Skip to main content
Version: 3.10.x

AI Agent Skills for API7 Gateway

Agent skills for API7 Gateway are SKILL.md knowledge packs that teach an AI coding agent — such as Claude Code, Cursor, or GitHub Copilot — how to configure and operate a live API7 Enterprise Edition gateway. Each skill covers one plugin, recipe, or operator workflow, with the exact commands to run. Install them once, then describe the outcome you want:

"Add key-auth to my /orders route and rate-limit it to 100 requests per minute."

The agent loads the matching skills and runs the real a7 CLI commands against your API7 Enterprise Edition control plane and Admin API.

note

The skills below use a7, the command-line tool for API7 Enterprise Edition, maintained in the api7/a7 repository. a7 wraps the API7 EE control-plane API and the APISIX Admin API; all runtime operations are scoped to a gateway group.

The SKILL.md format is understood by any agent that supports the Agent Skills convention — including Claude Code, Cursor, GitHub Copilot, Windsurf, and OpenCode.

Browse the skills

Personav1.0.0

a7-persona-developer

Persona skill for API developers building and testing APIs on API7 Enterprise Edition (API7 EE) using the a7 CLI. Provides decision frameworks for service-backed API design, route configuration, plugin configuration, and local-to-cloud development workflows.

Personav1.0.0

a7-persona-operator

Persona skill for platform operators and DevOps engineers managing API7 Enterprise Edition (API7 EE) instances using the a7 CLI. Provides decision frameworks for managing Gateway Groups, Enterprise RBAC, complex deployments, troubleshooting, and disaster recovery.

Pluginv1.0.0

a7-plugin-ai-content-moderation

Skill for configuring API7 Enterprise Edition AI content moderation plugins via the a7 CLI. Covers both ai-aws-content-moderation (AWS Comprehend, request-only) and ai-aliyun-content-moderation (Aliyun, request + response with streaming), toxicity thresholds, category filtering, and integration with ai-proxy.

Pluginv1.0.0

a7-plugin-ai-prompt-decorator

Skill for configuring the API7 Enterprise Edition ai-prompt-decorator plugin via the a7 CLI. Covers prepending and appending system/user/assistant messages to LLM requests, setting conversation context, and enforcing safety guidelines.

Pluginv1.0.0

a7-plugin-ai-prompt-template

Skill for configuring the API7 Enterprise Edition ai-prompt-template plugin via the a7 CLI. Covers defining reusable prompt templates with variable placeholders, enforcing prompt structure, and combining with ai-proxy for a complete AI gateway pipeline.

Pluginv1.0.0

a7-plugin-ai-proxy

Skill for configuring the API7 Enterprise Edition ai-proxy plugin via the a7 CLI. Covers proxying requests to LLM providers (OpenAI, Azure OpenAI, DeepSeek, Anthropic, Gemini, Vertex AI, and more), authentication per provider, model configuration, streaming, logging, and route/service usage.

Pluginv1.0.0

a7-plugin-basic-auth

Skill for configuring the API7 Enterprise Edition (API7 EE) basic-auth plugin via the a7 CLI. Covers HTTP Basic Authentication setup on routes, consumer credential binding with username/password, hide_credentials, anonymous consumer fallback, and common operational patterns.

Pluginv1.0.0

a7-plugin-consumer-restriction

Skill for configuring the API7 Enterprise Edition consumer-restriction plugin via the a7 CLI. Covers restricting access by consumer name, service ID, or route ID using whitelist/blacklist modes and per-consumer HTTP method restrictions.

Pluginv1.0.0

a7-plugin-cors

Skill for configuring the API7 Enterprise Edition (API7 EE) cors plugin via the a7 CLI. Covers Cross-Origin Resource Sharing setup on routes, allow_origins, allow_methods, allow_headers, credentials handling, regex origin matching, preflight caching, and common operational patterns.

Pluginv1.0.0

a7-plugin-datadog

Skill for configuring the API7 Enterprise Edition datadog plugin via the a7 CLI. Covers pushing custom metrics to Datadog via DogStatsD, metric tags, batching, plugin metadata for global DogStatsD server config, and Datadog Agent integration.

