全部能力

Audits whether test results can be trusted: flakiness, isolation, real external dependencies, time/random/order dependency, and shared state. Use when auditing…

Analyzes Story and builds optimal task plan (1-8 tasks), then routes to create or replan. Use when Story needs task breakdown or replanning.

RICE-scores Stories with market research and generates prioritization table. Use when Stories need business priority ranking for sprint planning.

Creates reference docs (ADRs, guides, manuals) for nontrivial tech stack choices. Use when project needs justified architecture decision records.

Configures ESLint, Prettier, Ruff, mypy, and .NET analyzers. Use when setting up linting and formatting for a project.

Generates .NET Clean Architecture backend structure from entity definitions. Use when bootstrapping .NET backend projects.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences…

Checks DRY, KISS/YAGNI, error handling, DI patterns. Use when auditing code principles compliance.

Checks redundant fetches, N+1 loops, over-fetching, missing bulk operations, wrong caching scope. Use when auditing query efficiency.

Creates task management docs (kanban board, workflow rules) with configured tracker integration. Use when setting up task tracking for a project.

Crafts high-converting outreach messages and email sequences for cold outreach, LinkedIn DMs, and follow-ups. Use when user needs personalized outreach…

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

Generate CI/CD configuration for Linear Release. Use when setting up

Node.js development guidelines covering Payload CMS, Vue.js with TypeScript, and general TypeScript best practices

Less CSS best practices and coding guidelines for maintainable, modular stylesheets

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.

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

Scaffolds new React projects or restructures monoliths to component-based architecture. Use when setting up frontend structure.

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

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