全部能力

Web research skill using Tavily API for search, extract, crawl, map, and structured research tasks. Use when you need latest information, extract content from…

Checks layer leakage in method signatures, missing DTOs, entity leakage to API, inconsistent error contracts. Use when auditing API contracts.

OpenTelemetry with Grafana stack. Covers OTel SDK instrumentation for Go/Java/Python/Node.js/.NET, OTLP protocol and endpoint configuration, sending telemetry to Grafana Cloud via OTLP endpoint, Grafana Alloy as OTel collector, sampling strategies, Kubernetes OTel Operator, and migration from other observability tools. Use when instrumenting apps with OTel, configuring OTLP endpoints, setting up collectors, or migrating to OpenTelemetry.

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Story-level quality gate with 4-level verdict (PASS/CONCERNS/FAIL/WAIVED) and Quality Score. Use when Story is ready for quality assessment.

Guidelines for using TanStack Query (React Query) for server state management, data fetching, caching, and synchronization

Deploy and manage web apps using Azure App Service with auto-scaling, deployment slots, SSL/TLS, and monitoring. Use for hosting web applications on Azure.

Provide comprehensive techniques for penetration testing AWS cloud environments. Covers IAM enumeration, privilege escalation, SSRF to metadata endpoint, S3…

Clerk auth with API Keys beta (Dec 2025), Next.js 16 proxy.ts (March 2025 CVE context), API version 2025-11-10 breaking changes, clerkMiddleware() options, webhooks, production considerations (GCP outages), and component reference. Prevents 15 documented errors. Use when: API keys for users/orgs, Next.js 16 middleware filename, troubleshooting JWKS/CSRF/JWT/token-type-mismatch errors, webhook verification, user type inconsistencies, or testing with 424242 OTP.

Executes Story tasks in priority order (To Review, To Rework, Todo). Use when Story has planned tasks ready for implementation.

Verifies bootstrapped projects via build, test, and container health checks. Use when validating project setup completeness.

Sets up logging, error handling, CORS, health checks, and API docs. Use when adding cross-cutting concerns to backend projects.

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling…

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls…

Scores each test by portfolio value and returns KEEP/DELETE/MERGE/REWRITE. Use when pruning test-suite cost.

基础模板生成器代理技能 - 使用 $agent-base-template-generator 调用

Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build config issues. Use when auditing build health.

Fixes tasks in To Rework by applying reviewer feedback, then returns to To Review. Use when task was rejected during review.

Sets up linters, pre-commit hooks, and test infrastructure. Use when adding code quality tooling to a project.

Package any component into a self-contained, isolated widget with shadow DOM, scoped styles, and multi-framework support