Pluginv1.0.0

a7-plugin-ext-plugin

Skill for configuring the API7 Enterprise Edition external plugin system (ext-plugin-pre-req, ext-plugin-post-req, ext-plugin-post-resp) via the a7 CLI. Covers Plugin Runner architecture, configuration for Go/Java/Python runners, RPC protocol, graceful degradation, and performance considerations.

Pluginv1.0.0

a7-plugin-fault-injection

Skill for configuring the API7 Enterprise Edition fault-injection plugin via the a7 CLI. Covers injecting delays and HTTP aborts for chaos engineering, percentage-based sampling, conditional injection via vars expressions, custom response headers and body with Nginx variable interpolation.

Pluginv1.0.0

a7-plugin-grpc-transcode

Skill for configuring the API7 Enterprise Edition (API7 EE) grpc-transcode plugin via the a7 CLI. Covers converting RESTful HTTP requests to gRPC, proto file management, pb_option settings for data type conversion, error detail decoding, and gateway group scoping.

Pluginv1.0.0

a7-plugin-hmac-auth

Skill for configuring the API7 Enterprise Edition (API7 EE) hmac-auth plugin via the a7 CLI. Covers HMAC signature authentication, consumer credential binding with key_id/secret_key, allowed algorithms, clock skew handling, request body validation, signed headers, and common operational patterns.

Pluginv1.0.0

a7-plugin-http-logger

Skill for configuring the API7 Enterprise Edition (API7 EE) http-logger plugin via the a7 CLI. Covers pushing access logs to HTTP/HTTPS endpoints in batches, custom log formats, and gateway group scoping.

Pluginv1.0.0

a7-plugin-ip-restriction

Skill for configuring the API7 Enterprise Edition (API7 EE) ip-restriction plugin via the a7 CLI. Covers IP whitelist/blacklist setup on routes, CIDR range support, IPv4/IPv6, real client IP extraction behind proxies, custom error messages, and common operational patterns.

Pluginv1.0.0

a7-plugin-jwt-auth

Skill for configuring the API7 Enterprise Edition (API7 EE) jwt-auth plugin via the a7 CLI. Covers JWT token authentication, HS256/RS256 algorithm selection, consumer credential binding, token lookup from header/query/cookie, claims handling, clock skew, secret management, and common operational patterns.

Pluginv1.0.0

a7-plugin-kafka-logger

Skill for configuring the API7 Enterprise Edition (API7 EE) kafka-logger plugin via the a7 CLI. Covers pushing access logs to Apache Kafka topics, broker configuration, SASL authentication, and gateway group scoping.

Pluginv1.0.0

a7-plugin-key-auth

Skill for configuring the API7 Enterprise Edition (API7 EE) key-auth plugin via the a7 CLI. Covers API key authentication setup on routes, consumer credential binding, key lookup from header/query/cookie, hide_credentials, anonymous consumer fallback, and common operational patterns.

Pluginv1.0.0

a7-plugin-limit-count

Skill for configuring the API7 Enterprise Edition (API7 EE) limit-count plugin via the a7 CLI. Covers fixed-window rate limiting, count/time_window configuration, key types, Redis and Redis-cluster policies for distributed limiting, group-based shared quotas, consumer-level vs route-level limiting, response headers, and common operational patterns.

Pluginv1.0.0

a7-plugin-limit-req

Skill for configuring the API7 Enterprise Edition (API7 EE) limit-req plugin via the a7 CLI. Covers leaky-bucket rate limiting, rate/burst configuration, nodelay behavior, key types, Redis policies for distributed limiting, traffic smoothing, and common operational patterns including combination with limit-count.

Pluginv1.0.0

a7-plugin-openid-connect

Skill for configuring the API7 Enterprise Edition (API7 EE) openid-connect plugin via the a7 CLI. Covers OIDC authorization code flow, bearer token validation, token introspection vs JWKS verification, session management, provider setup for Keycloak/Auth0/Okta, redirect URIs, and common operational patterns.

Pluginv1.0.0

a7-plugin-prometheus

Skill for configuring the API7 Enterprise Edition (API7 EE) prometheus plugin via the a7 CLI. Covers enabling Prometheus metrics export on routes and globally, exposed metrics (HTTP status, latency, bandwidth, upstream health), and gateway group scoping.

