups APIs by category. Each API contains:
- `Action`: API name (e.g., `DescribeInstances`)
- `NameCn`: Chinese name (e.g., "Query instance list")
- `ApiGroup`: group name (e.g., "Instance", "Image")
- `Description`: functional description
- `UsageScenario`: usage scenarios
- `Attentions`: constraints and caveats
Match user intent using `Action`, `NameCn`, and `Description`.
#### 2d. Query API details (core step)
```
GET https://api.volcengine.com/api/common/explorer/api-swagger?ServiceCode={ServiceCode}&Version={Version}&APIVersion={Version}&ActionName={ActionName}
```
Returns the full Swagger/OpenAPI specification for the API. Extract key information as follows.
##### HTTP Method
The key under `paths["/{ActionName}"]` (`get` or `post`) indicates the HTTP method.
##### Request Parameters
Parameter location depends on the HTTP method:
**GET requests:** parameters are in `paths["/{ActionName}"].get.parameters`. Each parameter includes:
- `name`: parameter name
- `required`: whether it is required
- `schema.type`: data type
- `schema.description`: parameter description (often contains enum values, conditional rules, and value ranges)
- `schema.enum`: allowed values (if any)
- `schema.default`: default value (if any)
- `schema.example`: example value (if any)
Arrays and nested objects in GET parameters use naming conventions:
- Arrays: `ParamName.N` (N starts from 1), e.g., `InstanceIds.1`, `InstanceIds.2`
- Nested objects: `Parent.Child`, e.g., `TagFilters.N.Key`, `TagFilters.N.Values.N`
**POST requests:** parameters are in `paths["/{ActionName}"].post.requestBody.content["application/json"].schema`, using JSON Schema:
- `properties`: parameter definitions, keyed by name
- `required`: array of required parameter names
POST parameters often have nested structures that require recursive parsing:
- `type: object` -> inspect `properties` for child parameters
- `type: array` -> inspect `items` for element structure
- `$ref: "#/components/schemas/XxxObject"` -> look up the definition in `components.schemas` and expand recursively
Present nested parameters in a tree structure:
```
- InstanceId (string, required): instance ID
- DatabasePrivileges (array, optional): database privilege list
- AccountName (string, required): account name
- AccountPrivilege (string, required): privilege type — enum: ReadWrite, ReadOnly, ...
- AccountPrivilegeDetail (string, optional): privilege detail, comma-separated
```
##### Parameter Dependencies
Many parameters have conditional dependencies, typically described in the `description` field. Watch for:
- **Conditionally required**: e.g., "required when `EnableIpv6` is true"
- **Mutually exclusive**: e.g., "when `Ipv6CidrBlock` is specified, `Ipv6MaskLen` is ignored"
- **Value constraints**: e.g., "when `Ipv6Isp` is BGP, only 56 is supported"
- **Prerequisites**: e.g., "`TagFilters.N.Values.N` requires `TagFilters.N.Key` to be set first"
Highlight these dependencies in the answer to help users avoid misconfiguration.
##### Pagination Parameters
Volcengine APIs use two common pagination patterns, identifiable from the Swagger parameters:
- **Token-based**: uses `MaxResults` (page size) + `NextToken` (continuation token). The response includes `NextToken`; an empty value means the last page.
- **Offset-based**: uses `PageSize` + `PageNumber` (or `Offset`/`Limit`). The response includes `TotalCount`.
Specify which pagination pattern the API uses, along with default values and upper limits.
##### Response Structure
The response schema is defined at `paths["/{ActionName}"].{method}.responses["200"].content["application/json"].schema`, and may reference `components.schemas` via `$ref`.
Key response information:
- Field names, types, and descriptions
- Enum fields and their possible values (e.g., `Status`: RUNNING / STOPPED / CREATING)
- Nested object structures (e.g., fields within each item in an `Instances` array)
The `info.x-demo` section also provides useful reference — `responseDemo[0].Code` shows the complete response structure with example values.
##### Request/Response Examples
In the `info.x-demo` array:
- `requestDemo[0].Code`: request example (shows how parameters are filled)
- `responseDemo[0].Code`: response example (shows the full return structure with sample values)
These are official examples and highly valuable. Proactively include them in the answer.
##### Associated Error Codes
In `paths["/{ActionName}"].{method}.responses["x-error-code"].content["application/json"].schema.oneOf`, each error code contains:
- `code`: error code identifier (e.g., `InvalidInstanceId.NotFound`)
- `http_code`: HTTP status code (e.g.Related 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.