Pluginv1.0.0

a7-plugin-proxy-rewrite

Skill for configuring the API7 Enterprise Edition (API7 EE) proxy-rewrite plugin via the a7 CLI. Covers rewriting request URI, host, method, headers, and scheme before forwarding to upstream. Includes regex URI rewriting, header manipulation, and gateway group scoping.

Pluginv1.0.0

a7-plugin-redirect

Skill for configuring the API7 Enterprise Edition (API7 EE) redirect plugin via the a7 CLI. Covers URI redirects, HTTP-to-HTTPS redirection, regex-based URI rewriting, query string handling, and gateway group scoping.

Pluginv1.0.0

a7-plugin-response-rewrite

Skill for configuring the API7 Enterprise Edition (API7 EE) response-rewrite plugin via the a7 CLI. Covers rewriting response status codes, headers, and body before returning to clients. Includes conditional execution with vars, regex body filters, and gateway group scoping.

Pluginv1.0.0

a7-plugin-serverless

Skill for configuring the API7 Enterprise Edition serverless-pre-function and serverless-post-function plugins via the a7 CLI. Covers inline Lua function execution in configurable request phases, function signature, closure patterns, available Lua APIs, and execution ordering.

Pluginv1.0.0

a7-plugin-skywalking

Skill for configuring the API7 Enterprise Edition (API7 EE) skywalking plugin via the a7 CLI. Covers distributed tracing with Apache SkyWalking OAP, sampling configuration, service topology, and gateway group scoping.

Pluginv1.0.0

a7-plugin-traffic-split

Skill for configuring the API7 Enterprise Edition (API7 EE) traffic-split plugin via the a7 CLI. Covers weighted traffic splitting between upstreams with conditional match rules. Includes canary release, blue-green deployment, A/B testing patterns, and gateway group scoping.

Pluginv1.0.0

a7-plugin-wolf-rbac

Skill for configuring the API7 Enterprise Edition (API7 EE) wolf-rbac plugin via the a7 CLI. Covers integration with the Wolf RBAC server for role-based access control, token management, login/user-info/change-password API endpoints, permission checking flow, and multi-application setup.

Pluginv1.0.0

a7-plugin-zipkin

Skill for configuring the API7 Enterprise Edition (API7 EE) zipkin plugin via the a7 CLI. Covers distributed tracing with Zipkin, Jaeger, or any Zipkin-compatible collector, B3 propagation headers, sampling, and gateway group scoping.

Recipev1.0.0

a7-recipe-api-versioning

Recipe skill for implementing API versioning strategies using API7 Enterprise Edition (API7 EE) and the a7 CLI. Covers URI path versioning, header-based versioning, traffic splitting for gradual migration, and version lifecycle management.

Recipev1.0.0

a7-recipe-blue-green

Recipe skill for implementing blue-green deployments using the a7 CLI in API7 Enterprise Edition. Covers creating two service-backed environments, switching traffic via route service_id updates, rollback procedures, and config sync workflows with gateway group scoping.

Recipev1.0.0

a7-recipe-canary

Recipe skill for implementing canary releases using the a7 CLI in API7 Enterprise Edition. Covers gradual traffic shifting with the traffic-split plugin, header-based canary routing, monitoring checkpoints, and full promotion or rollback workflows.

Recipev1.0.0

a7-recipe-circuit-breaker

Recipe skill for implementing circuit breaker patterns using the a7 CLI in API7 Enterprise Edition. Covers the api-breaker plugin, unhealthy thresholds, healthy recovery, response code classification, and integration with service health checks.

Recipev1.0.0

a7-recipe-graphql-proxy

Recipe skill for implementing GraphQL proxying patterns using API7 Enterprise Edition (API7 EE) and the a7 CLI. Covers operation-based routing, per-operation rate limiting, REST-to-GraphQL conversion, and enterprise security for GraphQL APIs.

Recipev1.0.0

a7-recipe-health-check

Recipe skill for configuring backend health checks using the a7 CLI in API7 Enterprise Edition. Covers active health checks, passive health checks, combining both, healthy/unhealthy thresholds, and service-backed route wiring.

Recipev1.0.0

a7-recipe-mtls

Recipe skill for configuring mutual TLS (mTLS) using the a7 CLI in API7 Enterprise Edition. Covers SSL certificate management, upstream mTLS to backend services, client certificate verification, and end-to-end mTLS setup from client through API7 EE to upstream.

Recipev1.0.0

a7-recipe-multi-tenant

Recipe skill for implementing multi-tenant patterns using API7 Enterprise Edition (API7 EE) and the a7 CLI. Covers gateway-group isolation, consumer policies, service-backed tenant routes, and credential-based tenant access.

Corev1.0.0

a7-shared

Core skill for working with the a7 CLI — the command-line tool for API7 Enterprise Edition. Provides project conventions, command patterns, dual-API architecture, and development workflow. Load this skill when working on a7 source code, adding new commands, writing tests, or modifying any a7 component.

Install

Install every skill with one command — it downloads the packs into ~/.claude/skills for Claude Code:

curl -fsSL https://raw.githubusercontent.com/api7/a7/master/install.sh | sh

Then ask your agent to configure API7 Gateway in natural language — no slash command to memorize.

Other agents

The same skills work with any agent that reads Markdown skills. Install them into a different directory with --dir (or the SKILLS_DIR environment variable) — for example, a project-local Cursor rules directory:

curl -fsSL https://raw.githubusercontent.com/api7/a7/master/install.sh | sh -s -- --dir ./.cursor/rules

Prefer to install by hand? Clone api7/a7 and copy skills/**/SKILL.md into your agent's skills directory.

Prerequisites

  • The a7 CLI installed and on your PATH (go install github.com/api7/a7/cmd/a7@latest)
  • A running API7 Enterprise Edition instance with control-plane and Admin API access
  • An API7 EE access token
  • A target gateway group

Example: end to end

A single request like "add key-auth to /orders and rate-limit it to 100 rpm" loads the a7-plugin-key-auth and a7-plugin-limit-count skills. The agent generates the route configuration and applies it with the file-based a7 command, scoped to your gateway group:

# route.yaml
uri: /orders
upstream_id: orders-upstream
plugins:
key-auth: {}
limit-count:
count: 100
time_window: 60
key: remote_addr
rejected_code: 429
a7 route update orders -g default -f route.yaml

Frequently asked questions

What are agent skills for API7 Gateway?

Agent skills for API7 Gateway are SKILL.md knowledge packs that teach an AI coding agent how to configure and operate a live API7 Enterprise Edition gateway through the a7 CLI. Each skill covers one plugin, recipe, or operator workflow and the exact commands to run.

Can I use API7 Gateway with Claude Code?

Yes. Install the API7 agent skills into Claude Code, then describe what you want your gateway to do in natural language — Claude Code loads the matching skill and runs the underlying a7 CLI commands against your API7 Enterprise Edition control plane and Admin API.

Which AI agents support the API7 skills?

Any agent that understands the Agent Skills convention, including Claude Code, Cursor, GitHub Copilot, Windsurf, and OpenCode. The skills are plain Markdown files with no runtime or lock-in.

How do I install the API7 AI agent skills?

Install every skill with one command — for Claude Code: curl -fsSL https://raw.githubusercontent.com/api7/a7/master/install.sh | sh (it copies the packs into ~/.claude/skills). To install into another agent’s directory, pass it through: curl -fsSL https://raw.githubusercontent.com/api7/a7/master/install.sh | sh -s -- --dir ./.cursor/rules.

What is the a7 CLI?

a7 is the command-line tool for API7 Enterprise Edition. It wraps the API7 EE control-plane API and the APISIX Admin API to manage gateway groups, routes, services, consumers, certificates, and plugins from your terminal — all runtime operations are scoped to a gateway group.

What can the skills configure?

The catalog spans day-to-day API7 Gateway work: 29 plugin skills (authentication, rate limiting, observability, AI proxying, and more), 8 operational recipes (canary, blue-green, circuit breaking, health checks, mTLS), 2 role personas, and shared CLI conventions.

Learn more